Vehicle detection based on shape priors and level set

被引：0

作者：

Zhao L. ^{[1
]}

Yu H.-M. ^{[1
]}

机构：

[1] Department of Information Science and Electronic Engineering, Zhejiang University

来源：

Zhejiang Daxue Xuebao(Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2010年 / 44卷 / 01期

关键词：

Level set; Shadow detection; Shape alignment; Shape priors; Vehicle detection;

D O I：

10.3785/j.issn.1008-973X.2010.01.022

中图分类号：

学科分类号：

摘要：

A moving vehicle detection method based on the prior shape knowledge and active contour method was proposed for the application of traffic video detection. First, the shadow was eliminated for obtaining the initial contour of the vehicle using the color and edge information. Then, an implicit shape model with level set signed distant image was built to improve the accuracy of vehicle contour pick-up, and an active contour energy function with the restriction of the existing shape priors was constructed. The obtained vehicle contour was set to initial contour of the vehicle segmentation evolvement contour, and then the minimal value of the energy function could be found by variational method. The precise contour of the vehicle was obtained by applying the shape alignment and level set method to evolving the initial contour. Experimental results of real traffic sequences proved the good effectiveness of the proposed method.

引用

下载

页码：124 / 130

页数：6

共 16 条

[1] Stauffer C., Grimson W.E.L., Adaptive background mixture models for real-time tracking, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 246-252, (1999)
[2] Cucchiara R., Grana C., Piccardi M., Et al., Detecting moving objects, ghosts, and shadows in video streams, IEEE Transactions on Pattern Analysis and Machine Intelligence, 25, 10, pp. 1337-1342, (2003)
[3] Elgammal A., Duraiswami R., Harwood D., Et al., Background and foreground modeling using nonparametric kernel density estimation for visual surveillance, Proceedings of the IEEE, 90, 7, pp. 1151-1163, (2002)
[4] Wang Y., Loe K.F., Wu J.K., A dynamic conditional random field model for foreground and shadow segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, 2, pp. 279-289, (2006)
[5] Chen R., Deng Y., Xiang S.-M., Et al., A non-parametric foreground/background segmentation method by fusion of intensity and edge feature, Journal of Computer-Aided Design and Computer Graphics, 17, 6, pp. 1278-1284, (2005)
[6] Caselles V., Kimmel R., Sapiro G., Geodesic active contours, International Journal of Computer Vision, 22, 1, pp. 61-79, (1997)
[7] Xu Y., Yu H.-M., Contour-based motion segmentation using few priors, International Conference on Signal Processing, pp. 1376-1379, (2006)
[8] Yu H.-M., Xu Y., Liu J.-Z., Et al., A spatiotemporal multiple moving objects segmentation and tracking with level set, Journal of Image and Graphics, 12, 7, pp. 1218-1223, (2007)
[9] Yu H.-M., You Y.-S., Detecting and segmenting multiple moving objects using level-set method, Journal of Zhejiang University: Engineering Science, 41, 3, pp. 412-417, (2007)
[10] Cootes T.F., Taylor C.J., Cooper D.H., Et al., Active shape models-their training and application, Computer Vision and Image Understanding, 61, 1, pp. 38-59, (1995)

← 1 2 →