Weighted Histogram of Oriented Uniform Gradients for Moving Object Detection
With the growth of the automotive electronics technology, the advanced driver assistance system (ADAS) becomes more and more important. Especially, the moving object detection (MOD) is an important issue in the ADAS in intelligent vehicles. In realistic systems, there exist two critical challenges including computing time and detection rate for MOD. To overcome these problems, we propose a novel moving object detection system which contains pre-processing, feature extraction, classification and state machine. The pre-processing contains ROI extraction and skipping low busyness windows, which accelerates the computing time to solve the mentioned problem. To improve the performances, in this paper, the weighted histogram of oriented uniform gradient (WHOUG) with support vector machine (SVM) is proposed to promote the detection accuracy. Besides, the finite state machine could further improve the robustness of the proposed system. The results demonstrate that the proposed system achieves better performance than the traditional one, and also maintains real time computation.
KeywordsMoving object detection Histogram of oriented gradient Support vector machine
This work was supported by the Ministry of Science and Technology, Taiwan, under Grant MOST 105-2221-E-006-065-MY3.
- 1.Gavrila, D.M., Philomin, V.: Real-time object detection for smart vehicles. In: Proceedings of IEEE International Conference on Computer Vision, vol. 1, pp. 87–93 (1999)Google Scholar
- 4.Nguyen, D.T., Li, W., Ogunbona, P.: A part-based template matching method for multi-view human detection. In: Proceedings of IEEE International Conference on Image and Vision Computing, New Zealand, pp. 357–362 (2009)Google Scholar
- 6.Wu, B., Nevatia, R.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: Proceedings of IEEE International Conference on Computer Vision, vol. 1, pp. 90–97 (2005)Google Scholar
- 7.Zhu, Q., Yeh, M.C., Cheng, K.T.: Fast human detection using a cascade of histograms of oriented gradients. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1491–1498 (2006)Google Scholar
- 8.Chen, Y.T., Chen, C.S.: A cascade of feed-forward classifiers for fast pedestrian detection. In: Proceedings of Asian Conference on Computer Vision, pp. 905–914 (2007)Google Scholar
- 9.Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 878–885 (2005)Google Scholar
- 10.Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: Proceedings of European Conference on Computational Learning theory, pp. 23–37. Springer, Berlin (1995)Google Scholar
- 11.Belongie, S., Malik, J.: Matching with shape contexts. In: Proceedings of IEEE Workshop on Content-based Access of Image and Video Libraries, vol. 1, pp. 20–26 (2000)Google Scholar
- 12.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)Google Scholar
- 14.Bishop, G., Welch, G.: An introduction to the Kalman filter. In: Proceedings of SIGGRAPH, Course 8 (2001)Google Scholar
- 15.Dalal, N., Triggs, B.: INRIA Person Dataset (2005). http://pascal.inrialpes.fr/data/human/