The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking

By Dawei Du, Yuankai Qi, Hongyang Yu, Yi-Fan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian. European Conference on Computer Vision, 2018

990 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a213bbf9740854a276fdf71dad8f30cfbe3ea4d4

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization (2020, methodology): “UAVDT: UAVDT [47] mainly emphasizes vehicle tracking in various scenarios.”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “The Unmanned Aerial Vehicle Benchmark [145] includes single and multiple bounding boxes for detection and tracking in various flight conditions.”
Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, neutral): “5k 12029×5014 √ 2018 UAVDT [36] drone R 80k 3 280.”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “…tracking evaluation datasets include the PETS09 (Ferryman and Shahrokni, 2009), PETS16 (Patino), KITTI (Geiger et al., 2012), MOT15 (Leal-Taix´e et al., 2015) and MOT16 (Milan et al., 2016), and UAVDT (Du et al., 2018) (Zitnick and Doll´ar, 2014) with the number of proposal ﬁxed at 5 , 000.”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, background): “OTB2015 [220], VOT2018 [39], LaSOT [221], UAV123 [222], UAVDT [223], and VisDrone2019 [224], and the state-of-theart visual trackers are analyzed based on different aspects.”
Block-NeRF: Scalable Large Scene Neural View Synthesis (2022, background): “Reconstructing large-scale environments enables several important use-cases in domains such as autonomous driving [32,44,68] and aerial surveying [14,35].”
Learning Rich Features at High-Speed for Single-Shot Object Detection (2019, methodology): “The black regions are ignored in UAVDT dataset images [9].”
A Review on Deep Learning in UAV Remote Sensing (2021, neutral): “, 2018], UAVDT [Du et al., 2018], VisDrone [B et al.”
D2Det: Towards High Quality Object Detection and Instance Segmentation (2020, methodology): “Experiments are performed on the MS COCO [33] and UAVDT [11] datasets.”
Clustered Object Detection in Aerial Images (2019, methodology): “The maximum number of clusters (TopN) in cluster chip generation is empirically set to 3 on VisDrone [37], 2 on UAVDT [8], and 5 on the DOTA [33].”
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction (2024, neutral): “Large scene reconstruction is essential for many applications, including autonomous driving [22, 33, 54], aerial sur-veying [6, 13], and virtual reality, which require photo-realistic visual quality and real-time rendering.”
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results (2019, methodology): “Compared with the previous drone based datasets [29, 15, 9], a larger scale drone based object detection dataset [48] is proposed to evaluate detection algorithms in real scenarios.”
UAVid: A semantic segmentation dataset for UAV imagery (2018, methodology): “Although there are existing UAV datasets for detection, tracking, and behavior analysis [41, 16, 27, 29], to the best of our knowledge, there exists only one low altitude UAV semantic segmentation dataset before our UAVid, namely the Aeroscapes [19] dataset.”
Guided Attention Network for Object Detection and Counting on Drones (2019, methodology): “dataset [6], we compute the Average Precision (AP@0.”
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.”