INSPEC 5107143 B9512-6140C-584 C9512-7445-080 Doc Type: Conference Paper Title: Color cues for traffic scene analysis Authors: De Micheli, E.; Prevete, R.; Piccioli, G.; Campani, M. Affiliation: Istituto di Cibernetica e Biofisica, CNR, Genova, Italy Conf. Title: Proceedings of the Intelligent Vehicles '95. Symposium (Cat. No.95TH8132) p. 466-71 Publisher: IEEE New York, NY, USA Date: 1995 x+537 pp. Country of Publication: USA ISBN: 0 7803 2983 X Language: English Conf. Date: 25-26 Sept. 1995 Conf. Loc: Detroit, MI, USA Conf. Sponsor: IEEE Ind. Electron. Soc Treatment: Theoretical/Mathematical Copyright 1995, IEE Abstract: In this paper a system for the analysis of color images of traffic scenes is presented. This system, which is based on a suitable processing of the chromatic information contents of the images, aims at recovering in a robust way important parts of a road scene like the road-bed, obstacles which are present on the road-bed, horizontal and vertical road signs, and traffic lights. A wide experimentation on images of urban and country roads has shown the power of using color information compared to the performance we obtained by algorithms for object detection and recognition that rely solely on geometric features extracted from monochromatic images. The results suggest that color cue can be very helpful to construct drivers' assistant systems based on computer vision technologies even in the presence of quite complex road environments. (18 Refs.) Classification: B6140C (Optical information, image and video signal processing); C7445 (Traffic engineering computing); C5260B (Computer vision and image processing techniques) Thesaurus: Driver information systems; Image processing Free Terms: Color cues; Traffic scene analysis; Color images; Chromatic information contents; Road-bed; Road signs; Traffic lights; Object detection; Object recognition INSPEC 5107116 B9512-6140C-582 C9512-5260B-429 Doc Type: Conference Paper Title: Ideogram identification in a realtime traffic sign recognition system Authors: Priese, L.; Lakmann, R.; Rehrmann, V. Affiliation: Image Recognition Lab., Koblenz-Landau Univ., Germany Conf. Title: Proceedings of the Intelligent Vehicles '95. Symposium (Cat. No.95TH8132) p. 310-14 Publisher: IEEE New York, NY, USA Date: 1995 x+537 pp. Country of Publication: USA ISBN: 0 7803 2983 X Language: English Conf. Date: 25-26 Sept. 1995 Conf. Loc: Detroit, MI, USA Conf. Sponsor: IEEE Ind. Electron. Soc Treatment: Practical Copyright 1995, IEE Abstract: A robust system for the automatic detection of traffic signs has been developed at the Image Recognition Laboratory of the University of Koblenz. This traffic sign recognition (TSR) system was originally designed to localize traffic signs and to recognize their classes, e.g. prohibition signs, danger signs, beacons, etc. The exact identification of traffic signs is added. Traffic signs are identified by the interpretation of their ideograms realized by different modules in our TSR. The first module detects the position and direction of arrows. A second tool recognizes numerals and interprets them as reasonable speed limits. A third one is a general nearest neighbor classifier applied to three classes of ideograms (prohibition sign ideograms, speed limits, arrows on mandatory signs). The fourth module is based on neural nets and applied to two of these classes. Some of these components are used competitively in our realtime TSR. The use of several results from different tools increases the safety and provides high recognition rates. (12 Refs.) Classification: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C5290 (Neural computing techniques) Thesaurus: Image recognition; Neural nets; Object recognition; Real-time systems Free Terms: Ideogram identification; Real-time traffic sign recognition system; Automatic detection; Road signs; Arrows; Numeral recognition; Speed limits; Nearest neighbor classifier; Neural nets INSPEC 5107102 C9512-5260B-426 Doc Type: Conference Paper Title: A feature-based recognition scheme for traffic scenes Authors: Parodi, P.; Piccioli, G. Affiliation: Dipartimento di Fisica, Genoa Univ., Italy Conf. Title: Proceedings of the Intelligent Vehicles '95. Symposium (Cat. No.95TH8132) p. 229-34 Publisher: IEEE New York, NY, USA Date: 1995 x+537 pp. Country of Publication: USA ISBN: 0 7803 2983 X Language: English Conf. Date: 25-26 Sept. 1995 Conf. Loc: Detroit, MI, USA Conf. Sponsor: IEEE Ind. Electron. Soc Treatment: Experimental Copyright 1995, IEE Abstract: This paper describes a method for the interpretation of traffic scenes based on the detection and recognition of those objects, or classes of objects which are typically found in an urban scene. Since generic model-based recognition schemes are unsuitable for the analysis of traffic scenes and result in very poor performances, each of the different classes of objects which we expect to find in a typical scene is identified according to some selected features. After identifying the object, its main parameters are computed and, when needed, the object is further classified. The classes of objects we have considered included the roadbed, vehicles, buildings, trees, crosswalks and road signs. The method described here has been successfully tested on a wide set of images of traffic scenes and provided a general-purpose reconstruction of the whole traffic scene as viewed by the driver. (8 Refs.) Classification: C5260B (Computer vision and image processing techniques); C7445 (Traffic engineering computing); C1250 (Pattern recognition) Thesaurus: Computer vision; Feature extraction; Image reconstruction; Object detection; Object recognition; Road traffic; Stereo image processing; Traffic control Free Terms: Feature-based recognition; Traffic scenes; Object detection; Object recognition; Feature extraction; 3D structure reconstruction INSPEC 5021702 A9517-4230-036 B9509-6140C-570 C9509-1250-400 Doc Type: Conference Paper Title: