Target tracking based on staring multispectral imager
Zijian Cui, Honglin Ji · 2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA) · 2022
In the actual dim target tracking problems, there are often interference targets similar to the detected targets. At this time, it is often difficult to ensure the accuracy of recognition and tracking if only rely on the spectral feature of a single infrared band or the motion feature of the detected targets. Therefore, based on the staring multispectral imaging system, a target tracking method based on multispectral feature fusion is proposed, which solves the problem of indistinguishable small and weak targets in single-band infrared images and improves the accuracy of recognition and tracking.