通过算法的移植，在试验箱TMS320DM642基本实现了前景目标的提取，以及实现了基于边缘的运动目标的检测。-Through the transplantation of the algorithm, in the chamber TMS320DM642 the basic realization of the extraction of foreground objects and the realization of the moving target detection based on

详细描述了图像处理在钢材缺陷检测方面的前景，应用以及趋势。-Detailed Descr iption of the foreground image processing, applications and trends in the steel defect detection. .

Tracking moving objects in video sequence is an important problem in computer vision, with applications several fields, such as video surveillance and target tracking. Most techniques reported in the literature use background subtraction tech

This paper advances prior work by proposing a joint learning framework to simultaneously identify the spatial and temporal extents of the action of interest in training videos. To get pixel-level localization results, our method uses dense traj