A scale-adaptive kernel correlation filtering（KCF） target tracking algorithm combined with the learning rate adjustment is proposed. Initial position of the target is obtained by using the KCF

and a lowcomplexity scale estimation scheme is used to obtain the scale of target

which improves the ability of the algorithm to adapt to the change of the scale of target

and the tracking speed is also ensured. Average difference between two adjacent images is used to analyze the change of the image

and the learning rate of the target model is adjusted in segments according to the average difference to solve the tracking failure problem when the target is severely obstructed. Compared the proposed algorithm with other five classic target tracking algorithms

the experimental results show that the proposed algorithm is well adapted to the complex environments such as scale change of target

severe occlusion and background interference. At the same time

it has a real-time tracking speed of 231 frame/s.