Fujitsu Leverages Deep Learning to Achieve World's Most Accurate Recognition of Complex Actions and Behaviors Based on Skeleton Data
TOKYO, Jan 13, 2021 - (JCN Newswire) - Fujitsu Laboratories Ltd. has announced the development of a technology that utilizes deep learning to recognize the positions and connections of adjacent joints in complex movements or behavior in which multiple joints move in tandem. This makes it possible to achieve greater accuracy in recognizing, for instance, when a person performs a task like removing objects from a box. This technology successfully achieved the world's highest accuracy(1) against the world standard benchmark(2) in the field of behavior recognition, with significant gains over the results achieved using conventional technologies, which don't make use of information on neighboring joints.
|Fig. 1 Outline of the newly developed technology compared with conventional technologies|
|Fig. 2 Improvement of accuracy with new technology|
By leveraging this technology to perform checks of manufacturing procedures or unsafe behavior in public spaces, Fujitsu aims to contribute to significant improvements in public safety and in the work place, helping to deliver on the promise of a safer and more secure society for all.
Fujitsu will present the details of this technology at the 25th International Conference on Pattern Recognition (ICPR 2020), which is being held online from January 10th, 2021 (Sunday) to January 15th, 2021 (Friday).
In recent years, advances in AI technology have made it possible to recognize human behavior from video images using deep learning. This technology offers a variety of promising applications in a wide range of real-world scenarios, for example, in performing checks of manufacturing procedures in factories or detecting unsafe behavior in public spaces. In general, human behavior recognition utilizing AI relies on temporal changes in the position of each of the skeletal joints, including in the hands, elbows, and shoulders, as identifying features, which are then linked to simple movement patterns such as standing or sitting.
With time series behavior-recognition technology developed by Fujitsu Labs, Fujitsu has successfully realized highly-accurate image recognition using a deep learning model that can operate with high-accuracy even for complex behaviors in which multiple joints change in conjunction with each other, such as removing objects from a box during unpacking.
About the Newly Developed Technology
Complex movements like unpacking involve hand, elbow, and shoulder joints moving in tandem with the arm bending and stretching. Fujitsu has developed a new AI model for a graph convolutional neural networks(3) that performs convolution operation of the graph structure by adopting a graph consisting of edges connecting adjacent joints based on the structure of the human body with the joint position as a node (Vertex). By training this model in advance using the time series data of joints, the connection strength (Weight) with neighboring joints can be optimized, and effective connection relationships for behavior recognition can be acquired. With conventional technologies, it was necessary to accurately grasp the individual characteristics of each joint. With an AI model that has already been trained, the combined features of the adjacent joints that are linked can be extracted, making it possible to achieve highly-accurate recognition for complex movements.
This technology was evaluated against the world standard benchmark in the field of behavior recognition using skeleton data, and in the case of simple behaviors such as standing and sitting in the open data set, the accuracy rate was maintained at the same level as that of conventional technology(4) that does not use information on neighboring joints. In the case of complex behaviors like a person unpacking a box or throwing an object, however, the accuracy rate improved greatly, to achieve an overall improvement of more than 7% over the conventional alternative to reach the world's highest recognition accuracy.
By adding the newly developed AI model for recognizing complex behaviors obtained with this technology to the 100 basic behavior already accommodated by Fujitsu's behavioral analysis technology "Actlyzer,"(5), it will become possible rapidly deploy new, highly-accurate recognition models. Fujitsu ultimately aims to leverage this new capability to roll out the system in fiscal year 2021, and contribute to the resolution of real-world issues to deliver a safer and more secure society.
(1) World's highest accuracy: As of January 13th, 2021. In the Kinetics-Skeleton category.
(2) World standard benchmark: Kinetics-Skeleton dataset benchmarks.
(3) graph convolutional neural networks: Deep neural network for convolutional operation on graph structure.
