CVPR 2023 BDD100K Challenges
We are hosting multi-object tracking (MOT) and segmentation (MOTS) challenges based on BDD100K, the largest open driving video dataset as part of the CVPR 2023 Workshop on Autonomous Driving (WAD).
Read more2023-03: | We released our CVPR 2023 challenges! |
2022-07: | We released our ECCV 2022 challenges! |
2022-03: | We released our CVPR 2022 challenges! |
2021-12: | We released the pose estimation annotations and models! |
2021-10: | We released our model zoo and leaderboards! |
We are hosting multi-object tracking (MOT) and segmentation (MOTS) challenges based on BDD100K, the largest open driving video dataset as part of the CVPR 2023 Workshop on Autonomous Driving (WAD).
Read moreWe are hosting multi-object tracking (MOT) and segmentation (MOTS) challenges based on BDD100K, the largest open driving video dataset as part of the ECCV 2022 Self-supervised Learning for Next-Generation Industry-level Autonomous Driving (SSLAD) Workshop.
Read moreWe are hosting multi-object tracking (MOT) and segmentation (MOTS) challenges based on BDD100K, the largest open driving video dataset as part of the CVPR 2022 Workshop on Autonomous Driving (WAD).
Read more100K driving videos collected from more than 50K rides. Each video is 40-second long and 30fps. More than 100 million frames in total.
Diverse scene types including city streets, residential areas, and highways, and diverse weather conditions at different times of the day.
Lane detection, object detection, semantic segmentation, instance segmentation, panoptic segmentation, multi-object tracking, segmentation tracking and more.
70,000/10,000/20,000 images for train/val/test, 1.8M objects.
7,000/1,000/2,000 images for train/val/test, 120K masks.
1,400/200/400 videos for train/val/test, 160K instances, 4M objects.
154/32/37 videos for train/val/test, 25K instances, 480K masks.
7,000/1,000/2,000 images for train/val/test, 40 object classes.
70,000/10,000/20,000 images for train/val/test, 8 main categories.
70,000/10,000/20,000 images for train/val/test, 8 main categories.
6 weather conditions, 6 scene types, 3 distinct times of the day
GPS/IMU recordings with visual input and the driving trajectories.
Diverse weather, road and daytime conditions.
We provide documents and tools for inspection, preparation, and evaluation of the BDD100K dataset.
You can simply log in and download the data in your browser after agreeing to BDD100K license.
We provides scripts to parse and visualize the labels, and a tool to display the trajectories.
We use a consistent data annotation format across all different tasks. We choose the Scalabel [link] format for this.
We provide evaluation scripts, online testing servers and challenges to verify your algorithm.
BDD100K is compatible with the labels generated by Scalabel. The labels are released in Scalabel Format.