基于边界边缘检测的在线产品轮廓跟踪

摘要

The real-time detection of moving products of assembly line, needing tracking effectively moving products, by selecting only tracked subject boundary edges in a video stream, is proposed. First,removing background edges using edge motion, selecting boundary edges using a normal direction derivative of the tracked contour. Accurate tracking is based on reduction of the effects of irrelevant edges, by only selecting boundary edge pixels. In order to remove background edges using edge motion, the tracked subject motion is computed and edge motions and edges having different motion directions from the subjects are removed. And moving product' s contour is obtained. Simulation results show that the method of tracking with complicated scene of texture on product line, has strong robustness.%产品流水线实时检测需有效解决流水线上运动产品的图像跟踪,提出仅选择在视频码流中跟踪目标的一个边界边缘来实现产品轮廓的跟踪.首先利用边缘运动去除背景,随后使用跟踪轮廓的正常方向导数选择边界边缘.准确跟踪是基于减少无关边缘的影响,因此仅选择边界边缘像素.使用边缘运动消除背景边缘需要计算跟踪目标的运动,同时移除边缘的运动和边缘与目标不同方向的运动,从而得到运动产品的轮廓.仿真实验结果表明,该跟踪方法对流水线上的产品有较好的跟踪效果,且具有较强的稳健性.