DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection

By Haibao Yu, Yizhen Luo, Mao Shu, Yiyi Huo, Zebang Yang, Yifeng Shi, Zhenglong Guo, Hanyu Li, Xing Hu, Jirui Yuan and 1 more. Computer Vision and Pattern Recognition, 2022

618 citations recorded by the source corpus.

Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities. It has been widely agreed that vehicle-infrastructure cooperation is required to achieve Level 5 autonomy. However, there is still NO dataset from real scenarios available for computer vision researchers to work on vehicle-infrastructure cooperation-related problems. To accelerate computer vision research and innovation for Vehicle-Infrastructure Cooperative Autonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the first large-scale, multi-modality, multi-view dataset from real scenarios for VICAD. DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all frames are captured from real scenes with 3D annotations. The Vehicle-Infrastructure Cooperative 3D Object Detection problem (VIC3D) is introduced, formulating the problem of collaboratively locating and identifying 3D objects using sensory inputs from both vehicle and infrastructure. In addition to solving traditional 3D object detection problems, the solution of VIC3D needs to consider the temporal asynchrony problem between vehicle and infrastructure sensors and the data transmission cost between them. Furthermore, we propose Time Compensation Late Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmark based on DAIR-V2X. Find data, code, and more up-to-date information at https://thudair.baai.ac.cn/index and https://github.com/AIR-Thu/dair-V2x.

Subfields: Aerospace Engineering, Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f3f2e2853029ecbece2d1d27ec45305a36a6b509

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. Bolei Zhou
2. Hao Xiang
3. Jiaqi Ma
4. Xin Xia
5. Runsheng Xu

In Automotive Engineering

1. Bolei Zhou
2. Hao Xiang
3. Jiaqi Ma
4. Xin Xia
5. Zhengzhong Tu
6. Runsheng Xu

In Computer Vision and Pattern Recognition

1. Zhengzhong Tu
2. Runsheng Xu
3. Hao Xiang
4. Jiaqi Ma
5. Xin Xia
6. Siheng Chen
7. Xiaoyu Dong
8. Bolei Zhou

Citations in the corpus

• Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (2022, methodology): “We complement several intermediate fusion-based baselines on DAIR-V2X to comprehensively validate our method on real data.”
• V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception (2023, methodology): “Similar to DAIR-V2X [54], we categorize different vehicle types as the same class and focus only on vehicle detection.”