arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.00518cs.CV
收藏

无人机基准:目标检测与跟踪

The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking

University of Chinese Academy of Sciences(中国科学院大学);Harbin Institute of Technology(哈尔滨工业大学);Harbin Institute of Technology, Weihai(哈尔滨工业大学(威海));The University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)

Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian

摘要:

无人机(UAV)具有高度机动性的优势,被用于推动计算机视觉中的许多重要应用,比具有固定摄像机角度、比例和视角的监控摄像机提供更高的效率和便利性。然而,提出的UAV数据集非常有限,并且它们仅关注于特定任务,例如在相对受限的场景中的视觉跟踪或目标检测。因此,建立一个无约束无人机基准测试系统对推动相关研究具有重要意义。在本文中,我们构建了一个新的无人机基准专注于复杂的场景与新的水平的挑战。从10小时的原始视频中选择,大约80,000个代表性帧用边界框以及多达14种属性(例如,天气条件、飞行高度、摄像机视野、车辆类别和遮挡),用于三个基本的计算机视觉任务:目标检测、单目标跟踪和多目标跟踪。然后,使用最新的国家的最先进的算法为每个任务进行详细的定量研究。实验结果表明,目前最先进的方法在我们的数据集上表现相对较差,这是由于基于无人机的真实场景中出现了新的挑战,例如,高密度、小对象和相机运动。据我们所知,我们的工作是第一次在无约束的场景中全面探讨这类问题。

英文摘要:

With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80,000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