VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

TL;DR

This paper introduces a large-scale drone crowd counting dataset and organizes a challenge to evaluate algorithms, addressing the lack of data and advancing research in drone-based crowd analysis.

Contribution

It provides a new comprehensive dataset and benchmark for drone crowd counting, fostering development of algorithms tailored for drone-captured data.

Findings

14 algorithms evaluated on the dataset

Detailed analysis of algorithm performance

Benchmark results published for future research

Abstract

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.