基于数学形态学的运动目标检测算法

帧差法和背景差法都是重要的运动目标检测方法,帧差法不能完全提取出目标的所有相关点,而背景差法又受环境光照的影响。针对传统运动目标检测算法的不足,提出一种基于数学形态学的帧差法与背景差法相结合的运动目标检测算法。先将帧差法得到的图像经过数学形态学处理,再将其与背景差法得到的图像相结合。实验表明,该算法能适应复杂变化的环境,准确地提取运动目标,对复杂干扰场景下的实时运动目标检测得到了较为满意的效果。

Algorithm of moving target detection based on mathematical morphology

Inter-frame difference and background subtraction are both important methods to detect the moving target.Inter-frame difference can not get all the related pixels of the target,and background subtraction is influenced by the light and environmental change.In view of the faults of the traditional methods a moving target detecting method is proposed based on the combination of background subtraction and inter-frame difference using mathematical morphology.The images obtained from inter-frame difference will be processed by mathematical morphology,and then combined with the images obtained from background subtraction.The calculation results show that the algorithm can adapt to the complex environmental change and perfectly detect the moving target.It has more satisfactory results for the real-time motion detecting under the interference of complex scenes.