Shadow removal for robust vehicle detection

• Autorzy: Rodriguez T.
• Języki publikacji: EN

Abstrakty

EN

Shadow removal is a critical process for any computer vision based vehicle detection system. Traditional shadow removal methods are not sufficiently robust since they frequently remove parts of the vehicles together with the shadows. For robust shadow identification and removal, shadow information must be compiled at every step of the computer vision chain from the time the shadow enters the scene until it finally disappears. In this paper we present a shadow removal algorithm that preserves the compactness of the vehicles' object masks while allowing for dealing with changing illumination conditions, long and broken shadows and multiple shadows at night. The method is based on a complex shadow model which includes, among others, information regarding: luminance and chromaticity, morphology, dynamics and spatial relations analysis.

Słowa kluczowe

EN

computer vision; real-time; traffic monitoring; shadow removal

PL

wizja komuterowa; czas rzeczywisty; kontrola ruchu; usuwanie cienia

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2008
• Tom: Vol. 17, No. 3
• Strony: 249--266
• Opis fizyczny: Bibliogr. 15 poz., rys., tab., wykr.

Twórcy

autor

Rodriguez T.

• Universidad Nacional de Educacion a Distancia, UNED, ETSI Informatica, Madrid, Spain

Bibliografia

• [1] Tzomakas C. and W. von Seelen.: Vehicle detection in traffic scenes using shadows. Technical Report IRINI 98-06, Institut fur Neuroinformatik, Ptuhr-Universita, 1998.
• [2] Horprasert T., Harwood D., Davis L.: A statistical approach for real-time robust background subtraction and shadow detection. Proceedings of IEEE ICCV99 FRAME-RATE Workshop, 1999.
• [3] Stauder D., Mech R., Ostermann J.: Detection of moving cast shadows for object segmentation. IEEE Transactions on multimedia, 1: 65-76, March. 1999.
• [4] Mikic I., Cosrnan P., Kogut G., Trivedi M.: Moving shadow and object detection in traffic scenes. Proc. of International Conference on Patter Recognition, volume 1, pages 321-324, September, 2000.
• [5] Seki M., Fujiwara H., Sumi K.: A robust background subtraction method for changing background. In Proceedings of IEEE Workshop on Applications of Computer Vision, pages 207-213, 2000.
• [6] Cucchiara R., Grana C., Piccardi M., Prati A., and Sirotti S.: Improving shadow suppression in moving object detection with hsv color information. ln Proceedings of IEEE Intelligent Transportation System Conference (ITSC 2001)., pages 334-339, Oakland, CA, USA, August, 2001.
• [7] Ohta N.: A statistical approac to background suppression for surveillance systems. In Proceeedings of IEEE Int'l. Conference on Computer Vision, pages 481-486, 2001.
• [8] Prati A., Mikic I., Cucchiara R., Trivedi M.: Comparative evaluation of moving shadow detection algorithms. In IEEE CVPR Workshop on Empirical Evaluation Methods in Computer Vision, Kauai, December, 2001.
• [9] Prati A., Mikic I., Grana C., Triveni M.: Shadow detection algorithms for traffic flow analysis: a comparative study. In Proc. IEEE Int’l Conf. on Intel. Transport. System., pages 304-345, Aug., 2001.
• [l0] Cucchiara R., Grana C., Prati A.: Detecting moving objects and their shadows: an evaluation with the pets 2002 dataset. In Proceedings of Third IEEE International Workshop on Performance Evaluation of Tracking and Surveillance. ECCV 2002., pages 18-25, Copenhagen, Denmark, May.
• [11] Martin R.F.K, Masoud Osama, and Papanikopoulos Nicolas: Using intrinsic images for shadow handling. In Proc. IEEE 5th International Conference on Intelligent Transportation Systems, pages 152-155, Singapore, September, 2002.
• [12] Yoneyama A., Yeh C., Kuo C.: Moving cast shadows elimination for robust vehicle extraction based on 2d joint / vehicle shadow models. In IEEE Conference on Advanced Video and Signal Based Surveillance. AVSSO3, pages 229-236, 2003.
• [13] Sohail Nadimi and Bir Bhanu: Physical models for moving shadow and object detection in video. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 26, pages 1079-1087, August, 2004.
• [14] Rodriguez T.: Adaptive real-time segmentation in traffic sequences. Machine Graphics & Vision Journal, 13(1):39-52, 2004.
• [15] Rodriguez T.: Camera calibration and image rectification in a traffic monitoring system. Advances in Transportation Studies, (8):81-96, April, 2006.