ESTIMATION EMBARQUEE DU RISQUE ROUTIER
CORRELEE A L’ACCIDENTOLOGIE

ESTIMATION EMBARQUEE DU RISQUE ROUTIER CORRELEE A L’ACCIDENTOLOGIE :
UN PROBLEME ENTIEREMENT RESOLU ET UN PRODUIT SUR ETAGERE DISPONIBLE

par NEXYAD

INTRODUCTION

Mesurer la sécurité routière en fonction du contexte vécu par le conducteur est un sujet qui intéresse :
. les constructeurs automobiles, qui peuvent informer le conducteur d’éventuels dangers
. les développeurs du véhicule autonome qui ont besoin de prouver que le robot de conduite est
capable de minimiser le risque routier
. les gestionnaires de flottes et les assureurs qui souhaitent mesurer le risque pris par les conducteurs
. les gestionnaires de l’infrastructure routière qui cherchent à aménager les routes pour baisser le risque
d’accident

La société NEXYAD a développé un module embarqué, SafetyNex, qui permet d’estimer en temps réel le risque.

LES IDEES PRECONCUES CONCERNANT LE STYLE DE CONDUITE ET L’ACCIDENTOLOGIE

Beaucoup d’essais ont été réalisés ou en cours de réalisation, surtout par les assureurs et les gestionnaires
de flottes, pour mesurer ce qui s’appelle « le style de conduite ».

L’hypothèse est que certains conducteurs sont plus « nerveux » que d’autres, et que cela a un impact sur
l’accidentologie : ceux qui accélèrent ou freinent assez souvent brutalement seraient des « mauvais conducteurs », alors que ceux qui ont une conduite plus tranquille seraient des « bons » conducteurs.
Cette hypothèse est contredite par les faits. Il n’y a pas de liaison statistique entre le style de conduite et
l’accidentologie.

Formellement, chacun conçoit très bien que si un conducteur conduit très tranquillement, sans freiner, sans
accélérer, à 30 km/h, et qu’il grille un stop … son style de conduite est tranquille mais très accidentogène.

On voit alors qu’au-delà de la liaison statistique éventuelle, il ne peut y avoir de relation de cause à effet.
Toutes les expérimentations qui ont été menées ont conduit à ce résultat.
Toutes celles qui seront menées, basées sur le seuillage plus ou moins intelligent des valeurs d’accélérations
sont vouées à l’échec. Il ne faut pas confondre éco-conduite et conduite sûre.

Le style de conduite en lui-même ne peut être exploité qu’en regard :
. de l’infrastructure sur laquelle le véhicule évolue
. du trafic (présence d’autres usagers de la route)
. des conditions météo (visibilité, adhérence, …)
. du niveau d’attention du conducteur (distraction, hypovigilance, endormissement, …)

NEXYAD a développé une solution évolutive capable de prendre en compte tous ces facteurs.
SafetyNex en version « labo » est donc capable d’estimer le risque lié à la conduite de façon complète.
La version 2.1 de SafetyNex, en cours de déploiement, prend en compte l’adéquation du style de conduite au type et à la forme de l’infrastructure (ruptures sur les itinéraires, virages, passages piétons, croisements, …).

Cette version a été volontairement réduite car elle donne déjà une corrélation du risque estimé avec
l’accidentologie de plus de 90%, et elle est déployable à très bas coût :
. sur smart phone
. sur boîtier électronique (développé par un équipementier automobile de rang 1, sans utilisation de la prise OBD)

CORRELATION ENTRE L’ESTIMATION DU RISQUE PAR SafetyNex V2.1 ET L’ACCIDENTOLOGIE

NEXYAD a participé à des programmes de recherche collaborative depuis 2001, et a pu de cette manière collaborer avec des experts de l’équipement des routes.

En particulier, le programme de recherche SARI a conduit à des travaux de détection de ce que les experts appellent une « rupture sur l’itinéraire ». Par exemple, un virage peut constituer un grand danger lorsqu’il arrive derrière une longue ligne droite, alors que le même virage ne sera pas dangereux sur une route de montagne.

NEXYAD a publié un article lors de la conférence sur la Sécurité routière le 6 Mai 2010 à Paris : PRAC 2010 Prévention des Risques et Aide à La Conduite, Session 1 Caractérisation du risque routier vs. infrastructure « Evaluation du risque routier pour l’aide à la conduite ou le diagnostic de l’infrastructure », Johann Brunet, Pierre Da Silva Dias, Gérard Yahiaoui, PRAC 2010, Mai 2010, Paris.

Les travaux qui ont conduit à cette publication ont été intégrés au produit SafetyNex. Cela signifie que par construction, le risque estimé par SafetyNex est corrélé à l’accidentologie. Cela est vrai par construction, et NEXYAD a réalisé des essais sur routes, en ville, sur autoroutes, en zones urbaines, et a pu valider ce résultat.

PRINCIPE DE FONCTIONNEMENT DE SafetyNex V2.1

SafetyNex est un système à base de connaissances (système expert) qui applique les règles des experts de l’équipement. Ces règles sont rangées dans une base de règles sous une forme mathématique qui permet de les adapter de manière graduelle aux caractéristiques réelles de l’infrastructure.

Les entrées obligatoires sont :
. la carte de navigation et le GPS : afin de scruter la forme et les caractéristiques de l’infrastructure située en aval du véhicule (virages avec leur rayon de courbure, points d’intérêt de type passage piéton, croisement de routes, etc …)
. la vitesse instantanée du véhicule.

A partir de ces deux entrées, SafetyNex évalue, par application des règles, l’adéquation de la vitesse d’approche du véhicule en fonction du niveau de difficulté et de danger d’accidents de l’infrastructure.

