Object detection using Edge Direction Histogram features

被引：3
作者：
机构：
[1] School of Computer and Information Science, Hubei Engineering University, 432000, Xiaogan
[2] School of Computer and Information Technology, Nanyang Normal University, 473061, Nanyang
来源：
Wang, G. | 1600年 / Asian Network for Scientific Information卷 / 12期
关键词：
Edge Direction Histogram; Feature descriptor; Hough voting; Object detection;
D O I：
10.3923/itj.2013.8275.8280
中图分类号：
学科分类号：
摘要：
In In this study, we propose an object detection approach using edge direction histogram features. Since edge points are related to shape information closely. Edge Direction Histogram (EDH) is a very simple and direct way to characterize shape information of an object. We divide an object into several parts and employ edge direction histogram method to extract the EDH features. The EDH descriptor is designed to decouple variations of the object due to affine warps and other forms of shape deformations. We further train a support vector machine classifier for each object part and apply a generalized Hough voting scheme to generate object locations and scales. We evaluate the proposed approach on two different kinds of objects: Car and h. Experimental results show that the proposed approach is efficient and robust in object detection. © 2013 Asian Network for Scientific Information.
引用
收藏
页码：8275 / 8280
页数：5
相关论文
共 32 条
  • [1] Agarwal S., Roth D., Learning a sparse representation for object detection, Proceedings of the 7th European Conference on Computer Vision Copenhagen, Denmark, 2353, pp. 113-127, (2002)
  • [2] Agarwal S., Awan A., Roth D., Learning to detect objects in images via a sparse, part-based representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 11, pp. 1475-1490, (2004)
  • [3] Agarwal S., Awan A., Roth D., UIUC Image Database for Car Detection, (2004)
  • [4] Amit Y., Trouve A., POP: Patchwork of parts models for object recognition, International Journal of Computer Vision, 75, 2, pp. 267-282, (2007)
  • [5] Ballard D.H., Generalizing the hough transform to detect arbitrary shapes, Patt. Recog., 13, pp. 111-122, (1981)
  • [6] Bosch A., Zisserman A., Muoz X., Image classification using ROIs andmultiple kernel learning, Int. J. Comput. Vision, (2008)
  • [7] Bouchard G., Triggs B., Hierarchical part-based visual object categorization, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, I, pp. 710-715, (2005)
  • [8] Chang C.C., Lm C.J., LIBSVM-A Library for Support Vector Machines, (2007)
  • [9] Crandall D., Felzenszwalb P., Huttenlocher D., Spatial priors for part-based recognition using statistical models, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattem Recognition, 1, pp. 10-17, (2005)
  • [10] Dalal N., Triggs B., Histograms of oriented gradients for human detection, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, I, pp. 886-893, (2005)
1234