Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models

By Siyi Li, Dit-Yan Yeung. AAAI Conference on Artificial Intelligence, 2017

415 citations recorded by the source corpus.

Despite recent advances in the visual tracking community, most studies so far have focused on the observation model. As another important component in the tracking system, the motion model is much less well-explored especially for some extreme scenarios. In this paper, we consider one such scenario in which the camera is mounted on an unmanned aerial vehicle (UAV) or drone. We build a benchmark dataset of high diversity, consisting of 70 videos captured by drone cameras. To address the challenging issue of severe camera motion, we devise simple baselines to model the camera motion by geometric transformation based on background feature points. An extensive comparison of recent state-of-the-art trackers and their motion model variants on our drone tracking dataset validates both the necessity of the dataset and the effectiveness of the proposed methods. Our aim for this work is to lay the foundation for further research in the UAV tracking area.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6ebc40a061433c24a3ea1f305bb6533b8f3dd5f4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Vision Meets Drones: A Challenge (2018, methodology): “[30] capture 70 video sequences of high diversity by drone cameras and manually annotate the bounding boxes of objects for single object tracking evaluation.”
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking (2019, methodology): “More specifically, ARCF-HC has achieved an advancement of 8.1% (UAV123@10fps), 9.8% (DTB70) and 5.2% (UAVDT) respectively from BACF in AUC in occlusion cases.”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, neutral): “[48], OTB2015 [186], TC128 [187], UAV123 [188], NUS-PRO [189], NfS [190], DTB [191], TrackingNet [192], OxUvA [193], BUAA-PRO [194], GOT10k [195], and LaSOT [196] are com-”
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization (2020, background): “invariant feature and bridge the visual appearance gap, and (2) design effective methods that fully exploit the rich information contained in multi-view data. With the recent development of the drone [10, 13, 38], we reveal that the drone could serve as a primary data collection platform for cross-v”
AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization (2020, methodology): “DTB70: DTB70 [46], composed of 70 difficult UAV image sequences, primarily addresses the problem of severe UAV motion.”