arXiv 2402.045192024-02-07cs.CV

BioDrone：基于仿生无人机的单目标跟踪基准，用于鲁棒视觉

BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision

School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Instrument Science and Engineering, Southeast University（东南大学仪器科学与工程学院）；Suzhou Institute of Nano-tech and Nano-bionics, Chinese Academy of Sciences（中国科学院苏州纳米技术与纳米仿生研究所）；Department of Computer Science, Stony Brook University（石溪大学计算机科学系）；Biostatistics & Medical Informatics Computer Sciences, University of Wisconsin-Madison（威斯康星大学麦迪逊分校生物统计学与医学信息学计算机科学系）

Xin Zhao, Shiyu Hu, Yipei Wang, Jing Zhang, Yimin Hu, Rongshuai Liu, Haibin Ling, Yin Li, Renshu Li, Kun Liu, Jiadong Li

备注：: This paper is published in IJCV (refer to DOI). Please cite the published IJCV
发表信息：: Int J Comput Vis (2023)
DOI：: 10.1007/s11263-023-01937-0

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出BioDrone，首个基于仿生无人机的单目标跟踪基准，针对微小目标和快速运动挑战，提供最大规模数据集及系统评估，为鲁棒视觉研究奠定基础。

摘要：

单目标跟踪（SOT）是计算机视觉中的一个基本问题，具有广泛的应用，包括自动驾驶、增强现实和机器人导航。SOT的鲁棒性面临两个主要挑战：微小目标和快速运动。这些挑战在无人机（UAV）拍摄的视频中尤为明显，其中目标通常距离相机较远，并且相对于相机常有显著运动。为了评估SOT方法的鲁棒性，我们提出了BioDrone——首个基于仿生无人机的SOT视觉基准。与现有的无人机数据集不同，BioDrone的特色在于视频由扑翼无人机系统拍摄，由于其空气动力学特性，存在显著的相机抖动。因此，BioDrone强调了对连续帧之间发生剧烈变化的微小目标的跟踪，为SOT提供了新的鲁棒视觉基准。迄今为止，BioDrone提供了最大的基于无人机的SOT基准，具有高质量细粒度的人工标注，并自动生成帧级标签，专为鲁棒视觉分析而设计。利用我们提出的BioDrone，我们对现有SOT方法进行了系统评估，比较了20个代表性模型的性能，并研究了优化一种最先进方法（KeepTrack）以实现鲁棒SOT的新途径。我们的评估为鲁棒SOT提供了新的基线和见解。展望未来，我们希望BioDrone不仅能作为鲁棒SOT的高质量基准，还能引发未来对鲁棒计算机视觉的研究。数据库、工具包、评估服务器和基线结果可在http://biodrone.aitestunion.com获取。

英文摘要：

Single object tracking (SOT) is a fundamental problem in computer vision, with a wide range of applications, including autonomous driving, augmented reality, and robot navigation. The robustness of SOT faces two main challenges: tiny target and fast motion. These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera. To evaluate the robustness of SOT methods, we propose BioDrone -- the first bionic drone-based visual benchmark for SOT. Unlike existing UAV datasets, BioDrone features videos captured from a flapping-wing UAV system with a major camera shake due to its aerodynamics. BioDrone hence highlights the tracking of tiny targets with drastic changes between consecutive frames, providing a new robust vision benchmark for SOT. To date, BioDrone offers the largest UAV-based SOT benchmark with high-quality fine-grained manual annotations and automatically generates frame-level labels, designed for robust vision analyses. Leveraging our proposed BioDrone, we conduct a systematic evaluation of existing SOT methods, comparing the performance of 20 representative models and studying novel means of optimizing a SOTA method (KeepTrack KeepTrack) for robust SOT. Our evaluation leads to new baselines and insights for robust SOT. Moving forward, we hope that BioDrone will not only serve as a high-quality benchmark for robust SOT, but also invite future research into robust computer vision. The database, toolkits, evaluation server, and baseline results are available at http://biodrone.aitestunion.com.

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。