A Method of Counting Pedestrians in Crowded Scenes
This paper proposes a method to automatically count the number of pedestrians in a video input of a crowed scene. The method proposed in this paper improves on our previous pedestrian counting method which estimates the number of pedestrians by accumulating low-level features (foreground pixels and motion vectors) on a virtual gate. To handle crowded scenes, the pedestrian counting process in this paper is weighted by the ratio of foreground pixels in the scene. The relationship between crowdedness and weighting factor is learned from 10,000 simulation images. Tests on real video sequences show that this method can successfully estimate the number of pedestrians with an accuracy of about 95%. Also, when compared to the previous method, the accuracy was increased by about 5% for highly crowded scenes. Moreover, the proposed method runs at an average rate of around 60 fps on a standard PC, which makes the algorithm realistic for multi-camera systems.
KeywordsVisual surveillance People counting Pedestrian flow
Unable to display preview. Download preview PDF.
- 1.Chen, T.H., Chen, T.Y., Chen, Z.X.: An Intelligent People-Flow Counting Method for Passing Through a Gate. In: Robotics, Automation and Mechatronics 2006 IEEE Conference, pp. 1–6 (2006)Google Scholar
- 2.Velipasalar, S., Tian, Y.-L., Hampapur, A.: Automatic Counting of Interacting People by using a Single Uncalibrated Camera. In: Multimedia and Expo., 2006 IEEE International Conference, pp. 1265–1268 (2006)Google Scholar
- 3.Terada, K., Yoshida, D., Oe, S., Yamaguchi, J.: A Method of Counting the Passing People by Using the Stereo Images. International Conference of Image Processing 2, 338–342 (1999)Google Scholar
- 5.Liu, X., Tu, P.H., Rittscher, J., Perera, A., Krahnstoever, N.: Detecting and Counting People in Surveillance Applications. Advanced Video and Signal Based Surveillance, pp. 306–311 (2005)Google Scholar
- 6.Sidla, O., Lypetskyy, Y., Brandle, N., Seer, S.: Pedestrian Detection and Tracking for Counting Applications in Crowded Situations. Advanced Video and Signal Based Surveillance, pp. 70–75 (2006)Google Scholar
- 7.Lee, G.G., Kim, B.S., Kim, W.Y.: Automatic Estimation of Pedestrian Flow. In: ACM/IEEE International Conference on Distributed Smart Cameras, pp. 291–296 (2007)Google Scholar
- 8.Stauffer, C., Grimson, W.E.L.: Adaptive Background Mixture Models for Real-Time Tracking. Compute Vision and Pattern Recognition 2, 246–252 (1999)Google Scholar
- 9.Kim, B.S., Lee, G.G., Hong, Y.-G., Seo, H.T., Kim, W.Y.: Method of Eliminating Shadow of Moving Object for Video Surveillance. In: IEEK Fall Conference, Korea, pp. 768–771 (2006)Google Scholar
- 10.Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: DARPA Image Understanding Workshop, pp. 121–130 (1981)Google Scholar
- 11.Lee, G.G., Song, S.H., Kim, W.Y.: Crowd Density Estimation for Video Surveillance. In: International Conference on Computing, Communications and Control Technologies, pp. 196–199 (2006)Google Scholar
- 13.PETS, Benchmark Data (2006), http://www.cvg.rdg.ac.uk/PETS2006/data.html