Paper Info
Title
Multipath Event-Based Network for Low-Power Human Action Recognition
Abstract
Event-based cameras are bio-inspired sensors capturing asynchronous per-pixel brightness changes (events), which have the advantages of high temporal resolution and low power consumption compared with traditional frame-based cameras. Despite recent progress in human action recognition on traditional cameras, few solutions on event cameras have been proposed due to its unconventional frameless output. To perform low-power human action recognition on event camera, we propose a multipath deep neural network for action recognition based on event camera outputs. Specifically, a fixed number of asynchronous events are accumulated to form frames for feature extraction. With events encoding dynamic information, we estimate human pose from event frames to encode static information to improve recognition accuracy. The complementary properties between dynamic event frames and static human poses are jointly explored and fused to predict action. Extensive experiments verify the effectiveness of the proposed model with a recognition accuracy of 85.91% on the DHP19 dataset.
Year
DOI
Venue
2020
10.1109/WF-IoT48130.2020.9221355
2020 IEEE 6th World Forum on Internet of Things (WF-IoT)
Keywords
DocType
ISBN
Event Camera,Action Recognition,Dynamic Vision Sensor,CNN,Low-Power Computing
Conference
978-1-7281-5503-6
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Xiao Wu1113.75
Junsong Yuan23703187.68