【摘要】 提出一种动态场景下多运动目标检测的方法.该方法融合基于帧间图像差值的运动分割技术以及区域生长法来获得各运动目标的初始轮廓,再利用主动轮廓线模型进行优化,从而得到各运动目标的最优轮廓.该方法具有以下明显特点:允许背景任意复杂;在无补偿情况下仍能得到良好结果;目标大小不影响算法的鲁棒性.实验证明了该方法的有效性、实用性和鲁棒性.更多还原

【Abstract】 An approach is presented to detect the moving multi-targets in dynamic scenes. The method extracts the contour of each moving object based on the fusion of a motion segmentation technique using image subtraction and region growing process. The final result after the optimization with active contour model can be achieved. The background can be arbitrarily complicated by using this method. Good results can be obtaind without motion compensation. The robustness can not be influenced by the size of the target. Experimental results show that the algorithm is reliable, practical and robust.更多还原