VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results

Chen, Guanlin; Yang, Yi; He, Zhijian; Wang, Lujia; Yuan, Yixuan; Zhang, Dingwen; Zhang, Jinglin; Zhu, Pengfei; Gool, Luc Van; Han, Junwei; Hoi, Steven C. H.; Hu, Qinghua; Liu, Ming; Sciarrone, Andrea; Sun, Chao; Garibotto, Chiara; Tran, Duong Nguyen-Ngoc; Lavagetto, Fabio; Haleem, Halar; Motorcu, Hakki; Ates, Hasan F.; Jeon, Hee-Kyung; Bisio, Igor; Jeon, Jae Wook; Li, Jiahao; Pham, Long Hoang; Jeon, Moongu; Feng, Qianyu; Li, Shengwen; Tran, Tai Huu-Phuong; Pan, Xiao; Song, Young-min; Yao, Yuehan; Du, Yunhao; Xu, Zhenyu; Luo, Zhipeng

doi:10.1109/iccvw54120.2021.00318

Cited by 22 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PASCAL VOC challenge (Everingham et al, 2005) and the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) (Russakovsky et al, 2015) are among the earliest image analysis challenges featuring deep learning methods albeit focusing on simple classification. Subsequent challenges advance the recognition task to object detection (Lin et al, 2014;Everingham et al, 2010), single and multi-object tracking (Dendorfer et al, 2020;Chen et al, 2021;Kristan et al, 2016), segmentation (Cordts et al, 2016;Voigtlaender et al, 2019), etc., spearheading the development of state-of-the-art models. Repeating some challenges over the years comes with either or both increasing the size of datasets and task difficulty.…”

Section: Benchmark Challenge: From Recognition To Detectionmentioning

confidence: 99%

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

Nwoye¹,

Tao²,

Sharma³

et al. 2023

Preprint

View full text Add to dashboard Cite

Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier efforts and the CholecTriplet challenge introduced in 2021 have put together techniques aimed at recognizing these triplets from surgical footage. Estimating also the spatial locations of the triplets would offer a more precise intraoperative context-aware decision support for computer-assisted intervention. This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection. It includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of instrument, verb, target triplet. The paper describes a baseline method and 10 new deep learning algorithms presented at the challenge to solve the task. It also provides thorough methodological comparisons of the methods, an in-depth analysis of the obtained results, their significance, and useful insights for future research directions and applications in surgery.

show abstract

Section: Benchmark Challenge: From Recognition To Detectionmentioning

confidence: 99%

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

Nwoye¹,

Tao²,

Sharma³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For MOT-a (no prior object detection results), AP-based evaluating metrics were employed [64], while concerning MOT-b, evaluating metrics from [65] were used (with prior detection results). For the performance evaluation of MOT algorithms in Visdrone-2019 and later [40], [66], authors used the metrics from [64], irrespective of the availability of prior detection outcomes. Regarding the evaluation of tracking tasks in traffic monitoring systems, MOTA and MOTP metrics have been primarily employed.…”

Section: ) For Tracking Taskmentioning

confidence: 99%

A Systematic Review of Drone Based Road Traffic Monitoring System

et al. 2022

Self Cite

View full text Add to dashboard Cite

Drone deployment has become crucial in a variety of applications, including solutions to traffic issues in metropolitan areas and highways. On the other hand, data collected via drones suffers from several problems, including a wide range of object scales, angle variations, truncation, and occlusion. To process and manipulate visual data from the drones, a variety of image processing algorithms have been employed, each with a distinct aim. Additionally, recent breakthroughs in the field of Artificial Intelligence, particularly deep learning, have attracted broad interest and are being applied to many domains in the framework of smart cities, including road traffic monitoring. The purpose of this study is to conduct a systematic review of drone-based traffic monitoring systems from a deep learning perspective. This work focuses on vehicle detection, tracking, and counting, since they are fundamental building blocks towards founding solutions for traffic congestion, flow rate and vehicle speed estimation. Additionally, drone-based datasets are examined, which face issues and problems caused by the diversity of features inherent of drone devices. The review analysis presented in this work summarizes the literature solutions provided and deployed so far and discusses future research trends in establishing a comprehensive traffic monitoring system in support of the development of smart cities INDEX TERMS deep learning, drone, smart city, traffic monitoring, uav.

show abstract

“…We used 40 video sequences in the dataset as a training set and 10 video sequences as a test set for experiments. The VisDrone MOT dataset [12] was collected by the Machine Learning and Data Mining Laboratory of Tianjin University. The dataset provides 96 video sequences, including training video sequences (56 in total, 24201 frames), validation video sequences (7 in total, 2819 frames), and test video sequences (33 in total, 12968 frames).…”

Section: The Detection Score Threshold Ablation Studymentioning

confidence: 99%

“…We combined the two into a new multi-object tracking algorithm, named STN-Track. We used STN-Track to conduct experiments on the UAVDT [11] and VisDrone [12] MOT datasets.…”

Section: Introductionmentioning

confidence: 99%

STN-Track: Multiobject Tracking of Unmanned Aerial Vehicles by Swin Transformer Neck and New Data Association Method

Feng

Cao

et al. 2022

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

View full text Add to dashboard Cite

The gradual development of remote sensing object tracking technology based on unmanned aerial vehicles (UAV) videos has become one of the main research directions in the field of visual tracking. However, due to characteristics of the UAV platform, typical visual tracking algorithms currently applied to natural scenes cannot be used directly. Small-scale objects in UAV remote sensing videos are difficult to detect and have the problem of tracking identity switching. In order to solve these problems, we designed the Swin transformer neck YOLOX (STN-YOLOX) object detection algorithm as the detection module, and the G-Byte data association method as the tracking module. We then combined the two into a new multi-object tracking algorithm named STN-Track. We used STN-Track to conduct experiments on the UAVDT and VisDrone MOT datasets. The experimental results show that compared with the current state-of-the-art (SOTA) methods, our STN-Track has improved detection and tracking accuracy of small-scale objects and greatly improved identification capabilities for object tracking. Compared with the SOTA ByteTrack algorithm, MOTA of STN-Track can be improved by up to 3.2%, APS can be improved by up to 4.4%, MT can be improved by up to 6.8%, and IDSW can be reduced by up to 28.0%.

show abstract

VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results

Cited by 22 publications

References 24 publications

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

A Systematic Review of Drone Based Road Traffic Monitoring System

STN-Track: Multiobject Tracking of Unmanned Aerial Vehicles by Swin Transformer Neck and New Data Association Method

Contact Info

Product

Resources

About