VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results

Wen, Longyin; Zhu, Pengfei; Du, Dawei; Bian, Xiao; Ling, Haibin; Hu, Qinghua; Liu, Chenfeng; Cheng, Hao; Liu, Xiaoyu; Ma, Wenya; Nie, Qinqin; Wu, Haotian; Wang, Lianjie; Perera, Asanka G.; Zhang, Baochang; Heo, Byeongho; Li, Dongdong; Michail, Emmanouil; Chen, Hanlin; Líu, Hao; Li, Haojie; Kompatsiaris, Ioannis; Cheng, Jian; Fan, Jianchao; Zhang, Jie; Choi, Jin Young; Li, Jing; Yang, Jinyu; Choi, Jongwon; Zhao, Jiewen; Han, Jungong; Zhang, Kaihua; Duan, Kailiang; Song, Ke; Avgerinakis, Konstantinos; Lee, Kyuewang; Ding, Lu; Lauer, Martin; Giannakeris, Panagiotis; Zhang, Peizhen; Wang, Qiang; Xu, Qianqian; Huang, Qingming; Liu, Qingshan; Laganière, Robert; Zhang, Ruixin; Yun, Sangdoo; Zhu, Shuang; Wu, Sihang; Vrochidis, Stefanos; Tian, Wei; Zhang, Wei; Chen, Weidong; Hu, Weiming; Wang, Wenhao; Zhang, Wenhua; Ding, Wenrui; He, Xiaohao; Li, Xiaotong; Zhang, Xin; Luo, Xiaobing; Hu, Xuedong; Yang, Meng; Kuai, Yangliu; Zhao, Yanyun; Li, Yaxuan; Yang, Yifan; Zhang, Yifan; Wang, Yong; Qi, Yuankai; Deng, Zhipeng; He, Zhiqun

doi:10.1007/978-3-030-11021-5_28

Cited by 33 publications

(37 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we firstly evaluate the tracking performance of AutoTrack with current state-of-the-art trackers on four difficult UAV benchmarks [46,47,48,49]. Then, the proposed localization system is evaluated on Quanser * platform in the indoor practical scenarios.…”

Section: Methodsmentioning

confidence: 99%

AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization

Ding

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

343

195

View full text Add to dashboard Cite

Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of correlation filters. However, predefined parameters introduce much effort in tuning them and they still fail to adapt to new situations that the designer did not think of. In this work, a novel approach is proposed to online automatically and adaptively learn spatio-temporal regularization term. Spatially local response map variation is introduced as spatial regularization to make DCF focus on the learning of trust-worthy parts of the object, and global response map variation determines the updating rate of the filter. Extensive experiments on four UAV benchmarks have proven the superiority of our method compared to the state-of-the-art CPU-and GPU-based trackers, with a speed of ∼60 frames per second running on a single CPU.Our tracker is additionally proposed to be applied in UAV localization. Considerable tests in the indoor practical scenarios have proven the effectiveness and versatility of our localization method. The code is available at https: //github.com/vision4robotics/AutoTrack.

show abstract

Section: Methodsmentioning

confidence: 99%

AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization

Ding

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

343

195

View full text Add to dashboard Cite

show abstract

“…In this section, the proposed trackers with different components, summarized in Table 1, are exhaustively evaluated on four challenging UAV benchmarks, namely, UAV123@10fps [50], DTB70 [35], UAVDT [20] and Vistrone2018 [72]. UAV123@10fps is designed to investigate the impact of camera capture speed on tracking performance and constructed by down sampling the UAV123 benchmark [50] to 10 FPS from 30FPS.…”

Section: Methodsmentioning

confidence: 99%

“…• We demonstrate the proposed methods on four UAV benchmarks, namely, UAV123@10fps [50], DTB70 [35], UAVDT [20] and Vistrone2018 (VisDrone2018test-dev) [72]. Experimental results show that the proposed approaches achieves state-of-the-art performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking

Li¹,

Liu²,

Zhao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and public security. Recently, discriminative correlation filters (DCF)-based trackers have stood out in UAV tracking community for their high efficiency and appealing robustness on a single CPU. However, due to limited onboard computation resources and other challenges the efficiency and accuracy of existing DCF-based approaches is still not satisfying. In this paper, we explore using segmentation by the GrabCut to improve the wildly adopted discriminative scale estimation in DCF-based trackers, which, as a mater of fact, greatly impacts the precision and accuracy of the trackers since accumulated scale error degrades the appearance model as online updating goes on. Meanwhile, inspired by residue representation, we exploit the residue nature inherent to videos and propose residue-aware correlation filters that show better convergence properties in filter learning. Extensive experiments are conducted on four UAV benchmarks, namely, UAV123@10fps, DTB70, UAVDT and Vistrone2018 (VisDrone2018-test-dev). The results show that our method achieves state-of-the-art performance.

show abstract

“…However, for complex maneuvers, it is always hard to model the optimization problem, which has a great impact on the calculation efficiency and trajectory quality. In visual tracking [25,26], maneuvering is also required, vision-and-language navigation [27][28][29][30] provides another novel perspective. This method combines vision, language, and action which can turn relatively general natural-language instructions into robot agent actions.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid-Driven Optimization Framework for Fixed-Wing UAV Maneuvering Flight Planning

et al. 2021

View full text Add to dashboard Cite

Performing autonomous maneuvering flight planning and optimization remains a challenge for unmanned aerial vehicles (UAVs), especially for fixed-wing UAVs due to its high maneuverability and model complexity. A novel hybrid-driven fixed-wing UAV maneuver optimization framework, inspired by apprenticeship learning and nonlinear programing approaches, is proposed in this paper. The work consists of two main aspects: (1) Identifying the model parameters for a certain fixed-wing UAV based on the demonstrated flight data performed by human pilot. Then, the features of the maneuvers can be described by the positional/attitude/compound key-frames. Eventually, each of the maneuvers can be decomposed into several motion primitives. (2) Formulating the maneuver planning issue into a minimum-time optimization problem, a novel nonlinear programming algorithm was developed, which was unnecessary to determine the exact time for the UAV to pass by the key-frames. The simulation results illustrate the effectiveness of the proposed framework in several scenarios, as both the preservation of geometric features and the minimization of maneuver times were ensured.

show abstract

VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results

Cited by 33 publications

References 53 publications

AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization

AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization

Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking

A Hybrid-Driven Optimization Framework for Fixed-Wing UAV Maneuvering Flight Planning

Contact Info

Product

Resources

About