针对传统的红外目标跟踪算法对被跟踪目标出现形变、部分或全部遮挡后目标易发生丢失的问题,提出一种新的红外目标跟踪算法。该算法采用双边滤波处理方式并结合中值光流法,建立一种自适应红外目标模型,以达到准确、稳定跟踪目标的目的。实验结果表明,该算法能够有效跟踪变形或遮挡目标,且实时性强,准确率高,鲁棒性好。
In view of the traditional infrared target tracking algorithm appears to be tracked target goal after deformation, partial or full shade prone to leakage problems, a new infrared target tracking algorithm was put forward. The combines with the median optical flow method, algorithm adopts bilateral filtering approach and an adaptive infrared target model is set up, in order to achieve the purpose of accurate and stable tracking target. Experimental results show that the algorithm can effectively track deformation or screening targets, and the algorithm owns features of strong real time, high accuracy and good robustness.