(4) Same level as that of conventional technology
Using the Kinetics-Skeleton dataset released by Chinese University of Hong Kong, an evaluation was made with the technology released by the same university in 2018. The correct answer rate is the rate at which the predicted result matches the correct answer.
(5) Behavioral analysis technology "Actlyzer"
Deep learning technology that can recognize a variety of subtle and complex human movements without relying on large amounts of training data. (Press Release: 2019/11/25)
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 130,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.9 trillion yen (US$35 billion) for the fiscal year ended March 31, 2020. For more information, please see www.fujitsu.com.
About Fujitsu Laboratories
Founded in 1968 as a wholly owned subsidiary of Fujitsu Limited, Fujitsu Laboratories Ltd. is one of the premier research centers in the world. With a global network of laboratories in Japan, China, the United States and Europe, the organization conducts a wide range of basic and applied research in the areas of Next-generation Services, Computer Servers, Networks, Electronic Devices and Advanced Materials. For more information, please see: http://www.fujitsu.com/jp/group/labs/en/.
Source: Fujitsu Ltd
Sectors: Cloud & Enterprise
Copyright ©2021 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.
More Latest Release >>
Eisai to Present Latest Data on Pipeline Assets in the Area of Alzheimer's Disease and Dementia at the 15th International Conference on Alzheimer's and Parkinson's Disease
Mar 05, 2021 17:51 JST
MHI Group Presents "Best Innovation 2020" Awards for Activities that Contribute to Reducing Environmental Loads
Mar 05, 2021 09:30 JST
Billboard Hot 100 #1 Hit of the Year Band Member Partners with UREEQA
Mar 04, 2021 19:50 JST
Honda to Begin Sales of Legend with New Honda SENSING Elite
Mar 04, 2021 16:29 JST
Eisai to Support Construction of Screening Framework for the Novel Coronavirus Infection in Kenya
Mar 04, 2021 09:12 JST
Chiseikan Dojo in Kyoto Grand Opening Event: "When in danger, how can you best protect yourself?"
Mar 04, 2021 07:00 JST
Hitachi Developed the Hitachi Electronic Signature Service, to Eliminate Personal Seals with High Authenticity of Information by Blockchain Technology
Mar 03, 2021 11:48 JST
DENSO, KDDI Research 5G's use in Automated Driving to Achieve Safe and Secure Mobility
Mar 03, 2021 11:16 JST
Toyota Plans to Issue 'Woven Planet Bonds'
Mar 02, 2021 15:34 JST
Lockheed Martin and NEC Put AI to Work on Programs like NASA's Artemis Mission
Mar 02, 2021 14:03 JST
New Drug Approval for in-House Developed Anti-Insomnia Drug Dayvigo (Lemborexant) in Hong Kong
Mar 02, 2021 09:06 JST
Mitsubishi Power Commences Development of World's First Ammonia-fired 40MW Class Gas Turbine System
Mar 01, 2021 18:46 JST
MHI Machine Tool Develops Gear Shaping Machine for High-Precision Small-Module Gears Used in Robots
Mar 01, 2021 18:36 JST
Flying Finn Rovanpera Claims the Championship Lead in the Toyota Yaris WRC
Mar 01, 2021 10:46 JST
BYD to Help Kyoto Reach Japan's 2050 Carbon Neutral Goal
Feb 26, 2021 11:20 JST
Fujitsu and University of Toronto Researchers Develop Quantum-Inspired Technology to Optimize Radiation Treatment Plans for Brain Tumors and Other Diseases
Feb 26, 2021 10:59 JST
DENSO and Yamato Transport Develop D-mobico, Compact Mobile Refrigerator
Feb 25, 2021 19:28 JST
Mazda Production and Sales Results for January 2021
Feb 25, 2021 17:33 JST
Honda Reports Production, Sales and Export Results in January, 2021
Feb 25, 2021 15:27 JST
Toyota's Global Sales and Production Up Year-on-Year in January for Fifth Consecutive Month
Feb 25, 2021 15:12 JST