Research on target detection based on spatio-temporal filtering and KCF under low light conditions

Weak light environment poses challenges for target detection. It is difficult for the existing target detection algorithms to track the target in the noise-flooded image. In order to improve the accuracy of the target detection algorithm, it is necessary to process the low-light image first. In this paper, a time-domain filter is used, which combines the dynamic detection of time-domain filter and the denoising ability of spatio-temporal filter to provide help for target detection under low light conditions. This paper focuses on the motion compensation filtering by calculating the associated parameters of the front and back frames through multi-direction edge filtering. The down-sampling differential pyramid is used to avoid the discontinuity of the partition blocks. A convolutional strong edge detection method based on multi-directional template is proposed to improve the edge detection function of traditional spatial filtering template. Finally, kernel correlation filtering (KCF) is applied to the image to realize target detection. By comparing the target detection rate and accuracy before and after filtering, it is proved that the algorithm can effectively improve the detection ability of low-light level image. By comparing with other algorithms, it is proved that the proposed algorithm has more advantages than the uncombined traditional algorithm.