Real-time infrared small target search and tracking algorithm based on adaptive track correlation

In this paper, the imaging characteristics and motion characteristics of small targets in infrared images are analyzed from the perspective of space domain and time domain respectively, and a real-time infrared small target search and tracking algorithm based on adaptive track correlation is proposed. From the perspective of spatial domain, the curvature filtering algorithm is used to suppress the background according to the feature that the small target usually presents a sharp peak on the 3D surface with gray value as Z-axis. From the perspective of time domain, according to the difference of motion state between the target and the false alarm point, the track correlation method is used to further suppress the false alarm rate and realize the search and tracking of the target. In this paper, the concept of cosine similarity is introduced to judge the matching degree between suspected target and track on the basis of the traditional track correlation algorithm based on the idea of "nearest neighborhood", so as to reduce the probability of wrong track correlation. At the same time, based on residual analysis, the correlation gate size is selected adaptively and the observation results are smoothing by adaptive first-order low-pass filtering. Experiments show that the search and tracking algorithm proposed in this paper has real-time performance and high accuracy, and has good adaptability to different scenes.