Un conducteur sportif qui accélère fort, freine fort, mais passe les endroits dangereux à faible vitesse aura un risque faible.

Un conducteur tranquille qui grille un stop à 30 km/h mais qui n’accélère ni ne freine presque jamais aura un risque très élevé.

On le voit, SafetyNex n’est pas corrélé à la valeur absolue des accélérations, mais à l’adaptation FACTUELLE de la vitesse au type de difficulté de l’infrastructure, à chaque instant.

Des entrées supplémentaires (optionnelles) sont déjà prévue, et peuvent permettre de moduler l’estimation du risque pour la rendre encore plus précise :
. l’adhérence mobilisable (si l’on dispose d’un capteur, à connecter à l’entrée prévue à cet effet de SafetyNex)
. la météo (si l’on dispose de l’information spatio temporelle, à connecter à l’entrée prévue à cet effet de SafetyNex)
. la visibilité atmosphérique (si l’on dispose d’une mesure adéquate : exemple : une caméra et le module de mesure de visibilité atmosphérique VisiNex)
. la distance à d’éventuels obstacles ‘si l’on dispose d’une estimation adéquates : exemple : un radar, un lidar, ou une caméra avec les modules RoadNex et ObstaNex)
. un coefficient de distraction du conducteur (si l’on observe le conducteur avec une caméra et/ou si l’on surveille l’activité de son téléphone mobile, etc …)

Toutes ces entrées supplémentaires sont déjà prévues dans SafetyNex, mais elles augmentent le coût de déploiement de la solution en impliquant des capteurs (caméra, …) et de la puissance de calcul supplémentaire en amont de SafetyNex pour traiter les signaux et les images issus des capteurs optionnels.

L’utilisation de SafetyNex V2.1 avec uniquement les entrées obligatoires permet déjà une corrélation très forte du risque estimé avec l’accidentologie. Nous préconisons d’implanter cette version, déjà infiniment plus efficace que toutes les mesures embarquées que NEXYAD a pu découvrir dans son activité de veille.
L’intérêt de SafetyNex est que l’avenir est déjà assuré : la loi de Moore faisant baisser rapidement le coût de l’électronique et de l’informatique embarquées, SafetyNex est prêt à accueillir les entrées supplémentaires, dès que les utilisateurs voudront intégrer les caméras et les capteurs.

UTILISATIONS TYPES DE SafetyNex V2.1

. Sociétés d’assurances :
      – Pay how you Drive
      – Modulation prédictive du bonus malus : le même accident dans les mêmes conditions ne conduit pas aux mêmes conclusions en fonction de l’historique cumulé et de l’enregistrement des dernières secondes du risque de SafetyNex.
      – Génération muette d’une variable de risque, corrélée à l’accidentologie, pour aider les actuaires à affiner la tarification

. Les gestionnaires de flottes

. Equipementiers automobile :
      – Alarme sur risque
      – Navigation intelligente capable de conseiller le conducteur

. Ingénieurs et chercheurs du véhicule autonome :
      – Evaluation de la qualité de conduite générée par le robot

CONCLUSION

L’estimation embarquée du risque routier est aujourd’hui un problème résolu par un produit sur étagère, SafetyNex, déployable dès maintenant
à bas coût sur :
. téléphones mobiles
. boitier électronique d’un équipementier de rang 1 de l’automobile.

Et déjà prévu pour intégrer (dès que le coût est jugé acceptable) des capteurs d’adhérence et des caméras (par exemple) pour estimer le trafic et la visibilité atmosphérique, ainsi que des informations telles que la météo et la distraction du conducteur.

Tous ces éléments sont déjà traités par le système de règles de SafetyNex, si bien que l’outil peut évoluer rapidement à chaque baisse de coût des éléments capteurs et de la puissance de calcul rattachée à ces éléments capteurs.

Pour déployer SafetyNex, contacter NEXYAD : Olivier BENEL obenel@nexyad.net 01 39 04 13 60

REAL TIME ONBOARD RISK ESTIMATION
CORRELATED WITH ROAD ACCIDENT

REAL TIME ONBOARD RISK ESTIMATION CORRELATED WITH ROAD ACCIDENT :
AN ENTIRELY SOLVED PROBLEM AND A PRODUCT ALREADY AVAILABLE FOR DEPLOYMENT

by NEXYAD

(Version Française ici)

INTRODUCTION

Measuring road safety in the context experienced by the driver is a topic of interest for several activities :
. car manufacturers, who can inform the driver of potential dangers
. autonomous vehicle developers who need to prove that the driving actually minimizes risk of accident.
. fleet managers and insurance companies who wish to measure the risk taken by drivers (how they drive)
. managers of road infrastructure that alway change infrastructure to adapt and lower the risk of accident

The company NEXYAD has been developing since 2001 an embedded onboard module, SafetyNex, to
estimate in real time the risk of accident.

PRECONCEIVED IDEAS ABOUT ROAD ACCIDENTS AND DRIVING STYLE

Many trials have been completed or in progress, particularly by insurance companies and fleet managers,
In order to measure what is called the “driving style”.

The assumption is that some drivers are more “nervous” than others, and that this has an impact on the accident: those that speed up or slow down quite often brutally would be “bad drivers” while those with a quieter driving style would be “good” drivers.
This assumption is contradicted by the facts. There is no statistical connection between the driving style and
the accident.

Formally, one can easily fancy very well that if a driver operates very quietly, without slowing, without
accelerating at 30 km / h, and if this driver passes through a stop road sign without braking … then the driving style is quiet but very accident-prone.
We then see that beyond the possible statistical link (that doesn’t exist), there can be no relationship of cause and effect.

