Towards Night Fog Detection through use of In-Vehicle Multipurpose Cameras Romain Gallen Aurélien Cord Nicolas Hautière Didier Aubert.

Slides:



Advertisements
Similar presentations
ARTIFICIAL PASSENGER.
Advertisements

Genoa, Italy September 2-4, th IEEE International Conference on Advanced Video and Signal Based Surveillance Combination of Roadside and In-Vehicle.
Chapter 2: Marr’s theory of vision. Cognitive Science  José Luis Bermúdez / Cambridge University Press 2010 Overview Introduce Marr’s distinction between.
The fundamental matrix F
Road-Sign Detection and Recognition Based on Support Vector Machines Saturnino, Sergio et al. Yunjia Man ECG 782 Dr. Brendan.
Chapter 12 Simple Linear Regression
International Symposium on Automotive Lighting, Darmstadt, Germany Review of the Mechanisms of Visibility Reduction by Rain and Wet Road Nicolas Hautière,
Rear Lights Vehicle Detection for Collision Avoidance Evangelos Skodras George Siogkas Evangelos Dermatas Nikolaos Fakotakis Electrical & Computer Engineering.
Visual Traffic Simulation Thomas Fotherby. Objective To visualise traffic flow. –Using 2D animated graphics –Using simple models of microscopic traffic.
Artificial PErception under Adverse CONditions: The Case of the Visibility Range LCPC in cooperation with INRETS, France Nicolas Hautière Young Researchers.
Intervenant - date Distributed Simulation Architecture for the Design of Cooperative ADAS D. Gruyer, S. Glaser, S. Pechberti, R. Gallen, N. Hautière 05/09/2011.
Vehicle-Infrastructure-Driver Interactions Research Unit
ITS World Congress, Stockholm, Sweden Sensing the Visibility Range at Low Cost in the SAFESPOT Road Side Unit Nicolas Hautière 1, Jérémie Bossu 1, Erwan.
TRB 2011 “ Visibility Monitoring Using Conventional Roadside Cameras: Shedding Light On and Solving a Multi- National Road Safety Problem“ A project supported.
Hokkaido University Efficient Rendering of Lightning Taking into Account Scattering Effects due to Clouds and Atmospheric Particles Tsuyoshi Yamamoto Tomoyuki.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Free Space Detection for autonomous navigation in daytime foggy weather Nicolas Hautière, Jean-Philippe Tarel, Didier Aubert.
Visibility Subspaces: Uncalibrated Photometric Stereo with Shadows Kalyan Sunkavalli, Harvard University Joint work with Todd Zickler and Hanspeter Pfister.
Robust Lane Detection and Tracking
Obstacle detection using v-disparity image
CS 223B Assignment 1 Help Session Dan Maynes-Aminzade.
CSE 291 Final Project: Adaptive Multi-Spectral Differencing Andrew Cosand UCSD CVRR.
A Fast and Efficient VOP Extraction Method Based on Watershed Segmentation Alireza Tavakkoli Dr. Shohreh Kasaei Gholamreza Amayeh Sharif University of.
Augmented Reality: Object Tracking and Active Appearance Model
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Perceptual Hysteresis Thresholding: Towards Driver Visibility Descriptors Nicolas Hautière, Jean-philippe Tarel, Roland Brémond Laboratoire Central des.
1 Real Time, Online Detection of Abandoned Objects in Public Areas Proceedings of the 2006 IEEE International Conference on Robotics and Automation Authors.
1 Video Surveillance systems for Traffic Monitoring Simeon Indupalli.
Computer Graphics Inf4/MSc Computer Graphics Lecture Notes #16 Image-Based Lighting.
1 REAL-TIME IMAGE PROCESSING APPROACH TO MEASURE TRAFFIC QUEUE PARAMETERS. M. Fathy and M.Y. Siyal Conference 1995: Image Processing And Its Applications.
GM-Carnegie Mellon Autonomous Driving CRL TitleAutomated Image Analysis for Robust Detection of Curbs Thrust AreaPerception Project LeadDavid Wettergreen,
