Detecting Moving Targets from Traffic Video Based on the Dynamic Background Model
- 836 Downloads
An efficient method to detect the moving target in traffic video based on the dynamic background model is proposed in this paper, after analyzing existing methods for target detection. The model of target detection is given firstly, then a rough set weighted classification method for video image is presented. Based on the video classifications, the background model is established on the historical data. The background judgment and moving object detection for video are done with this model and then the background model is updated with the current video. The experimental results show that this method can adapt the diversification of background and has high adaptability and precision. The processing speed can meet the requirement of real time detection.
Keywordsimage processing rough set weighted classification transportation monitoring dynamic background mode
Unable to display preview. Download preview PDF.
- 6.Wenxiu, Z., et al.: Rough Set Theory and Method, pp. 17–25. Science publisher, Beijing (2001)Google Scholar
- 8.Tsai, L.-W., Hsieh, J.-W., Fan, K.-C.: Vehicle detection using normalized color and edge map. In: IEEE International Conference on Image Processing (ICIP 2005), September 11–14 2005, vol. 2, pp. 598–601 (2005)Google Scholar
- 9.Jacques, J.C.S., Jung, C.R., Musse, S.R.: Background Subtraction and Shadow Detection in Grayscale Video Sequences Computer Graphics and Image Processing. In: 18th Brazilian Symposium on SIBGRAPI 2005, pp. 189–196 (2005)Google Scholar
- 11.Youtian, D., Feng, C., Wenli, X.: Region-based moving shadow detection approach. Journal of Tsinghua University (Science and Technology) 1, 141–144 (2006)Google Scholar