The GF-4 geosynchronous orbit satellite can observe a large area for a long time, but the unique characteristics of its optical remote sensing image restrict the detection of maritime targets. This paper proposes a maritime target detection and tracking method for the GF-4 satellite image sequence based on the differences in information between frames in the image sequence. First, a preprocessing method is proposed for the unique characteristics of the image. Then, the ViBe (Visual Background Extractor) algorithm is used to extract the targets in the image sequence. After detection, the DCF-CSR (discriminative correlation filters with channel and spatial reliability) is used as a tracker to track and correlate the detected target to complete the task of predicting and monitoring the targets’ movements. Finally, through the comparative analysis of experiments with several classic methods, the feasibility and effectiveness of this method are verified.
High-speed moving target detection and tracking method based on speed estimation
