飞控与探测2023，Vol.6Issue(4)：18-25,8.
基于相关滤波和轨迹预测的视频卫星动态目标跟踪算法
Video Satellite Moving Object Tracking Algorithm Based on Correlation Filter and Trajectory Prediction
摘要
Abstract
For video satellite moving object tracking under the conditions of occlusion or similar objects,an improved correlation filter algorithm is proposed.The correlation filter algorithm is combined with the interference discrimination module and trajectory prediction model based on the neural network.The values of the average peak-to-correlation energy and the adaptive threshold are compared to discriminate whether the tracker is interfered.The bi-directional long-short term memory network takes trajectory embeddings as the inputs for trajectory prediction.The object in the video is located by combining the output of the correlation filter and the network.Experiments in-dicate that the proposed algorithm improves the tracking precision by 2.10%,and it could achieve better tracking performance in satellite videos even with occlusion or similar objects.关键词
卫星视频/视觉跟踪/轨迹预测Key words
satellite video/visual tracking/trajectory prediction分类
信息技术与安全科学引用本文复制引用
苏雨,李润泽,张科..基于相关滤波和轨迹预测的视频卫星动态目标跟踪算法[J].飞控与探测,2023,6(4):18-25,8.基金项目
国家自然科学基金(62106200) （62106200）
西北工业大学硕士研究生实践创新能力培育基金(PF2023042) （PF2023042）
