基于Canny检测算法实现的目标跟踪

为了设计一种实时高效、稳定可靠的图像目标跟踪系统平台,避免因图像边缘提取效果差而引起跟踪失败,采用自适应Canny边缘检测算法。该自适应算法能够很好的确定平滑参数以及高、低两个阈值,更好的获得图像边缘图。经Canny算法处理图像目标后,获得目标的单像素边缘图,根据边缘图计算得到目标质心。利用最小二乘法拟合出目标的运动轨迹,同时可根据时间间隔预测出目标质心的下一位置,控制伺服机构,实现目标跟踪。实验表明,采用Canny算法的目标跟踪系统,能够满足实时跟踪的需要。

Target tracking system based on Canny algorithm

In order to design a real-time stable and reliable platform for image target tracking system, to avoid tracking failures caused by poor performance of algorithm, adaptive Canny edge detection algorithm is proposed. The adaptive algorithm can determine a better smoothing parameter and the high and low thresholds, better to obtain the image edge map. After processing the target image and getting single pixel edge map, centroid can be calculated. Then estimate target trajectory by using Least- squares method, control servo mechanics to track the target. Experiments show that the system using Canny algorithm for target tracking system can meet the real-time tracking needs.