Wood Detection and Tracking in Videos of Rivers
Rivers during floods bring a lot of fallen trees and debris. Video surveillance systems are installed on strategically important places on the rivers. To protect these places from destructions due to accumulation of wood, such systems must be able to automatically detect wood. Image segmentation is performed to separate wood and other moving elements from the rest of the water. Moving objects are detected with respect to brightness and temporal variation features. The floating wood is then tracked in the sequence of frames by temporal linking of the segments generated in the detection step. Our algorithm is tested on multiple videos of floods and the results are evaluated both qualitatively and quantitatively.
KeywordsImage Segmentation Gaussian Mixture Model Water Wave Consecutive Frame Representative Point
- 5.Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practices of background maintenance. In: IEEE Int. Conf. Computer Vision (ICCV), pp. 255–261 (1999)Google Scholar
- 7.Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. In: IEEE Conf. Comp. Vision and Pattern Recog. (CVPR), pp. 302–309 (2004)Google Scholar
- 10.Gao, X., Boult, T., Coetzee, F., Ramesh, V.: Error analysis of background adoption. In: IEEE Conf. Comp. Vision and Pattern Recog. (CVPR), pp. 503–510 (June 2000)Google Scholar
- 11.Ali, I., Tougne, L.: Unsupervised video analysis for counting of wood in river during floods. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Kuno, Y., Wang, J., Pajarola, R., Lindstrom, P., Hinkenjann, A., Encarnação, M.L., Silva, C.T., Coming, D. (eds.) ISVC 2009. LNCS, vol. 5876, pp. 578–587. Springer, Heidelberg (2009)CrossRefGoogle Scholar