VisDrone-MOT2019: The Vision Meets Drone Multiple Object Tracking Challenge Results

Wen, Longyin; Zhang, Yue; Bo, Liefeng; Shi, Hailin; Zhu, Rui; Jadhav, Ajit; Dong, Bing; Lall, Brejesh; Liu, Chang; Zhang, Chunhui; Wang, Dong; Zhu, Pengfei; Feng, Nan; Bunyak, Filiz; Wang, Gaoang; Liu, Guizhong; Seetharaman, Guna; Li, Guorong; Ardö, Håkan; Zhang, Haotian; Yu, Hongyang; Lu, Huchuan; Du, Dawei; Hwang, Jenq‐Neng; Mu, Jiatong; Hu, Jinrong; Palaniappan, Kannappan; Chen, Long; Ding, Lu; Lauer, Martin; Nilsson, Mikael; Al-Shakarji, Noor M.; Mukherjee, Prerana; Bian, Xiao; Huang, Qingming; Laganière, Robert; Chen, Shuhao; Pan, Siyang; Kaushik, Vinay; Shi, Wei; Tian, Wei; Li, Weiqiang; Chen, Xin; Zhang, Xinyu; Ling, Haibin; Zhang, Yanting; Zhao, Yanyun; Wang, Yong; Song, Yue; Yao, Yuehan; Chen, Zhaotang; Xu, Zhenyu; Xiao, Zhibin; Tong, Zhihang; Luo, Zhipeng; Hu, Qinghua; Sun, Zhigang; Zheng, Jianming; Peng, Tao; Wang, Xinyao

doi:10.1109/iccvw.2019.00028

Cited by 24 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What's more, our method achieves the highest accuracy in all categories, which proves the effectiveness of our method strongly. More experimental results and analysis on test set can refer to VisDrone-VDT2018 [47] and VisDrone-MOT2019 [48].…”

Section: Results On Test Setmentioning

confidence: 99%

Multiple Object Tracking with Motion and Appearance Cues

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

Due to better video quality and higher frame rate, the performance of multiple object tracking issues has been greatly improved in recent years. However, in real application scenarios, camera motion and noisy per frame detection results degrade the performance of trackers significantly. High-speed and high-quality multiple object trackers are still in urgent demand. In this paper, we propose a new multiple object tracker following the popular tracking-by-detection scheme. We tackle the camera motion problem with an optical flow network and utilize an auxiliary tracker to deal with the missing detection problem. Besides, we use both the appearance and motion information to improve the matching quality. The experimental results on the VisDrone-MOT dataset show that our approach can improve the performance of multiple object tracking significantly while achieving a high efficiency.

show abstract

Section: Results On Test Setmentioning

confidence: 99%

Multiple Object Tracking with Motion and Appearance Cues

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A. Experimental setting 1) Datasets: The GLOA is trained and evaluated on two challenging large-scale datasets captured by drones, namely, VisDrone2019 [47] and UAVDT [48]. The VisDrone2019 dataset was created by the Machine Learning and Data Mining Laboratory of Tianjin University and is designed for tracking and detection in UAV views.…”

Section: Methodsmentioning

confidence: 99%

Global-Local and Occlusion Awareness Network for Object Tracking in UAVs

Shi,

Zhang,

Pan

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Multi-object tracking in unmanned aerial vehicle (UAV) scenes is a crucial task with numerous applications across various domains. The goal of this task is to track multiple objects such as people and vehicles over time as they move through the scene, often captured by cameras mounted on UAV. However, tracking objects in UAV scenes can be challenging due to several factors, including the scale variance of objects as they move through the scene and the frequent occlusions caused by complex scenes. To address these issues, we propose a Global-Local and Occlusion Awareness (GLOA) tracking network for unmanned aerial vehicles. It comprises two main components: global-local awareness detector (GLA-D) and the occlusion awareness data association (OADA). The GLA-D uses our specially designed global-local awareness block to extract scale variance feature information from the input frames. It then outputs more discriminative identity information by adding identity embedding branches to the prediction head. The GLA-D is designed to better handle scale variance issues and improve object tracking accuracy. The OADA method used different metrics for high and low scoring detection frames was to alleviate occlusion problems in tracking scenarios. By combining these two components, the GLOA provides a more robust and effective solution for multi-object tracking in UAV scenes. Experiments on two public datasets may indicate the effectiveness of the proposed method.

show abstract

“…We first review 11 widely used datasets for MOT, including KITTI [177], [211], [212], MOT15 [213], DukeMTMCT [215] 2018 -153.6K Pose VisDrone [223] 2018 -1.8M 2D box BDD100K [219] 2018 160K 4M 2D box/Mask MOTS [37] 2019 228 26K Mask KITTI MOTS [37] 2019 --Mask CityFlow [20] 2019 666 230K 2D box MOT20 [144] 2020 3,833 2.1M 2D box Waymo [218] 2020 -12.6M 2D box/3D box nuScenes [217] 2020 -1.4M 3D box [117], MOT16-17 [143], PathTrack [124], UA-DETRAC [214], PoseTrack [215], [216], MOTS [37], CityFlow [20], KITTI MOTS [37], MOT20 [32], [144], nuScenes [217], Waymo [218], BDD100K [219], [220], and VisDrone [221], [222], [223], [224]. These datasets mainly focus on the person and vehicle tracking.…”

Section: Datasetsmentioning

confidence: 99%

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

Wang¹,

Song²,

Hwang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has gained significantly increased interest in the computer vision community. Embedding methods play an essential role in object location estimation and temporal identity association in MOT. Unlike other computer vision tasks, such as image classification, object detection, re-identification, and segmentation, embedding methods in MOT have large variations, and they have never been systematically analyzed and summarized. In this survey, we first conduct a comprehensive overview with in-depth analysis for embedding methods in MOT from seven different perspectives, including patch-level embedding, single-frame embedding, cross-frame joint embedding, correlation embedding, sequential embedding, tracklet embedding, and cross-track relational embedding. We further summarize the existing widely used MOT datasets and analyze the advantages of existing state-of-the-art methods according to their embedding strategies. Finally, some critical yet under-investigated areas and future research directions are discussed.

show abstract

VisDrone-MOT2019: The Vision Meets Drone Multiple Object Tracking Challenge Results

Cited by 24 publications

References 41 publications

Multiple Object Tracking with Motion and Appearance Cues

Multiple Object Tracking with Motion and Appearance Cues

Global-Local and Occlusion Awareness Network for Object Tracking in UAVs

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

Contact Info

Product

Resources

About