All experiments that were conducted led to this result.
All those that will be conducted, based on more or less intelligent thresholding of the acceleration values are doomed to failure.
Do not confuse eco-driving and safe driving.

Driving style cannot be interpreted itself without context description :
. infrastructure shape and characteristic, on which the vehicle is traveling
. traffic (presence of other road users)
. weather conditions (visibility, grip, …)
. level of driver vigilance (distraction, drowsiness, sleep …)

NEXYAD has developed a scalable solution capable of taking into account all these factors.
SafetyNex is therefore able to estimate the risk of driving using all those variables.
Version 2.1 of SafetyNex, under deployment, takes into account the adequacy of driving style with the type and shape of infrastructure (breaks on route characteristics, turns, pedestrian crossings, intersections …).

This version has been intentionally reduced to « driving style vs infratructure characteristics », because it already gives a 90% correlation with accident and because this version is deployable at very low cost:
. on smart phone
. electronic device (developed by an automotive tier one company), without using the OBD socket)

CORRELATION OF RISK OF ACCIDENT ESTIMATED BY SafetyNex V2.1 AND ACCIDENT

NEXYAD participated in collaborative research programs since 2001, and worked then with experts from the road equipment.

In particular, SARI research program led to detecting what experts call “Break on the route characteristics”. For example, a turn with a big curve may be a danger when it arrives behind a long straight line, while the same curve will not be dangerous bend on a mountain road.

NEXYAD published a paper at the conference on road safety May 6, 2010 in Paris: PRAC 2010
Risk Prevention and Save The Conduct, Session 1 Characterization of road risk vs. infrastructure
« Evaluation du risque routier pour l’aide à la conduite ou le diagnostic de l’infrastructure », Johann Brunet, Pierre Da Silva Dias, Gérard Yahiaoui, PRAC 2010, Mai 2010, Paris.

The work that led to this publication were integrated in the available product SafetyNex. This means that by construction, the risk estimated by SafetyNex is correlated to the accident. This is true by construction, and NEXYAD conducted tests on roads, downtown, on motorways in urban areas, etc … and was able to validate this result.

PRINCIPLE OF SafetyNex V2.1

SafetyNet is a knowledge based system (expert system) which applies rules of the experts of the equipment.
These rules are stored in a rules data base in a mathematical form that can adapt to gradual actual characteristics of the infrastructure.

Required inputs are :
. the navigation map and the GPS: To examine the shape and type of the infrastructure located downstream of the vehicle (turns with their radius of curvature, points of interest like pedestrian crossing, crossroads, etc …)
. the instantaneous vehicle speed

From these two inputs, SafetyNex evaluates, by applying the rules, the adequacy of the driving speed of the vehicle to difficulty and danger of infrastructure.

A sporty driver accelerating hard, braking hard, but passing dangerous places at low speed will be scored with a low risk.
A quiet driver that passes through a stop road sing at 30 km / h without braking will be scored with a high risk.
A brutal braking cannot be considered as « bad driving » if it is necessary to avoid an accident …

We see then, that SafetyNex risk estimation is not correlated with the absolute value of acceleration, but with ACTUAL speed adaptation to difficulty and danger of the infrastructure, in real time.

Additional inputs (optional) are already scheduled, and can afford to modulate the estimated risk to increase acuracy of SafetyNex :
. grip (if one has a sensor to connect to the input provided for the purpose of SafetyNex)
. weather report (if one has the temporal and spatial information)
. atmospheric visibility (if one has adequate measure: example: a camera and the measuring module of atmospheric visibility : VisiNex)
. distance to potential obstacles (if it has an adequate sensor : eg radar, lidar, or camera with RoadNex ObstaNex modules)
. a driver distraction factor (if the driver is observed with a camera and / or if one monitors the activity of mobile phone, etc …)

All these additional inputs are already ready to be used by SafetyNex but of course, they increase the cost of deployment, involving sensors (camera, …) and additional computing power before getting in SafetyNex to process signals and images from the optional sensors.

Using SafetyNex V2.1 with only the required inputs already allows a very high correlation of the estimated risk with the accident. We recommend to implement this version, already infinitely more effective than any other onboard measurements.
The interest of SafetyNex is that the future is already assured: Moore’s Law by rapidly lowering the cost of electronics and embedded computing, SafetyNex is ready to process the additional inputs, when users want to integrate cameras and sensors.

TYPICAL USES OF SafetyNet V2.1

. Insurance Companies:

– Pay how you drive
– Predictive modeling of bonus malus: the same accident under the same conditions does not lead to the same conclusions based on accumulated historical and recording the last seconds risk SafetyNex
– Generation of a dumb risk variable, correlated to the accident, to help actuaries refine pricing (big data)

. Fleet managers

. Automotive equipment suppliers:

– Alarm on risk
– Intelligent Navigation able to advise the driver

. Engineers and researchers from autonomous vehicle:

– Driving Quality Assessment generated by the robot

CONCLUSION

Embedded estimation of road risk of accident is now a problem completely solved by a product available for deployment, SafetyNex.
SafetyNex is deployable at Low cost on:
. mobile phones
. electronic device of a Automotive Tier 1 supplier (without plugging the OBD).

And SafetyNex already planned to integrate (once the cost is acceptable) grip sensors and cameras (for example) to estimate traffic and atmospheric visibility, as well as information such as weather and driver distraction.

All of these are already processed by SafetyNex rules based system, so that the tool can quickly evoluate with each decrease in the cost of sensor elements and cost of computing power needed to compute sensors outputs.

