The VisDrone 2021 Challenge
The VisDrone 2021 Challenge will be held on the ICCV 2021 workshop “Vision Meets Drone: A Challenge” (or VisDrone 2021, for short) in October 2021, in SEC, Montreal, Canada, for object detection, tracking and counting in visual data taken from drones. We invite researchers to participate in the challenge and to evaluate and discuss their research at the workshop, as well as to submit papers describing research, experiments, or applications based on the VisDrone2021 dataset. The challenge mainly focuses on three tasks:
(1) Task 1: object detection challenge. The task aims to detect objects of predefined categories (e.g., cars and pedestrians) from videos taken from drones.
(2) Task 2: multi-object tracking challenge. The task aims to recover the trajectories of objects in each video frame.
(3) Task 3: crowd counting challenge. The task aims to counting vehicles and people in each video frame.
The scope of the workshop comprises all aspects of image and video analysis with respect to drone platform, including but not limited to the following topics: object detection and tracking, large scale learning, visual surveillance and tracking in crowded scenes, traffic flow analysis, motion trajectory analysis, human and vehicle indexing and retrieval in video sequences, and dataset proposals and bias analysis.
The Visual SLAM Challenge
This visual SLAM benchmark is based on the FusionPortable dataset, which has been collected by covering a variety of environments on The Hong Kong University of Science and Technology campus by exploiting multiple platforms for data collection. It provides a large range of difficult problems for SLAM.