DHP19: Dynamic Vision Sensor 3D Human Pose Dataset
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1695-1704
Abstract
Human pose estimation has dramatically improved thanks to the continuous developments in deep learning. However, marker-free human pose estimation based on standard frame-based cameras is still slow and power hungry for real-time feedback interaction because of the huge number of operations necessary for large Convolutional Neural Network (CNN) inference. Event-based cameras such as the Dynamic Vision Sensor (DVS) quickly output sparse moving-edge information. Their sparse and rapid output is ideal for driving low-latency CNNs, thus potentially allowing real-time interaction for human pose estimators. Although the application of CNNs to standard frame-based cameras for human pose estimation is well established, their application to event-based cameras is still under study. This paper proposes a novel benchmark dataset of human body movements, the Dynamic Vision Sensor Human Pose dataset (DHP19). It consists of recordings from 4 synchronized 346x260 pixel DVS cameras, for a set of 33 movements with 17 subjects. DHP19 also includes a 3D pose estimation model that achieves an average 3D pose estimation error of about 8 cm, despite the sparse and reduced input data from the DVS.Keywords
This publication has 25 references indexed in Scilit:
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Steering a predator robot using a mixed frame/event-driven convolutional neural network2016
- Combined frame- and event-based detection and tracking2016
- Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras2015
- A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision SensorIEEE Journal of Solid-State Circuits, 2014
- 3D Pictorial Structures for Multiple Human Pose Estimation2014
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Multi-view Pictorial Structures for 3D Human Pose Estimation2013
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008