To deploy SafetyNex, contact NEXYAD: Olivier BENEL obenel@nexyad.net +33 1 39 04 13 60

Onboard road safety/risk Measurement correlated to accidents



Onboard road safety/risk Measurement correlated to accidents :
How to use SafetyNex V2.1 for Insurance applications, and for
Automotive applications (ADAS & autonomous vehicle)

by NEXYAD


INTRODUCTION: Description of 2.1 SafetyNex

SafetyNex is a software module proposed by the French company NEXYAD. This module aims to match the driving style (acceleration, vehicle speed) with the danger characteristics of infrastructure.

SafetyNex development started in 2001 and benefited from three national collaborative research programs (PREDIT and FUI) that allowed NEXYAD modeling expertise of road equipment notation accident-prone infrastructure.

Indeed, the accident-prone nature of a local infrastructure, cannot be deduced from statistical studies on this local element, for the simple reason that accidents are rare events.A driver has one accident every 70 000 km.

To investigate the accident, the experts of the equipment mainly use two methods:
. aggregated statistics at national and European level : it provides large numbers of accidents and thus make statistics relevant. But heterogeneous infrastructure through Europe makes it difficult to project results on a local infrastructure that has its own characteristics, sometimes far from the average characteristic in France or Europe.
. the observation of “near misses” or « almost accident » as they are numerous : most potential accidents can be nearly avoided by drivers. Experts of infrastructure developed observatories for those danger situations and it brings useful information.

From these elements, the experts of the infrastructure have published a set of rules for predicting accidents, based on characteristics, the accident-prone characters of a piece of infrastructure.
For example, a bend may be accident-prone if its radius greatly shortens in its middle (curve which closes), but a “normal” curve may become dangerous if it comes after a long distance of straight line (this is called “break out on the pathway “).

NEXYAD integrated all these rules in SafetyNex and has made numerous tests on real world to validate the efficiency of scoring danger.

SafetyNex V2.1 reads on-board navigation map that gives infrastructure characteristics , downstream of the vehicle, and then SafetyNex scores the relevancy of the driving style, knowing the shape of the road ahead and other important things (pedestrian pathway, …).

Note: in a higher version (already being tested), SafetyNex may also reflect the presence of other users on the road (cars, trucks, bicycles, motorcycles, pedestrians …) by coupling it to RoadNex (road detection by camera), and ObstaNex (obstacles detection by camera).
But this version will require to have appropriate computing power to process videos. The Moore law lets us think i twill be easy and cheap in 2 or 3 years.
For now, we think that adaptation of the driving type with infrastructure characteristics meets a real issue and SafetyNex V2.1 is the only available (and for sale) module in the world for performing this function.

The output computed by SafetyNex is the road safety risk, between 0 and 100%, at every moment.

It is possible to use SafetyNex in real time to alert the driver.
It also may be used off-line, aggregating the risk : SafetyNex used to complete big data with revelant variables to study the road safety risk, in a statistical way.

SafetyNex is available in three types of running environments:
. PC under Windows or Linux
. Electronic device of an Automotive Tier One Company, for the new vehicles and aftermarket
. smartphones


SafetyNex V2.1 FOR USE OF INSURANCE

Insurance Companies have several ways to use SafetyNex V2.1:

. free distribution of the SafetyNex App for smartphones to all their customers :
In this case, the business model is to seek partners who want to reduce their cost of acquiring customers online.
In fact, when you divide the advertising budget of a major retailer (Amazon, Fnac, Darty, …) by the number of purchases, there are about 30 euros (cost of a customer).
The idea of NEXYAD then is to propose a serious game that “gives” points to drivers who behave well.
These points are converted into “coupons” with one or more distributors. The drivers will go on the website in order to validate coupons by purchasing products. In doing so (spotted digitally with flash code …), the distributor will give back 15 euros : 7,5 euros for the cupons, and 7,5 euros for the Insurance Company that distributed the NEXYAD App to their millions of customers. The insurer therefore makes money and share revenue with NEXYAD and its technology partners.

This solution is particularly interesting for several reasons:
. the insurance company earns money directly on millions of purchases.
. drivers do their best to earn coupons, and therefore change their driving behavior to achieve it.
The insurer therefore modifies in a sustainable way the driving style, and contributes to the decline in the number of accidents. The Communications Department of the the Insurance company may use this fact for communicating it to the public.
. the largest distributors lower their customers acquisition costs and they can then lower their advertising budget
. the driver improves self safety, and is able to purchase more.
. distribution in an electronic device :
The electronic device has the advantage of being still operational without driver intervention.
This solution is particularly interesting for business fleets, and allows to quickly and efficiently initiate a type of pricing system “pay how you drive” that may be seen as an extension of the bonus / malus system, but with a predictive power.
. constitution of big data for actuaries:
Risk can be recorded onboard, or in aggregate, giving statisticians a new variable for more accuracy on pricing.


SafetyNex V2.1 FOR USE IN ADAS AND AUTONOMOUS CAR APPLICATIONS

The road safety risk measurement is of course interesting for automotive applications :
. SafetyNex read the shape of infrastructure downstream of the vehicle (electronic horizon), and can therefore help to choose which types of sensors are relevant.
. SafetyNex can estimate the maximum distance targetable by sensors (radar, camera, …) depending on the shape of the infrastructure (turn, climb, …)
. During a delegation of driving, the robot drives the vehicle and then SafetyNex V2.1 can estimate the road safety related to the automatic driving.

