Detection and Tracking Meet Drones Challenge

By Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Heng Fan, Qinghua Hu, Haibin Ling. 2020

1,156 citations recorded by the source corpus.

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. We first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

1. Junwei Han
2. Gong Cheng
3. Qinghua Hu
4. Pengfei Zhu
5. Ke Yan
6. G. Wang
7. Yiming Sun
8. Bing Cao

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Xiwen Yao
4. G. Wang
5. Tong Zhang
6. Wei Zhang
7. Zhuang Yin
8. Xuerui Mao

Citations in the corpus

• 3D Instance Segmentation of MVS Buildings (2021, neutral): “Though there are also many drone datasets in public, such as VisDrone [63] and dataset for object detection in aerial images”
• Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, methodology): “The images in 173 UAVDT [31] and VisDrone [1] were all collected by drones, 174 and can support object detection in traffic-related applica175 tions.”
• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “Enlightened by the previous works [7], [158], [159], we assign ignore label to the two datasets when: 1) the instances belonging to the preset categories but with an area greater than 2000; 2) the objects that are excessively small and heavily occluded thus cannot be distinguished.”
• UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios (2023, methodology): “The VisDrone2019 dataset [46] is one of the mainstream UAV aerial photography The VisDrone2019 dataset [46] is one of the mainstream UAV aerial photography datasets team and variety the ), uses the and detection representative”
• EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, background): “For other tasks such as VQA, RSVG, and HBB detection, the two-step training strategy brings EarthGPT an increase of 3.82% (OA), 4.06% (mIoU), and 3.74% (AP@50) on RSVQA-HR, DIOR-RSVG, and MAR20 datasets, respectively.”