Application of optical multiple-correlation to recognition of road signs: the ability of multiple-correlation Authors: Matsuoka, K.; Taniguchi, M.; Mokuno, Y. Affiliation: Osaka Nat. Res. Inst., Japan Conf. Title: Optical Computing. Proceedings of the International Conference p. 305-8 Editors: Wherrett, B.S.; Chavel, P. Publisher: IOP Publishing Bristol, UK Date: 1995 xix+660 pp. Country of Publication: UK ISBN: 0 7503 0126 0 Language: English Conf. Date: 22-25 Aug. 1994 Conf. Loc: Edinburgh, UK Treatment: Application; Theoretical/Mathematical; Experimental Copyright 1995, IEE Abstract: We apply correlation filters to the location problem of multiple objects in a real scene and discuss the ability of optical correlators. Firstly, we design a correlation filter to reduce false signals caused by background and noise in an input scene. Then we introduce a color processing for locating multiple road signs. The performances of these filtering are verified by the computer simulations. (4 Refs.) Classification: A4230S (Pattern recognition); A4280B (Spatial filters, zone plates); A4230V (Image processing and restoration); B6140C (Optical information, image and video signal processing); B4190F (Optical coatings and filters); B8520 (Transportation); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques) Thesaurus: Automobiles; Clutter; Colour; Image processing; Image recognition; Optical correlation; Optical noise; Simulation; Spatial filters Free Terms: Optical multiple-correlation; Road sign recognition; Automobiles; Spatial filters; Multiple objects; Real scene; Optical correlators; Correlation filter design; False signal reduction; Background; Input scene noise; Computer simulations INSPEC 4973676 B9507-6140C-573 C9507-5260B-318 Doc Type: Conference Paper Title: Detection of highway warning signs in natural video images using color image processing and neural networks Authors: Kellmeyer, D.L.; Zwahlen, H.T. Affiliation: US Army Environ. Hygiene Agency, Fort Meade, MD, USA Conf. Title: 1994 IEEE International Conference on Neural Networks. IEEE World Congress on Computational Intelligence (Cat. No.94CH3429-8) p. 4226-31 vol.7 Publisher: IEEE New York, NY, USA Date: 1994 7 vol. (lxvii+lxii+4796 pp.) Country of Publication: USA ISBN: 0 7803 1901 X CCC: 0 7803 1901 X/94/$4.00 Language: English Conf. Date: 27 June-2 July 1994 Conf. Loc: Orlando, FL, USA Treatment: Practical Copyright 1995, IEE Abstract: This study reports on the development of a system that incorporates color image processing and neural networks to detect and locate highway warning signs in natural roadway images. Such a system could reduce the need for redundant or oversized signs by assisting drivers in acquiring roadway information. Transportation agencies could use such a system as the first step in an automated highway sign inventory system. Currently, a human operator must watch hours of highway videos to complete this inventory. While only warning signs were considered in this study, the procedure was designed to be easily adapted to all highway signs. The basic approach is to digitize a roadway image and segment this image, using a back-propagation neural network, into eight colors that are important to highway sign detection. Next, the system scans the image for color regions that may possibly represent highway warning signs. Upon finding possible warning sign regions, these regions are further analyzed by a second back-propagation neural network to determine if their shape corresponds to that of a highway warning sign. (8 Refs.) Classification: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C1240 (Adaptive system theory); C5290 (Neural computing techniques) Thesaurus: Backpropagation; Image recognition; Image segmentation; Neural nets; Object detection; Object recognition Free Terms: Highway warning sign detection; Natural video images; Color image processing; Neural networks; Highway videos; Image digitization; Image segmentation; Back-propagation neural network; Road signs INSPEC 4939349 C9506-3360B-024 Doc Type: Conference Paper Title: A vision-aided vehicle driving system: establishment of a sign finder system Authors: Fann Jeun-Haii; Lee Gang Affiliation: Dept. of Transp. Manage., Tamkang Univ., Taipei, Taiwan Conf. Title: 1994 Vehicle Navigation and Information Systems Conference Proceedings (Cat. No.94CH35703) p. 33-8 Publisher: IEEE New York, NY, USA Date: 1994 xxii+704 pp. Country of Publication: USA ISBN: 0 7803 2105 7 CCC: 0 7803 2105 7/94/$4.00 Language: English Conf. Date: 31 Aug.-2 Sept. 1994 Conf. Loc: Yokohama, Japan Conf. Sponsor: IEEE Vehicular Technol. Soc.; IEEE Tokyo Sect.; Inst. Electr. Eng. Japan; Soc. Automotive Eng. Japan Treatment: Theoretical/Mathematical; Experimental Copyright 1995, IEE Abstract: The purpose of this article is to build an automatic extraction and classification system for road sign images with color features. Median filtering technique is used to decrease the noises and increase the stability of the color characteristics. According to the color features of road signs, we establish four heuristic decision rules: the range of the hue, the fixed order of the intensity of RGB, the ratio of the intensity of RGB, and the range of the intensity of RGB. Experimental results have achieved a 93.3% correct rate. The system is proved to be successful in recognising the road signs for complex real highway environmental images. (10 Refs.) Classification: C3360B (Road-traffic system control); C5260B (Computer vision and image processing techniques); C1250 (Pattern recognition); C7445 (Traffic engineering computing) Thesaurus: Automobiles; Colour; Computer vision; Feature extraction; Filtering theory; Image classification; Image colour analysis; Navigation Free Terms: Vision-aided vehicle driving system; Image classification; Sign image recognition; Color feature extraction; Median filtering; Heuristic decision rules; Hue range; RGB intensity; Highway environment