The road safety score can be used in several ways:
. Off-line: the engineers who design and develop driving delegation system uses the risk score of SafetyNex V2.1 as a feedback, and try to minimize it by successive tests.
. On-line: the risk score is used by the decision-making system to generate actions that lead to the lowest possible risk.


CONCLUSION

SafetyNex V2.1 is now available and NEXYAD is currently working on deployment opportunities worldwide at the beginning of 2016.
This module is unique and has a direct effect, if properly used, on road safety.

For more information: sales@nexyad.net


DEMO WITH SOUND IN URBAN TRAFFIC

Put the sound on for this demo with vocal explanations :


Visibility Measurement for Road Safety

Visibility Measurement for Road Safety by NEXYAD

INTRODUCTION

Visibility is one of the structural elements of road safety. Indeed, the sense of sight is the only one that let us perceived the future path of the vehicle and then let us act on it : the driver “can see” in front of the vehicle, he predicts where the vehicle will go, and he can act on the controls (brake, steering wheel, …) in order to control the trajectory.

No other way allows us to anticipate.

If we model the task of driving with an automatic control engineering scheme, then we can notice that vision is used quite everywhere :

Set Point of Trajectory Modification

Vision plays a critical role in driving task, and what sizes the efficiency of this sense is « visibility ».

Visibility can be affected by many kinds of factors:
. the absence or insufficience of light (that is why the infrastructure is sometimes illuminated at night, and why vehicles are equipped with lighting.
. rain deposited on the windshield (that is why vehicles are equipped with wipers)
. mist on the windshield (that is why vehicles are equipped with demisting systems)
. humidity, fog or mist suspended in the air in the road scene.

Experts of road infrastructure add elements to enhance the visibility of the path :
. lane markings (white lines), reflective elements.

Similarly, automobile experts equip their vehicle with systems enabling them to improve visibility for the driver, but also allowing the vehicle to be more easily seen by other drivers.

We then understand that measurement of visibility is an important area of potential improvement of road safety in via ADAS.

VISIBILITY MEASUREMENT

The founders of the company NEXYAD have been working since the 80s on the measurement of visibility, early on military applications.
Indeed, it is the military who have studied since the 60’s which criteria allow human visual perception system to detect objects on their clutter.

For the military, the constant search for stealth (camouflage, for example) requires modeling the performance of the detection by human, depending on the light of a scene in the visible wavelength.

The work carried out tests on panels of thousands of soldiers, and led to predictive models for human vision of the ability to detect objects or not, depending on the image quality.
NEXYAD is one of the very few companies in the world to hold these models and have experience of their implementation for more than 20 years.
In simplified terms, we can consider that our eyes and brain need, depending on the size of the objects to be detected, a different contrast level.
We can then compare the contrast available in a scene (eg a road scene) with needed contrast to detect, , for each size of objects.

The comparison results in two scores :
. the apparent size of the smallest detectable object : as the apparent size of an object decreases with distance, it can then be deduced the maximum distance of detection for a reference object (a car, a truck, a pedestrian). Distances will obviously be different for every object because they don’t have the same size. Johnson criteria give let also estimate the maximum distance for object recognition, and the maximum distance for object identification.
. ease of interpretation of the visual scene. NEXYAD summarized this in a score computed from available and needed contrast: the Visual Quality Score (VQS).

This measure of visibility enables automotive application objectify the subjective. NEXYAD has developed two product lines from the same technology :

. a visibility test bench : VisiNex Lab https://nexyad.net/Automotive-Transportation/?page_id=159

VisiNex Lab

Place a vehicle on a test bench and VisiNex Lab measuring visibility among time. If there are disturbs of visibility from rain, for example (using NEXYAD RainNex rain machine, or another rain machine), then we see scores for degraded visibility. If one starts the vehicle visibility restoration systems (eg in the case where the disturbance is the rain : the wipers), then we measure the performance of the visibility restoration.
VisiNex Lab is used by the automotive industry and is still the only tool for measuring the performance of wipers, demisting system, lighting system, …

. an embedded module for ADAS : VisiNex Onboard https://nexyad.net/Automotive-Transportation/?page_id=438
VisiNex Onboard measures the image quality and predicts the detection power of the driver and onboard artificial vision modules. So we get a rating of confidence for artificial vision systems.
Again, NEXYAD is the only non military company to dispose of this technology.

Road Scene

CONCLUSION

Every tier one company or car manufacturer should use NEXYAD modules VisiNex in order to measure performance, robustness, and reliability of their wipers, lighting, and of their camera-based ADAS.
VisiNex Onboard is currently under implementation into the asynchronous real time framework RT-MAPS.

For more information : sales@nexyad.net

SafetyNex for Onboard Road Safety Measurement

SafetyNex for Onboard Road Safety Measurement by NEXYAD

INTRODUCTION

Car manufacturers and insurance companies both need a system that would estimate in real time the risk taken by the driver.
Most commercial applications use to consider that a driver that do not accelerate much doesn’t take risk, and that a driver that drives more sporty is dangerous.
However, insurance companies statisticians could notice that there no correlation between the driving style and the accidents.
It is completely obvious : danger comes when the driving style is not adapted to the infrastructure. So driving style doesn’t has no meaning by itself.

NEXYAD company has been working since 1995 on onboard risk estimation, and recently launched their module SafetyNex that estimates a risk which is correlated (by construction) with accidents.

SafetyNex is the result of three collaborative French research programs :
. ARCOS
. SARI
. SERA

SafetyNex measures onboard the adequacy of driving style (and in particular the speed of the vehicle) with the characteristics of the infrastructure : adequacy of the current speed and initiated acceleration to the radii of curvature of bends downstream, to the presence of downstream crossings, or pedestrian crossings, … etc.

