Human Action Recognition of Autonomous Mobile Robot Using Edge-AI

doi:10.1109/JSEN.2022.3225158

機構典藏 > College of Engineering > Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering > Journal Article > Item 987654321/123247

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/123247

Title:	Human Action Recognition of Autonomous Mobile Robot Using Edge-AI
Authors:	Wang, Shih-Ting;Li, I-Hsum;Wang, Wei-Yen
Keywords:	Autonomous mobile robot (AMR);bidirectional long-short-term-memory (BiLSTM);edge artificial intelligence (Edge AI);human action recognition (HAR);ROS
Date:	2023-01-15
Issue Date:	2023-04-28 17:26:52 (UTC+8)
Publisher:	IEEE
Abstract:	The development of autonomous mobile robots (AMRs) has brought with its requirements for intelligence and safety. Human action recognition (HAR) within AMR has become increasingly important because it provides interactive cognition between human and AMR. This study presents a full architecture for edge-artificial intelligence HAR (Edge-AI HAR) to allow AMR to detect human actions in real time. The architecture consists of three parts: a human detection and tracking network, a key frame extraction function, and a HAR network. The HAR network is a cascade of a DenseNet121 and a double-layer bidirectional long-short-term-memory (DLBiLSTM), in which the DenseNet121 is a pretrained model to extract spatial features from action key frames and the DLBiLSTM provides a deep two-directional LSTM inference to classify complicated time-series human actions. Edge-AI HAR undergoes two optimizations—ROS distributed computation and TensorRT structure optimization—to give a small model structure and high computational efficiency. Edge-AI HAR is demonstrated in two experiments using an AMR and is demonstrated to give an average precision of 97.58% for single action recognition and around 86% for continuous action recognition.
Relation:	IEEE Sensors Journal 23(2), p.1671-1682
DOI:	10.1109/JSEN.2022.3225158
Appears in Collections:	[Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	189	View/Open

Loading...