- While the term “object tracking” can be sometimes ambiguous, in the VisDrone2020 Single-Object Tracking Challenge (Task 2), we focus on generic single object tracking, also known as model-free tracking. In particular, for an input video sequence and the initial bounding box of the target object in the first frame, the challenge requires a participating algorithm to locate the target bounding boxes in the subsequent video frames. The objects to be tracked are of various types including pedestrians, cars, buses, and animals.
- The challenge will provide 192 challenging sequences, including 86 video sequences for training (69,941 frames in total), 11 video sequences for validation (7,046 frames in total) and 95 sequences for testing (144,933 frames in total). We manually annotate the bounding boxes of different objects in each video frame. Annotations on the training and validation sets are publicly available.
- [05.15]: Training, validation and testing data, and evaluation software released
- [06.30]: Result submission deadline
- [07.10]: Challenge results released
- [08.28]: Winner presents at ECCV 2020 Workshop
- The detailed information regarding how submissions will be scored is listed in the single-object tracking evaluation page. To limit overfitting while providing researchers more flexibility to test their algorithms, we have divided the test set into two splits, including test-challenge and test-dev.
- Test-dev (35 video clips) is designed for debugging and validation experiments and allows for unlimited submission. The up-to-date results of the test-dev set are available to view on the leaderboard of object detection in video.
- Test-challenge (60 video clips) is used for workshop competition, and the results will be announced during the ECCV 2020 Vision Meets Drones: A Challenge workshop. We encourage the participants to use the provided training data, while also allow them to use additional training data. The use of external data must be indicated during submission.
- The train+val video clips and corresponding annotations as well as the video clips in the test-challenge set are available on the download page. Before participating, every user is required to create an account using an institutional email address. If you have any question in registration, please contact us. After registration, the users should submit the results in their accounts. The submitted results will be evaluated according to the rules described on the evaluation page. Please refer to the evaluation page for detailed explanation.
Tools and Instructions
We provide extensive API support for the VisDrone videos, annotation and evaluation code. Please visit our GitHub repository to download the VisDrone API. For addition questions, please find the answers here or contact us.