INSPEC 5363210 B9610-4150D-012 C9610-5260B-208 Doc Type: Conference Paper Title: Optical processing at the driver's service Authors: Guibert, L.; Attia, M. Affiliation: Dept. Opt., ENST de Bretagne, Brest, France Conf. Title: Towards an Intelligent Transport System. Proceedings of the First World Congress on Applications of Transport Telematics and Intelligent Vehicle-Highway Systems p. 2134-40 vol.4 Publisher: Artech House London, UK Date: 1995 6 vol. xiv+3394 pp. Country of Publication: UK ISBN: 0 89006 810 0 Language: English Conf. Date: 30 Nov.-3 Dec. 1994 Conf. Loc: Paris, France Treatment: Practical; Experimental Copyright 1996, IEE Abstract: We design, implement and test an on-board optical joint transform correlator, using a nonlinear optically addressed ferroelectric liquid crystal spatial light modulator in the Fourier plane. This compact correlator performs real-time and on-board recognition tasks, such as road sign recognition. Preliminary results from real-time dynamic scenario experiments are presented. Electronic and optical pre- and post-processing as well as the extension to silicon backplane devices are discussed. (13 Refs.) Classification: B4150D (Liquid crystal devices); B2860 (Piezoelectric and ferroelectric devices); B6140C (Optical information, image and video signal processing); B4340 (Nonlinear optics and devices); B4270 (Integrated optoelectronics); B7220 (Signal processing and conditioning equipment and techniques); C5260B (Computer vision and image processing techniques); C7445 (Traffic engineering computing) Thesaurus: Driver information systems; Ferroelectric devices; Fourier transform optics; Image processing equipment; Image recognition; Integrated optoelectronics; Liquid crystal devices; Nonlinear optics; Optical correlation; Road vehicles; Spatial light modulators Free Terms: Optical processing; On-board optical joint transform correlator; Nonlinear optically addressed ferroelectric liquid crystal spatial light modulator; Fourier plane; Real-time on-board recognition tasks; Road sign recognition; Real-time dynamic scenario experiments; Optical post-processing; Optical pre-processing; Electronic post-processing; Electronic pre-processing; Silicon backplane devices INSPEC 5316602 B9608-6140C-356 C9608-5260B-221 Doc Type: Conference Paper Title: A real-time histographic approach to road sign recognition Authors: Estevez, L.; Kehtarnavaz, N. Affiliation: Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA Conf. Title: Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.96TH8166) p. 95-100 Publisher: IEEE New York, NY, USA Date: 1996 viii+263 pp. Country of Publication: USA ISBN: 0 7803 3200 8 CCC: 0 7803 3200 8/96/$5.00 Language: English Conf. Date: 8-9 April 1996 Conf. Loc: San Antonio, TX, USA Treatment: Theoretical/Mathematical; Experimental Copyright 1996, IEE Abstract: This paper presents the development and real-time implementation of an algorithm capable of recognizing stop, yield, and do-not-enter traffic warning signs. It consists of six modules: color segmentation, edge localization, RGB differencing, edge detection, histograph extraction, and classification. RGB transformed pixels are sparsely segmented and sequentially XOR-ed to localize edge areas. RGB differencing together with maxima edge detection is then deployed to locate edges in these areas. Recognition is achieved based on the angular histographic attribute extracted by a semi-rectangular histographic mask. All the modules are implemented on the TMS320C40 DSP processor allowing video data captured by a video camera to be processed in real-time. The devised real-time processing platform has led to an understanding of various environmental effects on video data. (9 Refs.) Classification: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques) Thesaurus: Edge detection; Feature extraction; Image classification; Image colour analysis; Image segmentation; Real-time systems; Road traffic; Video signal processing Free Terms: Real-time histographic approach; Road sign recognition; Stop traffic warning signs; Yield traffic warning signs; Do-not-enter traffic warning signs; Color segmentation; Edge localization; RGB differencing; Edge detection; Histograph extraction; Classification; RGB transformed pixels; Edge areas; Angular histographic attribute; Semi-rectangular histographic mask; TMS320C40 DSP processor; Video data INSPEC 5305323 B9608-6140C-134 C9608-1250-067 Doc Type: Journal Paper Title: Robust method for road sign detection and recognition Authors: Piccioli, G.; de Micheli, E.; Parodia, P.; Campani, M. Affiliation: Dipartimento di Fisica, Genoa Univ., Italy Journal: Image and Vision Computing Vol: 14 Iss: 3 p. 209-23 Publisher: Elsevier Date: April 1996 Country of Publication: UK ISSN: 0262-8856 CODEN: IVCODK CCC: 0262-8856/96/$15.00 Language: English Treatment: Application; Practical Copyright 1996, IEE Abstract: This paper describes a method for detecting and recognizing road signs in grey-level and colour images acquired by a single camera mounted on a moving vehicle. The method works in three states. First, the search for the road sign is reduced to a suitable region of the image by using some a priori knowledge on the scene or colour clues (when available). Secondly, a geometrical analysis of the edges