웨어러블 센서를 활용한 경량 인공신경망 기반 손동작 인식기술
A Light-weight ANN-based Hand Motion Recognition Using a Wearable Sensor
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Motion recognition is very useful for implementing an intuitive HMI (Human-Machine Interface). In particular, hands are the body parts that can move most precisely with relatively small portion of energy. Thus hand motion has been used as an efficient communication interface with other persons or machines. In this paper, we design and implement a light-weight ANN (Artificial Neural Network)-based hand motion recognition using a state-of-the-art flex sensor. The proposed design consists of data collection from a wearable flex sensor, preprocessing filters, and a light-weight NN (Neural Network) classifier. For verifying the performance and functionality of the proposed design, we implement it on a low-end embedded device. Finally, our experiments and prototype implementation demonstrate that the accuracy of the proposed hand motion recognition achieves up to 98.7%.
Abstract
Motion recognition is very useful for implementing an intuitive HMI (Human-Machine Interface). In particular, hands are the body parts that can move most precisely with relatively small portion of energy. Thus hand motion has been used as an efficient communication interface with other persons or machines. In this paper, we design and implement a light-weight ANN (Artificial Neural Network)-based hand motion recognition using a state-of-the-art flex sensor. The proposed design consists of data collection from a wearable flex sensor, preprocessing filters, and a light-weight NN (Neural Network) classifier. For verifying the performance and functionality of the proposed design, we implement it on a low-end embedded device. Finally, our experiments and prototype implementation demonstrate that the accuracy of the proposed hand motion recognition achieves up to 98.7%.
참고문헌 (17)
- K. Oka, "Real-time Fingertip Tracking and Gesture Recognition", IEEE Computer Graphics and Applications, 22(6), pp.64~71 (2002)
- Z. Ren, "Robust Hand Gesture Recognition with Kinect Sensor", Proceedings of ACM international conference on Multimedia (MM '11), pp.759~760 (2011)
- 전세윤, "산업용 로봇 원격제어를 위한 CNN기반 손 제스처 인식 방법", 대한임베디드공학회논문지, 16(2), pp.65~72 (2021), 대한임베디드공학회[DOI]
- L. M. Danga, "Sensor-based and Vision-based Human Activity Recognition: A Comprehensive Survey", Pattern Recognition, 108 (2020)
- "Bendlabs, 2-axis Soft Flex Sensor"[URL]
- B. S. Lin, "Data Glove System Embedded With Inertial Measurement Units for Hand Function Evaluation in Stroke Patients", IEEE Transaction on Neural Systems and Rehabilitation Engineering, 25(11), pp.2204~2213 (2017)
- C. E. A. Quiapo, "Development of a Sign Language Translator Using Simplified Tilt, Flex and Contact Sensor Modules", IEEE Region 10Conference (TENCON) (2016)
- H. J. Kim, "Design of Wearable Orthopedic Devices for Treating Forward Head Postures using Pneumatic Artificial Muscles and Flex Sensors", URAI 2017 (2017)
- G. Bhat, "Online Human Activity Recognition using Low-Power Wearable Devices", IEEE International Conference on Computer-Aided Design (ICCAD) (2018)
- L. Majeau, "Dataglove for Consumer Applications", 2011 7th International Workshop on Fibre and Optical Passive Components (2011)
- M. Kim, "IMU Sensor-Based Hand Gesture Recognition for Human-Machine Interfaces", Sensors, 19(18) (2019)
- L. Chen, "Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals", Sensors, 20(3) (2020)
- 정우순, "손가락 움직임 인식을 위한 웨어러블 디바이스 설계 및 ML 기법별 성능 분석", 한국산업정보학회논문지, 25(2), pp.129~136 (2020), 한국산업정보학회[DOI]
- A. K. Panda, "Hand Gesture Recognition using Flex Sensor and Machine Learning Algorithms", EMBS Conference on Biomedical Engineering and Science (2020)
- W. C. Chuang, "Continuous Finger Gesture Recognition Based on Flex Sensors", Sensors, 19(18) (2019)
- J. Chan, "Designing a Sensor Glove Using Deep Learning", International Conference on Intelligent User Interface (2021)
- "Datasheet of CC2652R"[URL]