A lightweight convolutional network for infrared object tracking

Abstract

As an important application of computer vision, visual tracking has being a fundamental topic. Compared with visible image, infrared image has the characteristic of low resolution, blurred contour and single color feature. Thus, it is still a challenge for infrared object tracking. Further, it is difficult to balance the real-time performance and accuracy. This paper proposed a tracker based on the SiamRPN tracker with a deeper and lightweight MobileNet V2 structure as the backbone network. During network training, the weights are updated by the scheme of the model-independent metalearning method. The computed model only passes a few gradient descents on the first frame can obtains the most suitable for the current frame. In the end, the tracker is tested on various datasets. Experimental results show that the tracker can achieve a balance between tracking accuracy and inference speed, which is crucial for deployment on mobile devices.