1 Li Li [WSC17] Institute of Integrated Sensor Systems Department of Electrical and Computer Engineering Multi-Sensor Soft-Computing System for Driver.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Contribution of Infrastructures upon Road Safety: Modeling and Regulation of Operating Vehicle Speeds Nicolas Hautière Marie-Line Gallenne.
Implementing Codesign in Xilinx Virtex II Pro Betim Çiço, Hergys Rexha Department of Informatics Engineering Faculty of Information Technologies Polytechnic.
Colour changes in a natural scene due to the interaction between the light and the atmosphere Raúl Luzón González Colour Imaging Laboratory.
© Siemens AG, 2002 s CP RS Agenda The Role of IT for Accident-free Driving Interaction with driver’s physical condition Interaction with the roadside environment.
Traffic Sign Pattern Recognition Pilho Kim (ECE), Zhaohua Wang, Yichang (James) Tsai (CE)
The University of Texas at Austin Vision-Based Pedestrian Detection for Driving Assistance Marco Perez.
Blind Contrast Restoration Assessment by Gradient Ratioing at Visible Edges Nicolas Hautière 1, Jean-Philippe Tarel 1, Didier Aubert 1-2, Eric Dumont 1.
Road Scene Analysis by Stereovision: a Robust and Quasi-Dense Approach Nicolas Hautière 1, Raphaël Labayrade 2, Mathias Perrollaz 2, Didier Aubert 2 1.
1 P. David, V. Idasiak, F. Kratz P. David, V. Idasiak, F. Kratz Laboratoire Vision et Robotique, UPRES EA 2078 ENSI de Bourges - Université d'Orléans 10.
Driver’s Sleepiness Detection System Idit Gershoni Introduction to Computational and Biological Vision Fall 2007.
MACHINE VISION Machine Vision System Components ENT 273 Ms. HEMA C.R. Lecture 1.
Reconstruction the 3D world out of two frames, based on camera pinhole model : 1. Calculating the Fundamental Matrix for each pair of frames 2. Estimating.
University of Montreal & iMAGIS A Light Hierarchy for Fast Rendering of Scenes with Many Lights E. Paquette, P. Poulin, and G. Drettakis.
1 Perception and VR MONT 104S, Fall 2008 Lecture 4 Lightness, Brightness and Edges.
DETECTING AND TRACKING TRACTOR-TRAILERS USING VIEW-BASED TEMPLATES Masters Thesis Defense by Vinay Gidla Apr 19,2010.
Intelligent Vision Systems ENT 496 Image Filtering and Enhancement Hema C.R. Lecture 4.
CSE 140: Computer Vision Camillo J. Taylor Assistant Professor CIS Dept, UPenn.
Department of Computer Science,
Under The Guidance of Smt. D.Neelima M.Tech., Submitted by
Photo-realistic Rendering and Global Illumination in Computer Graphics Spring 2012 Stochastic Path Tracing Algorithms K. H. Ko School of Mechatronics Gwangju.
CSSE463: Image Recognition Day 29 This week This week Today: Surveillance and finding motion vectors Today: Surveillance and finding motion vectors Tomorrow:
Suspicious Behavior in Outdoor Video Analysis - Challenges & Complexities Air Force Institute of Technology/ROME Air Force Research Lab Unclassified IED.
May 16-18, Tsukuba Science City, Japan Machine Vision Applications 2005 Estimation of the Visibility Distance by Stereovision: a Generic Approach.
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Learning and Removing Cast Shadows through a Multidistribution Approach Nicolas Martel-Brisson, Andre Zaccarin IEEE TRANSACTIONS ON PATTERN ANALYSIS AND.
Detection, Tracking and Recognition in Video Sequences Supervised By: Dr. Ofer Hadar Mr. Uri Perets Project By: Sonia KanOra Gendler Ben-Gurion University.
Reconstruction of a Scene with Multiple Linearly Moving Objects Mei Han and Takeo Kanade CISC 849.
Advanced Computer Graphics
Internet of Things : Opportunities for NMHS
A Forest of Sensors: Tracking
Development of VR Glasses
CSSE463: Image Recognition Day 25
Vehicle Segmentation and Tracking in the Presence of Occlusions
Dongwook Kim, Beomjun Kim, Taeyoung Chung, and Kyongsu Yi
Multi-Sensor Soft-Computing System for Driver Drowsiness Detection
Grey Level Enhancement
Presentation transcript:

