Hierarchical Convolution Fusion-Based Adaptive Siamese Network for Infrared Target Tracking

Infrared target tracking is a key technology in many applications of computer vision, such as traffic control, pedestrian surveillance, intelligent detection, and so on. However, due to the lack of color and texture information, tracking drift is easy to happen when the tracker encounters objects that are similar to the target in terms of grayscale distribution or contour shape. To address this issue, we propose a hierarchical convolution fusion-based adaptive Siamese (HCFA-Siam) network for infrared target tracking. First, in order to improve the discriminative capability of the network, a new hierarchical convolution fusion network is proposed to fuse the shallow spatial information and deep semantic information. Then, a channel attention module is followed to selectively enhance the feature channels of the infrared target, making the feature more discriminative. Finally, to further distinguish the target from the above-mentioned interference of appearance similarity, we add an adaptive update mechanism-based negative template pool at the front end of the network as the second input of the template branch. The experimental results on infrared sequences show that our method outperforms other state-of-the-art trackers in both success rate and precision.