DHP19 was developed by the Sensors Group of the Inst. of Neuroinformatics, Univ. of Zurich and ETH Zurich.
Information about other datasets and tools are on the Sensors Group webpage.
For questions related to DHP19, contact Enrico Calabrese (enrico01.calabrese@gmail.com) (formerly Sensors Group) and Tobi Delbruck (tobi@ini.uzh.ch) , Sensors Group, Institute of Neuroinformatics, University and ETH Zurich, Switzerland.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
DHP19 is the first human pose dataset with data collected from DVS event cameras.
It has recordings from 4 synchronized 346x260 pixel DVS cameras and marker positions in 3D space from Vicon motion capture system. The files have event streams and 3D positions recorded from 17 subjects each performing 33 movements.
It also includes a reference Convolutional Network implementation for instantaneous human pose estimation, trained on DVS constant-count frames from the two frontal DVS cameras.
Examples of DVS recordings and Vicon 3D labels.
See this video for introduction to the datatset
If you use DHP19, please cite the following paper:
Calabrese, E.*, Taverni, G.*, Easthope, C., Skriabine, S., Corradi, F., Longinotti, L., Eng, K., and Delbruck, T. DHP19: Dynamic Vision Sensor 3D Human Pose Dataset. CVPR Workshop on Event-based Vision and Smart Cameras, Long Beach, CA, USA, 2019. (or see this PDF version)
DHP19 was collected with DAVIS 346 cameras. The seminal citations for this sensor are:
Brandli, C., Berner, R., Yang, M., Liu, S.-C., and Delbruck, T. (2014). A 240x180 130 dB 3 us Latency Global Shutter Spatiotemporal Vision Sensor. IEEE Journal of Solid-State Circuits 49, 2333–2341. doi:10.1109/JSSC.2014.2342715.
Lichtsteiner, P., Posch, C., and Delbruck, T. (2008). A 128x128 120dB 15us Latency Asynchronous Temporal Contrast Vision Sensor. IEEE Journal of Solid-State Circuits 43, 566–576. doi:10.1109/JSSC.2007.914337.