LiDianze
  • Joined on Jul 22, 2022

Datasets

SODFormer
target detection computer vision 36

Models in 'SODFormer: Streaming Object Detection with Transformers Using Events and Frames'

Updated 1 year ago

PKU-DAVIS-SOD
target detection computer vision 229

The PKU-DAVIS-SOD dataset is a large-scale multimodal neuromorphic object detection dataset with some challenging scenarios (e.g., low-light and high-speed motion blur) included. This dataset is recorded using DAVIS346 whose resolution is of 346 * 260. Our PKU-DAVIS-SOD dataset contains 3 traffic scenarios by considering velocity distribution, light condition, category diversity and object scale, etc. We use the DAVIS346 to record 220 sequences including RGB frames and DVS events. In each sequence, we collect approximately 1 min as the raw data pool with 25 FPS of RGB frames. Manual annotations in the recordings are provided at a frequency of 25 Hz. As a result, this dataset has 276k labeled timestamps and 1080.1k labels in total. Compared to other similar datasets, it has an overwhelming advantage in aspect of scale.

Updated 1 year ago