It is possible to add to SafetyNex optional inputs such as :
. weather report,
. maximum grip
. atmospheric visibility (rain, fog …)
. distance to obstacles (coming from an ADAS system) and in this case, we use not only infrastructure characteristics but also trafic flow information that describe the way other users move on the same infrastructure.

Similarly, can be integrated into SafetyNex data from characteristics of ADAS in order to measure the adequacy of these driver assistance systems to the situation experienced by the vehicle on the infrastructure.
For example, if the vehicle has radar or camera, the data of the opening angle enable SafetyNex (which read shape of the infrastructure from the onboard navigation map) to compute the distance of geometric visibility, not for the driver, but for embedded artificial perception systems.

Cone of Perception

EXAMPLE OF USE IN URBAN TRAFFIC

The example below shows the predictive nature of safetyNex : when you get in an intersection, it’s a little before that you must slow down because you can not know what is likely to emerge from this intersection. However, when one is in the intersection, it is not dangerous to re-accelerate. This is the way that safe drivers use to drive.

Therefore, the risk score is not correlated to the value of the deceleration or acceleration but to the adequacy of speed to potential dangers of the infrastructure. You may drive sporty or lazy and have the same good or bad safety score computed by SafetyNex.

Video with sound (spoken explanations)

CONCLUSION

SafetyNex is now available for sale and is operating in the following environments:
. Framework RT-MAPS PC : This version is for automakers researchers, scientists of tier one techno suppliers, statisticians and actuaries of insurance companies. It allows real-time replay, in order to see what areas make the risk climb, it also allows to correlate the new variable (risk) with all other variables available, and for car manufacturers, it lets develop ADAS based on this module.
RT-MAPS is interfaced with the Data Base Management Systems, which is convenient to apply SafetyNex on the company’s information systems.
. electronic device of an automotive tier one company : the announcement will be made soon by the automotive tier one techno supplier.
. mobile phones (December 2015), which will allow everyone to have this road safety module.

To know more : sales@nexyad.net

Visibility Measurement for ADAS and Autonomous Vehicle

Visibility measurement for ADAS and Autonomous Vehicle
By NEXYAD

Advanced Driver Assistance Systems (ADAS), and partial or total delegation of car control systems will integrate more and more cameras. Those cameras are used to capture video and images are inputs for obstacle detection algorithms, road detection algorithms, detection of pedestrians systems, …

However, a camera can “see” only under certain conditions, and the algorithms used to exploit image need a certain level of image quality. It is possible that some algorithms test themselves if they are in a case of good image quality or not, but in the general case, they don’t, and it is then prudent to have a qualification system that is independent of the detection systems.

The company NEXYAD has worked for years on atmospheric visibility measurement for military application, and was able to develop predictive models of the ability for a human to detect objects. This work can be easily set to pass from a performance prediction of the human vision to a prediction of performance for a machine vision system.

The models consist in comparing the contrast in the scene with the required contrast for detection and / or pattern recognition.
Such a system requires that is respected a compromise between several characteristics of the image:
. number of different gray levels (for a digital camera, it depends on the number of bits)
. size of the objects to be detected
. contrast of objects from their background

Note for Automotive engineers : a performance specification for a camera-based detection system, without giving the minimum contrast, le maximum number of pixels, the number of bits … does NOT have any sense. It is important to know that fact in order to make applications that work and application that know when they work.
For instance, we are all able to detect stars in a dark night sky : the size of objects is very small, the number of Grayscale is very low (pure black and pure white), and the contrast of objects from the background is huge.

Contrast

Similarly, we are able to distinguish clouds over gray sky : the size of objects is very large, and even on edges there is no detail (no high frequency / contours), and the number of different gray levels is very large (gradual grey scale from black to white).

Clouds

Between these two extremes are all possible cases, and in particular with all traffic scenes that may vary greatly from one to another :
. sunny day, overcast day, dark night, undergrowth, sunset, night in headlights, fog, rain, etc …

Visibility_Measurement

In addition to these technical compromise, there are criteria (eg criteria Johnson) that allow to objectify the subjective.

NEXYAD has developed a tool called VisiNex that integrates models and criteria described above, which led to two products:

. VisiNex Lab : test bench for visibility measurement. It sets a vehicle with calibrated visibility disturbances (rain machine, fog machine, …), and VisiNex Lab measures the evolution of the available visibility during the disturbance and during activation of visibility restoration systems (lighting, demisting, wiping, …).
VisiNex Lab is used to adjust the rain sensors, the wiper systems, the lighting systems. VisiNex is a world leader on this type of use : https://nexyad.net/Automotive-Transportation/?page_id=159

VisiNex_Banc

. VisiNex Onboard : NEXYAD took his model into onboard applications to apply and qualify road visibility along the route running (important place to qualify for the road safety applications).
VisiNex Onboard is currently being integrated into the framework for asynchronous real-time applications development RT-MAPS, and will soon be in the NEXYAD vision modules pack for ADAS and driving delegation applications.

VisiNex Onboard
Standard visibility on a highway scene.                             Degraded visibility when approaching a tunnel

VisiNex Onboard can be used in automotive application on the following topics :
. visibility measurement to control Visibility restoration systems (wiper, lighting, …)
. qualification of visibility conditions where an obstacle detection or road detection system will work properly.

The second point is important because road safety applications require to maximize the reliability of vision systems.

To know more :sales@nexyad.net

Driving Delegation: key elements

Driving Delegation: key elements for an artificial perception system
Publication of September 2, 2015
Authors : Gérard YAHIAOUI & Pierre DA SILVA DIAS

INTRODUCTION
The automotive industry starts offering ADAS, and plans to propose in the near future partial or total driving delegation systems.

