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 4940846 A9511-4230-006 B9506-6140C-181 C9506-1250-129 Doc Type: Journal Paper Title: Scale-invariant optical correlators using ferroelectric liquid-crystal spatial light modulators Authors: Wilkinson, T.D.; Petillot, Y.; Mears, R.J.; de Bougrenet de la Tocnaye, J.L. Affiliation: Dept. of Eng., Cambridge Univ., UK Journal: Applied Optics Vol: 34 Iss: 11 p. 1885-90 Date: 10 April 1995 Country of Publication: USA ISSN: 0003-6935 CODEN: APOPAI CCC: 0003-6935/95/111885-06$06.00/0 Language: English Treatment: Application; New development; Theoretical/Mathematical Copyright 1995, IEE Abstract: New experimental results for scale-invariant implementations of the binary phase-only matched filter and the nonlinear joint transform correlator using ferroelectric liquid-crystal spatial light modulators are presented. We provide a comparative study of both architectures for real-time road-sign recognition. Signal-to-peak-noise ratios in excess of 5 dB over a scale range of 1.0 to 2.0 are achieved under realistic conditions of clutter. (17 Refs.) Classification: A4230S (Pattern recognition); A4280K (Optical beam modulators); A6130 (Liquid crystals); A4280B (Spatial filters, zone plates); A4230V (Image processing and restoration); B6140C (Optical information, image and video signal processing); B4150D (Liquid crystal devices); B4190F (Optical coatings and filters); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques) Thesaurus: Ferroelectric liquid crystals; Fourier transform optics; Image recognition; Liquid crystal devices; Matched filters; Optical correlation; Spatial filters; Spatial light modulators Free Terms: Scale-invariant optical correlators; Ferroelectric liquid-crystal spatial light modulators; Binary phase-only matched filter; Nonlinear joint transform correlator; Real-time road-sign recognition; Signal-to-peak-noise ratios; Scale range; Clutter INSPEC 4921693 B9505-6140C-199 C9505-5260B-193 Doc Type: Journal Paper Title: On-board optical joint transform correlator for real-time road sign recognition Authors: Guibert, L.; Keryer, G.; Servel, A.; Attia, M.; MacKenzie, H.S.; Pellat-Finet, P.; de Bougrenet de la Tocnaye, J.-L. Affiliation: Direction des Recherches et Affaires Sci., P.S.A. Peugeot Citroen, Velizy-Villacoublay, France Journal: Optical Engineering Vol: 34 Iss: 1 p. 1/135-43 Date: Jan. 1995 Country of Publication: USA ISSN: 0091-3286 CODEN: OPEGAR Language: English Treatment: New development; Experimental Copyright 1995, 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. The influence of the nonlinearity in the Fourier plane is investigated, and scale-invariant filters are tested and implemented. Preliminary results from real-time dynamic scenario experiments are presented. Electronic and optical pre- and postprocessing as well as the extension to silicon backplane devices are discussed. (23 Refs.) Classification: B6140C (Optical information, image and video signal processing); B4150D (Liquid crystal devices); C5260B (Computer vision and image processing techniques) Thesaurus: Ferroelectric liquid crystals; Image recognition; Liquid crystal devices; Optical correlation; Spatial light modulators Free Terms: On-board optical joint transform correlator; Real-time road sign recognition; Ferroelectric liquid-crystal spatial light modulator; Fourier plane; Nonlinearity; Scale-invariant filters; Silicon backplane devices INSPEC 4917203 C9505-5260B-159 Doc Type: Conference Paper Title: Robust road sign detection and recognition from image sequences Authors: Piccioli, G.; De Micheli, E.; Parodi, P.; Campani, M. Affiliation: Dipartimento di Fisica, Genoa Univ., Italy Conf. Title: Proceedings of the Intelligent Vehicles '94 Symposium (Cat. No.94TH8011) p. 278-83 Publisher: IEEE New York, NY, USA Date: 1994 xii+611 pp. Country of Publication: USA ISBN: 0 7803 2135 9 Language: English Conf. Date: 24-26 Oct. 1994 Conf. Loc: Paris, France Conf. Sponsor: IEEE Ind. Electron. Soc Treatment: Practical; Theoretical/Mathematical; Experimental Copyright 1995, IEE Abstract: This paper describes a method for detecting and recognizing road signs in grey-level images acquired by a single camera mounted on a moving vehicle. 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 a Kalman-filter-based temporal integration of the extracted information. The proposed approach can be very helpful for the development of a system for driving assistance. (13 Refs.) Classification: C5260B (Computer vision and image processing techniques); C3360B (Road-traffic system control); C7445 (Traffic engineering computing) Thesaurus: Driver information systems; Edge detection; Image recognition; Image sequences; Road vehicles Free Terms: Robust road sign detection; Road sign recognition; Image sequences; Grey-level images; Moving vehicle; Low-level noise corrupting edge detection; Contour following; Cluttered urban streets; Country roads; Highways; Kalman-filter-based temporal integration; Driving assistance INSPEC 4891024 C9504-7445-006 Doc Type: Conference Paper Title: A robust method for road sign detection and recognition Authors: Piccioli, G.; De Micheli, E.; Campani, M. Affiliation: Istituto di Fisica, Genoa Univ., Italy Conf. Title: Computer Vision - ECCV'94. Third European Conference on Computer Vision. Proceedings. Vol.I p. 495-500 Editors: Eklundh, J.-O. Publisher: Springer-Verlag Berlin, Germany Date: 1994 xvii+603 pp. Country of Publication: Germany ISBN: 3 540 57956 7 Language: English Conf. Date: 2-6 May 1994 Conf. Loc: Stockholm, Sweden Treatment: Practical Abstract: A robust method for detecting and recognizing road signs by vision is presented. The detection step is based on a geometrical analysis of the edges extracted from monochromatic images and is able to identify triangular and circular road signs from images of city streets, country roads and highways. A simple recognition system, which validates and classifies the detected road signs, greatly improves the reliability and the robustness of the whole system. Extensive experimentation on real images shows that road signs are usually correctly identified even in cluttered images. (10 Refs.) Classification: C7445 (Traffic engineering computing); C5260B (Computer vision and image processing techniques) Thesaurus: Computer vision; Edge detection; Image classification; Object detection; Reliability; Traffic engineering computing Free Terms: Robust method; Road sign detection; Road sign recognition; Computer vision; Geometrical analysis; Edge extraction; Monochromatic images; Triangular road signs; Circular road signs; City streets,; Country roads; Highways; Validation; Classification; Reliability; Robustness; Correct identification; Cluttered images