Affiliation:
1. Zhengzhou Tourism College
2. North China University of Water Resources and Electric Power
3. ZhengZhou Metro
Abstract
Video moving target detection is an important foundation issues in computer vision, based on the analysis of the advantages and disadvantages of each existing moving target detection model, using Bayesian statistical theory as a framework, proposes a statistical model that can detect moving objects in video in real-time. The model combines time, space and color and other relevant information of pixel, divides and extracts Video segmentation’s foreground. By selecting the appropriate reference background can improve the precision and accuracy of the detection.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. Chan K L. Detection of swimmer using dense optical flow motion map and intensity information. Machine Vision and Applications. 2013, 24(1): 75-101.
2. Li L, Huang W, Gu Y, et al. Statistical modeling of complex backgrounds for foreground object detection. IEEE Transactions on Image Processing. 2004, 13(11): 1459-1472.
3. Munoz-Salinas R, Aguirre E, Garcia-Silvente M. People detection and tracking using stereo vision and color. Image and Vision Computing. 2007, 25(6): 995-1007.
4. Araki S, Matsuoka T, Yokoya N, et al. Real-Time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence. IEICE TRANSACTIONS on Information and Systems. 2000, E83-D(7): 1583-1591.
5. Elgammal A, Harwood D, Davis L. Non-parametric Model for Background Subtraction. Computer Vision-ECCV 2000. 2000: 751-767.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献