Main cases to be processed first may be:
. Highway driving, where the number of events per kilometer is small because the infrastructure has been designed to minimize path irregularities (little or no turns, every car in the same direction, wide track, geometric visibility up to several kilometers, enough little interactions between vehicles, at least when the traffic is flowing).
. The city, where infrastructure complexity is very large, where interactions between the road users are very strong, making detection a difficult tasks, but where speed of the vehicle is low.
In all cases, these future ADAS require developing advanced systems of perception.

ADVANCED PERCEPTION
Perception consist in detecting objects, clustering, and possibly tracking them in their own trajectory, from selected sensors (cameras, radar, lidar, slam, ultrasound, …)

It is usually presented as several phases :
. Detection: we perceive that “something” comes off the background, but we do not know what it this is. The Johnson criteria for detection give a theoretical limit of one period, or a minimum width of two pixels to detect a stationary object.
. segmentation and tracking: when zones are detected as being detached from the background (the landscape for image processing, the cluter for a radar, …), the detection must be agglomerated to track large enough objects that may have a meaning.
. Recognition: Recognition is to be able to say what it is. The Johnson criteria for human vision is about 6 periods (for stationnary objects) which gives 12 pixels.
. identification: identification gives, in the recognized class, the precise name of the object.

Detection is by far the most complex. It is potentially based on several principles:
. breakage hypothesis : we made a number of assumptions about world geography. We choose this hypothesis and make sure they are verified for the landscape (or cluter), and not for the objects to be detected. The non-validation of assumptions corresponds to a detection.
. the confrontation of a knowledge of the landscape or cluter: Comparing the “background” as it is supposed to appear in the absence of additional objects with said background which contains objects lead to detection of those objects.
. the knowledge of the shape of the objects to be detected: in this case the detection and pattern recognition are the same. System detects an object in its environment because it recognizes this object.
Human perception jointly implements the three principles.

Perceptions systems incorporate sensors and methods of processing, and are generally effective in a frame capture conditions, and little or not effective in the other frames. For example, a camera in the visible wavelenghts (and its image processing methods), will generally not be effective at night or in fog because “you can not see anything.”

PERFORMANCE, STRENGTH, RELIABILITY
No detection system can operate in any case when dealing with a real problem in the open world.

Designing a detection system then comprises two important phases:
. extend the maximum possible number of cases where the detection system works.
. have a diagnosis that allows to know when it is or when it is not in a position to that the perception system is effective.

We talk about performance (very efficient detection of all objects of interest), strength (number of cases where the collection system remains effective), and reliability (Situational Awareness in which one is and thus the confidence that can be placed in the collection system).
These three elements, performance, robustness, reliability, should be fully known in order to cooperate collection systems (for example, a camera and a radar).

NEXYAD proposed the Methodology AGENDA for characterizing life situations, using the formalism of orthogonal plans of experiments. The recognition of cases of functioning mode can be based on the description of life situations with this methodology. This gives a theoretical and practical framework for an estimation of robustness and reliability.
Performance is measured with statistical comparison operators: in general, it is considered the output of a detection system is a categorical variable with two categories: “detected” and “not detected”. This variable must be compared to a qualitative variable of reference that also has two modalities: “Presence of an object to
be detected” and “absence of objects to be detected.” The comparison can not be made by calculating a percentage (yet it is often that performance is measured this way), but it must use tools such as contingency table, the Khi2, normalized Khi2, khi2 in the box, etc …
To extend the life situations of the domain where the system detects objects correctly, we use to make cooperate several detection systems which use complementary types of sensors (eg in fog, we will trust in radar or infrared detection, but not detection by conventional camera).
A reliable system is one that is able to answer “I do not know”: in the case of driving delegation a system that could detect all objects so powerful, robust, and reliable in 30% of the time has a great value.
The delegation of driving frees 30% time of the driver, which is a real value proposition.

SAFETY OPERATION
Safety is a discipline that encompasses many issues with the objective of ensuring the proper functioning of the system in all cases.
In particular, we must be vigilant concerning detection systems which require to have several measurement channels, such as stereovision.
If detection works only when you can have both cameras, then safety experts refuse such a system because two cameras means 2 times more likely that one fails.
We then see that perception system must have quite still usable “degraded mode” when simulating glitches sensors. A good design of a perception system for ADAS incorporates all these elements.

SYNTHESIS
The race for performance that interests the engineers is rarely the real issue in industrial systems. A system that allows to delegate the driving in 30% of cases (eg clear overcast day dry) and “knows” when there is a case for which it works or does not work, can delegate driving and release the driver for 30% of the time.
This is a proposal for a very high value for the driver.
A system that works effectively in 99% of cases without knowing precisely when it works is absolutely unusable. No manufacturer will put such a system in operation for road safety applications.
The company NEXYAD has been working on these issues for twenty years, especially on road detection, obstacles detection, measurement of visibility (to describe cases where the detection is reliable, for example), the estimation of road safety (suitability driving style with the infrastructure).

NEXYAD developed:
. efficient and very robust basic bricks: RoadNex, ObstaNex, VisiNex onboard, SafetyNex
. a methodology for characterizing life situations in which it develops and tests an ADAS: AGENDA (Improvement performance, the recognition of cases of good performance, and validation of ADAS).
. know-how in collaboration between multiple perception systems.

