To solve the problem that it is diffic ult to obtain the accurate estimations of the multiple targets in video with complex environment,we propose an adaptive multi-target tracking algorith m under the framework of multi-Bernoulli filter.First,the kernel density background subtraction techniqu e is introduced in this paper,which can effectively restrain the background interference.Then,continuously adaptive mean shift (CAMShift) method is integrated into the framework of multi-Bernoulli filter,and adaptive mechan isms are proposed to handle problems of closely spaced target tracking and the variation of target size.In addition,particle labeling technique is introduced to identify the path of each target in the video.Experimental result s show that the proposed algorithm with strong robustness can effectively achiev e the visual multi-target tracking in complex circumstances.