extracted from the image is carried out, which generates candidates to be circular and triangular signs. Thirdly, a recognition stage tests by cross-correlation techniques each candidate which, if validated, is classified according to the database of signs. An extensive experimentation has shown that the method is robust against low-level noise corrupting edge detection and contour following, and works for images of cluttered urban streets as well as country roads and highways. A further improvement on the detection and recognition scheme has been obtained by means of temporal integration based on Kalman filtering methods of the extracted information. The proposed approach can be very helpful for the development of a system for driving assistance. (251 Refs.) Classification: B6140C (Optical information, image and video signal processing); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques); C7445 (Traffic engineering computing) Thesaurus: Driver information systems; Edge detection; Image recognition; Object recognition Free Terms: Road sign detection; Road sign recognition; Grey-level; Colour images; Moving vehicle; A priori knowledge; Colour clues; Geometrical analysis; Low-level noise; Edge detection; Contour following; Cluttered urban streets; Country roads; Highways; Temporal integration; Kalman filtering methods; Driving assistance INSPEC 5286239 B9607-6140C-442 C9607-5260B-330 Doc Type: Conference Paper Title: Tracking of occluded vehicles in traffic scenes Authors: Frank, T.; Haag, M.; Kollnig, H.; Nagel, H.-H. Affiliation: Inst. fur Algorithmen und Kognitive Syst., Karlsruhe Univ., Germany Conf. Title: Computer Vision - ECCV `96. 4th Eurpean Conference on Computer Proceedings p. 485-94 vol.2 Editors: Buxton, B.; Cipolla, R. Publisher: Springer-Verlag Berlin, Germany Date: 1996 2 vol. (xix+725+722 pp.) Country of Publication: Germany ISBN: 3 540 61123 1 Language: English Conf. Date: 14-18 April 1996 Conf. Loc: Cambridge, UK Conf. Sponsor: Eur. Vision Soc.; British Machine Vision Assoc Treatment: Practical; Theoretical/Mathematical; Experimental Copyright 1996, IEE Abstract: Vehicles on downtown roads can be occluded by other vehicles or by stationary scene components such as traffic lights or road signs. After having recorded such a scene by a video camera, we noticed that the occlusion may disturb the detection and tracking of vehicles by previous versions of our computer vision approach. In this contribution we demonstrate how our image sequence analysis system can be improved by an explicit model-based recognition of 3D occlusion situations. Results obtained from real world image sequences recording gas station traffic as well as inner-city intersection traffic are presented. (11 Refs.) Classification: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C1250 (Pattern recognition) Thesaurus: Computer vision; Image recognition; Image sequences; Object recognition; Road traffic; Target tracking Free Terms: Occluded vehicle tracking; Traffic scenes; Downtown roads; Stationary scene components; Road signs; Traffic lights; Computer vision approach; Image sequence analysis; Explicit model-based recognition; 3D occlusion situations; Gas station traffic; Inner-city intersection traffic; Object recognition INSPEC 5157208 B9602-4270-011 C9602-5260B-168 Doc Type: Conference Paper in Journal Title: Autonomous on-board optical processor for driving aid Authors: Attia, M.; Servel, A.; Guibert, L. Affiliation: Direction des Recherches et Affaires Sci., PSA Peugeot Citroen, Velizy-Villacoublay, France Journal: Proceedings of the SPIE - The International Society for Optical Engineering Vol: 2344 p. 227-33 Publisher: SPIE-Int. Soc. Opt. Eng Date: 1995 Country of Publication: USA ISSN: 0277-786X CODEN: PSISDG CCC: 0 8194 1677 0/95/$6.00 Language: English Conf. Title: Intelligent Vehicle Highway Systems Conf. Date: 2-4 Nov. 1994 Conf. Loc: Boston, MA, USA Conf. Sponsor: SPIE Treatment: Theoretical/Mathematical; Experimental Copyright 1996, IEE Abstract: We take advantage of recent technological advances in the field of ferroelectric liquid crystal silicon back plane optoelectronic devices. These devices are well suited to perform massively parallel processing tasks. The technology enables the design of low cost vision systems and allows the implementation of on-board system. We focus on transport applications such as road sign recognition. Preliminary in-car experimental results are presented. (3 Refs.) Classification: B4270 (Integrated optoelectronics); B7230G (Image sensors); B8520B (Automobile electronics); B4150D (Liquid crystal devices); B4180 (Optical logic devices and optical computing techniques); B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C3240K (Image sensors); C3360B (Road-traffic system control); C5270 (Optical computing techniques) Thesaurus: Automotive electronics; Computer vision; Driver information systems; Integrated optoelectronics; Liquid crystal devices; Object recognition; Optical correlation; Road vehicles; Safety systems; Spatial light modulators Free Terms: On-board optical processor; Driving aid; Ferroelectric liquid crystal spatial light modulators; Optoelectronic devices; Road sign recognition; Vision systems; Parallel processing; Optical correlation; Joint transform correlator