Test the effectiveness of wipers and tune a wiper system : a complex problem (March 15, 2010)

The modern wiper systems for car windshields are complex mechatronics systems that implement both sensors (light sensor, rain sensor), electric motors, one or more wiper blades with rubber qualities to be defined, a software for analysis and recognition of the rain, and a software that automatically triggers the wipers with an appropriate strategy. Each of these components can be selected or adjusted by many ways:
– Rain sensor: location of the rain sensor on the windshield, adjusting the threshold of the first outbreak, its timings, its hysteresis, …
– Luminance Sensor: taking into account only the integration of infrared or visible wavelengths, the sensor location and direction (does is point only the sky?) …
– Rubbers : quality of the viscoelastic material, surface condition, …
– Arm of the wiper: with pressure points, shape memory, …
– Architecture of wipers: conventional two blades, butterfly with a stop in the down position, with throttle stop position, single blade, …
– Characteristics of wipability of the windshield (macroscopic form: take-off speeds, … surface condition)
– Not to mention the software that have huge degrees of freedom (lines of code) …

If we consider a system composed of six subsystems that can each take 10 different items (10 items of rubber, 10 potential triggering software, 10 settings of the rain sensor, …), we obtain 106 possible systems (1 million) !

On a million possible systems, the engineers have to find ONE solution that is industrially acceptable (effectiveness, overall cost of the solution …).

The traditional method and still the most widespread in the industry to test and develop such a system consists in equiping a vehicle with a configuration (set a priori), in waiting for rain, and then sending a expert driver driving on roads they know. The driver then completes qualitative assessment grids which are used by engineers to change the settings of their wiper system.

Obviously, this method is tedious, and they can only test an extremely small number of combinations, so that it passes next to the statistically best solution (the best compromise between performance and cost). In addition, weather conditions in several consecutive tests may NOT be the same: it is NEVER the same rain, NEVER the same light, …
Performance comparisons are theoretically and therefore virtually impossible: no regression testing can be performed at every change, no quantitative rating of the effectiveness can be given … in short, despite all the expertise of engineers and the care they take to perform these tests, it is far from the industrial approach, let alone the quality approach.

The sampling of this complexity requires the use of at least fractional orthogonal experimental design. For this it is necessary to know how to reproduce the weather conditions in the laboratory, dive the vehicle into a known and reproducible (calibrated) environment, and then quantitatively measure the performance of the wiping.

NEXYAD has developed a tool to achieve this. This tool is divided into three major functions:
– A system for generating calibrated lighting (to generate repeatable chronograms of illumination).
– A system for generating calibrated and reproducible artificial rainfall, (for watering the windshield with known artificial rainfall, with statistical characteristics of natural rainfall)
– A system for measuring the effectiveness of the wiper system (providing a score of effectiveness)

The measurement of effectiveness of the wiping was until fairly recently a point relatively blocker. Indeed, the wiper is not a “function” in terms of the driving task: the “function” would rather be “in all circumstances ensure good visibility for the driver”, and wiping is just a technical response to achieve that in the case where visibility is degraded by the water deposited on the windshield.

We then see that if we can measure the visibility of the road scene by the driver (through windshield), then we can measure the effectiveness of the wiping : the rain degrades the visibility, the wiping restores some of the lost visibility.

NEXYAD worked since 1995 on the measurement of visibility and has integrated his expertise in a tool called VisiNex ™.
Similarly, NEXYAD has developed a rain machine (RainNex ™).

The combined use of these tools can set a wiper system in two months with two people, where before we had 5 people for over a year. In addition, the system performance is known and can be optimized (since we know the measure). The technically efficient solutions can then be compared in terms of cost, allowing more to achieve substantial savings.

Some automotive industrials already use NEXYAD tools.

Visibility measurement (February 28, 2010)

Measuring the visibility of a scene for a human being needs to have a mathematical model of the human vision system.

Actually, human vision requires some compromise between measurable characteristics of image quality such as contrast, depth, and object size, so as to detect, recognize, and identify the content of collected images.

When this compromise is not met, the vision becomes very difficult, tedious or even impossible.
It is obvious that the noise in the image (electronic snow of a sensor, for example), or poor contrast (due to the presence of aerosols, fog, rain, humidity, …) may considerably lower the performance of our vision system.

We can therefore say that this “images quality” is a key point of our performance.
But we do not need the same quality to detect all types of objects. For example, we will detect a gray cloud on a gray background, even shapeless, with extremely low contrast if the luminance depth (number of bits for a digital image) is high. On the opposite, on a dark sky, we can detect a star whose contrast is extremely strong, but whose size is at the limit of our eye angular accuracy. In such a case we just need 2 luminance levels (binary images are OK).

Human vision mathematical models were originally developed by the U.S. Department of Defense who wanted to model the impact of camouflage on the probability of detection (of an infantryman, a tank, …), recognition, and identification by a watchman.

“Detection” means “I see something”.
“Recognition” means “I see a car.”
“Identification means “I see a 3 serie BMW”

Of course, it is obvious that the level of detail needed to perform these three operations is not the same.
Measurable criteria in the picture (example: Johnson criteria) could be determined after testing a variety of situations by panels of hundreds of soldiers.

Based on these criteria, it is possible to construct a mathematical model for measuring perceived quality of images. This model is predictive of the ability to detect or to understand the image content.
NEXYAD has developed such a mathematical model of human vision and applied it, among other things, to test the effectiveness of windshields wiping systems of vehicles (product : VisiNex ™) : the rain that collects on the windshield breeze down the performance of visual detection of the driver. Each pass of the wiper can restore some lost visibility.

NEXYAD is currently applying this same maths model in the context of the extent of visibility of road markings (white lines, …), depending on the weather (day / night, rain, …).
The number and scope of potential applications of such a human vision mathematical modelling system are extremely broad.