融合特征的卫星视频车辆单目标跟踪  

Integrating multiple features for tracking vehicles in satellite videos

作　　者：韩鸣飞 李盛阳[1,2,3] 万雪 轩诗宇 赵子飞 谭洪 张万峰[1,2] Han Mingfei;Li Shengyang;Wan Xue;Xuan Shiyu;Zhao Zifei;Tan Hong;Zhang Wanfeng(Technology and Engineering Center for Space Utilization,Chinese Academy of Sciences,Beijing 100094,China;Key Laboratory of Space Utilization,Chinese Academy of Sciences,Beijing 100094,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院空间应用工程与技术中心,北京100094 [2]中国科学院太空应用重点实验室,北京100094 [3]中国科学院大学,北京100049

出　　处：《中国图象图形学报》2021年第11期2741-2750,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(41701468,41971329);遥感信息与图像分析技术国家级重点实验室基金项目(Y8180711WN)。

摘　　要：目的卫星视频作为新兴遥感数据,可以提供观测区域高分辨率的空间细节信息与丰富的时序变化信息,为交通监测与特定车辆目标跟踪等应用提供了不同于传统视频视角的信息。相较于传统视频数据,卫星视频中的车辆目标分辨率低、尺度小、包含的信息有限。因此,当目标边界不明、存在部分遮挡或者周边环境表观模糊时,现有的目标跟踪器往往存在严重的目标丢失问题。对此,本文提出一种基于特征融合的卫星视频车辆核相关跟踪方法。方法对车辆目标使用原始像素和方向梯度直方图(histogram of oriented gradient,HOG)方法提取包含互补判别能力的特征,利用核相关目标跟踪器分别得到具备不变性和判别性的响应图;通过响应图融合的方式结合两种特征的互补信息,得到目标位置;使用响应分布指标(response distribution criterion,RDC)判断当前目标特征的稳定性,决定是否更新跟踪器的表征模型。本文使用的相关滤波方法具有计算量小且运算速度快的特点,具备跟踪多个车辆目标的拓展能力。结果在8个卫星视频序列上与主流的6种相关滤波跟踪器进行比较,实验数据涵盖光照变化、快速转弯、部分遮挡、阴影干扰、道路颜色变化和相似目标临近等情况,使用准确率曲线和成功率曲线的曲线下面积(area under curve,AUC)对车辆跟踪的精度进行评价。结果表明,本文方法较好地均衡了使用不同特征的基础跟踪器(性能排名第2)的判别能力,准确率曲线AUC提高了2.9%,成功率曲线AUC下降了4.1%,成功跟踪车辆目标,不发生丢失,证明了本文方法的先进性和有效性。结论本文提出的特征融合的卫星视频车辆核相关跟踪方法,均衡了不同特征提取器的互补信息,较好解决了卫星视频中车辆目标信息不足导致的目标丢失问题,提升了精度。Objective Satellite video is a new type of remote sensing system,which is capable of dynamic video and conventional image capturing.Compared with conventional very-high-resolution(VHR)remote sensing systems,a video satellite observes the Earth with a real-time temporal resolution,which has led to studies in the field of traffic density estimation,object detection,and 3D reconstruction.Satellite video has a strong potential in monitoring traffic,animal migration,and ships entering and leaving ports due to its high temporal resolution.Despite much research in the field of conventional video,relatively minimal work has been performed in object tracking for satellite video.Existing object tracking methods primarily emphasize relatively large objects,such as trains and planes.Several researchers have explored replacing or fusing the motion feature for a more accurate prediction of object position.However,few studies have focused on solving the problem caused by the insufficient amount of information of smaller objects,such as vehicles.Tracking vehicles in satellite video has three main challenges.The main challenge is the small size of the target.While the size of a single frame can be as large as 12000×4000 pixels,moving targets,such as cars,can be very small and only occupy 1030 pixels.The second challenge is the lack of clear texture because the vehicle targets contain limited and/or confusing information.The third challenge is that unlike aircraft and ships,vehicles are more likely to appear in situations where the background is complex,which makes tracking the vehicle more challenging.For instance,a vehicle may make quick turns,appear partially to the vehicle,or be marked by instant changes in illumination.Selecting or constructing a single image feature that can handle all the situations mentioned above is difficult.Using multiple complementary image features is proposed by merging them into a unified framework based on a lightweight kernelized correlation filter to tackle these challenges.Method First,two comp

关 键 词：目标跟踪 卫星视频 核化相关滤波 特征融合 车辆跟踪 

分 类 号：U495[交通运输工程—交通运输规划与管理] TP391.41[交通运输工程—道路与铁道工程]