High-performance tracker for infrared small targets

In optoelectronic systems, infrared target tracking is a critical function. Due to occlusion causing template drift in infrared target tracking, correlation filtering algorithms have poor performance for infrared targets. Although target trackers based on Siamese convolutional neural networks exhibit excellent tracking performance, their complex architecture and high computational complexity hinder their real-time application on embedded chips. Furthermore, the output of anchor-based trackers is often unstable, which can be detrimental to the closed-loop control of optoelectronic devices. Therefore, this paper proposes a tracker based on the Siamese network for infrared small target tracking and presents an innovative lightweight approach to enhance real-time performance while minimizing accuracy loss. With regards to different backbone network structures, the computational complexity required for embedded computing was initially analyzed. Subsequently, artificial intelligence interpretability methods were employed to assess the performance of distinct networks, select the optimal backbone network, and ultimately striking a balance between accuracy and speed. Ultimately, real-time operation is achieved on embedded devices.