面向小目标检测的卫星视频跟踪算法  

Multi-object tracking by detecting small objects in satellite video

作　　者：崔浩文 许楚杰 郑向涛[1] 卢孝强[1] CUI Haowen;XU Chujie;ZHENG Xiangtao;LU Xiaoqiang(Key Laboratory of Spectral Imaging Technology,Xi’an Institute of Optics and Precision Mechanics,Chinese Academy of Sciences,Xi’an 710119,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院西安光学精密机械研究所光谱成像技术实验室,西安710119 [2]中国科学院大学,北京100049

出　　处：《遥感学报》2024年第7期1812-1821,共10页NATIONAL REMOTE SENSING BULLETIN

基　　金：国家自然科学基金(编号:62271484);国家杰出青年科学基金(编号:61925112);陕西省创新能力支撑计划(编号:2020TD-015)。

摘　　要：遥感卫星的多目标跟踪任务面监目标弱小,场景多样等挑战。为此,提出了一种高分辨率遥感卫星视频的多目标跟踪算法。在检测阶段,构建小目标检测器,首先在主干网络中通过Transformer捕获全局的上下文信息,然后利用注意力机制增强目标特征,最后添加了一个预测小目标的分支;在轨迹关联阶段,将检测出的小目标与已有轨迹匹配,采用关注低置信度检测的关联算法。本文选取高分辨率遥感卫星视频进行测试,测验结果表明本文提出的方法在遥感卫星视频中的多目标跟踪数据集上的MOTA指标达到63.1%,相较于基准(baseline)模型提升13.5%,能够显著提升遥感卫星视频中多目标跟踪的性能。Multi-object tracking determines the position of an object and estimates the trajectory of objects in remote sensing satellite videos.This method has attracted considerable interest,and its application to security monitoring,motion analysis,and intelligent transportation has been explored.Compared with surveillance videos,remote sensing satellite videos contain smaller objects and a larger background,and thus the foreground object is difficult to detect.In addition,remote sensing satellite videos are extremely large,requiring massive computation and storage.Multi-object tracking in remote sensing satellite videos have high real-time requirements.Based on the mentioned problems,a multi-object tracking method for remote sensing satellite videos is proposed in this paper,which adopts tracking-bydetection paradigm.First,the backbone added a transformer that capture the global context information in the detection stage,enabling the detector to distinguish between objects and background.Then,an attention mechanism was used to enhance objects’features,enabling the proposed method to focus on the region of objects.Finally,an extra prediction branch was added to the network to generat a high-resolution feature map,which retained the details of small objects and was beneficial to small-object detection.Owing to the small objects and occlusion in remote sensing satellite videos,the confidence of hard positive samples was quite low.In the data association stage,an association strategy was adopted,which considered high and low confidence detection simultaneously and associated detected small objects with existing trajectories.To verify the effectiveness of the proposed method,ablation and comparison experiments were carried out on the remote sensing satellite videos dataset.The proposed method achieved 63.1%MOTA and 78.0%IDF1.The proposed method showed optimal performance,which reflected its suitability for multi-object tracking in remote sensing satellite videos.The proposed method ranked second in the multi-object trackin

关 键 词：遥感 多目标跟踪 小目标检测 注意力机制 神经网络 轨迹关联 

分 类 号：TP701[自动化与计算机技术—检测技术与自动化装置] P2[自动化与计算机技术—控制科学与工程]