Towards Night Fog Detection through use of In-Vehicle Multipurpose Cameras Romain Gallen Aurélien Cord Nicolas Hautière Didier Aubert

2 /11 Atmospheric Characterization with in-vehicle Multipurpose Cameras Triple goal –Driving assistance systems (lighting, wipers) –Fiabilize other ADAS based on cameras –Functionality used as input in intelligent speed adaptation systems Previous works on : –Rain detection –Day fog detection Almost nothing about Night fog A. Cord and D. Aubert, Towards Rain Detection through Use of In-Vehicle Multipurpose Cameras, IV’2011 (Poster session on Wednesday) N. Hautière, J.-P. Tarel, J. Lavenant, and D. Aubert, Automatic fog detection and estimation of visibility distance through use of an onboard camera, Machine Vision and Applications, vol. 17, no. 1, pp. 8–20, [Cord11] [Hautiere06]

Two distinct phenomenons that are not observable at the same time (due to the classical camera settings) : 3 /11 Embedded Night Fog Detection Multiple light sources in the environment Road is lit by car own lighting system R. Gallen, A. Cord, N. Hautière et D. Aubert, Procédé et dispositif de détection de brouillard, la nuit, Brevet Français n° , Sept

4 /11 Previous works [Leleve06][Kawasaki08] Perceptible back scattered veil J. Leleve, A. Bensrhair,, and J. Rebut, Method for detecting night fog and system implementing said method, Patent EP , N. Kawasaki, T. Miyahara, and Y. Tamatsu, Visibility condition determining device for vehicle, Patent , Back Scattered Veil Detection (1/5)

5 /11 Experiments conducted in a fog chamber at the LRPC, Clermont-Ferrand, France 30 m deep, 2.7 m high Monitored Fog Back Scattered Veil Detection (2/5) Software simulation Semi Monte Carlo ray tracing Photorealistic scenes PROF-LCPC Software

Correlation between real images and synthetic images 6 /11 Synthetic imageImage of in-vehicle camera Correlation mask Back scattered veil detection (3/5) ExperimentsSoftware simulation

Meteorological Visibility 7 /11 Back Scattered Veil Detection (4/5) Zero mean Normalized Sum of Squared Differences Correlation

7 /11 Back Scattered Veil Detection (5/5) Raw imageMean image Conclusion : Detection and characterization of night fog. Simple, adaptable, real time. Possibility to use a mean image How to manage in presence of light sources in the environment ?

8 /11 Detection of halos around light sources (1/3) Hypothesis : –halos are present around light sources –intensity decrease as the distance from the source increases –Sources unknown –Automatic camera settings

8 /11 Algorithm for halo detection around light sources Features analysed : - Surface - Gravity center - Compacity (surface/perimeter) - Elongation Detection of halos around light sources (1/3)

8 /11 Regions that appear at intermediate thresholds are not added to the tree Detection of halos around light sources (1/3)

8 /11 Detection of halos around light sources (1/3)

8 /11 Selection is made according to size, shape and lenght of branch criterions Detection of halos around light sources (1/3)

8 /11 Selection of interesting light sources Detection of halos around light sources (1/3)

9 /11 The slope of the profile is relevant regarding the presence of fog Extraction of the intensity profile of light sources Detection of halos around light sources (2/3)

Detection based on a single frame ~ 98% of good detection results 10 /11 Detection of halos around light sources (3/3) Fiabilized by a detection based on consecutive frames

11 /11 Conclusion Method allowing for fog detection with a dual algorithm with standard camera using automatic exposure settings Real time implemented and tested algorithms Preserves the usual working state of other camera based ADAS May be combined in order to improve Driver/car orientated ADAS (adaptive lighting systems, future vision enhancement systems in fog) Safety orientated ADAS (Preemptive driver information, Intelligent Speed Adaptation in fog) System orientated ADAS (detection of working state, improvement of camera based ADAS through image restoration)