지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 대한전자공학회 JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE Journal of Semiconductor Technology and Science Vol.19 No.4
- 발행연도
- 2019.8
- 수록면
- 396 - 403 (8page)
- DOI
- 10.5573/JSTS.2019.19.4.396
이용수
초록· 키워드
오류제보하기
A low-power and real-time hidden Markov model (HMM) accelerator is proposed for gesture user interface on wearable smart devices. HMM algorithm is widely used for sequence recognition problems such as speech recognition and gesture recognition thanks to its best-in-class recognition accuracy. However, the HMM algorithm has high computational complexity and requires massive memory bandwidth in sequence matching process. Therefore, there have been studies on hardware acceleration of the HMM algorithm to resolve these issues, but they were focusing on the speech recognition and therefore did not accommodate the motion orientation function required for the gesture recognition problem. The motion orientation function computes the direction of hand movement in gesture sequence and thus involves compute intensive division and arctangent operations. In this paper, we propose an HMM accelerator with a light weight motion orientation module for realizing gesture recognition on wearable devices. Binary search method is exploited in the motion orientation module to avoid the division and arctangent operations associated with calculating orientations for reduced arithmetic complexity. In addition, gesture models are clustered in the gesture database to reduce external memory transactions. Moreover, logarithmic arithmetic is adopted in Viterbi decoder of the HMM algorithm for more reduction in its complexity. Thanks to these proposed schemes, this work achieves 25.6% power reduction compared with a vanilla hardware implementation of the gesture recognizing HMM.
목차
Abstract
Ⅰ. INTRODUCTION
Ⅱ. HMM ACCELERATOR
Ⅲ. IMPLEMENTATION RESULTS
Ⅳ. CONCLUSION
REFERENCES
참고문헌 (10)
참고문헌 신청
S. Park, S. Choi, J. Lee, M. Kim, J. Park, and H.-J. Yoo, “A 126.1mW Real-Time Natural UI/UX Processor with Embedded Deep-Learning Core for Low-Power Smart Glasses,” ISSCC Dig. Tech. Papers, pp. 254-256, 2016.
S. Gunter and H. Bunke, “HMM-based handwritten word recognition: On the optimization of the number of states, training iterations and Gaussian components,” Pattern Recognition, vol. 37, no. 10, pp. 2069?2079, Apr. 2004.
N. Farra, G. Raffa, L. Nachman, and H. Hajj, “Energy-Efficient Mobile Gesture Recognition with Computation Offloading,” Proc. Int. Conf. Energy Aware Comput., pp. 1-6, 2011.
S. A. Fahmy, P. Y. K. Cheung, and W. Luk, “Hardware Acceleration of Hidden Markov Model Decoding for Person Detection,” in Proc. Conf. Des., Autom. Test Eur. (DATE), vol. 3, pp. 8-13, 2005.
M. Price, J. Glass, and A. P. Chandrakasan, “A 6 mW, 5,000-Word Real-Time Speech Recognizer Using WFST Models,” IEEE J. Solid-State Circuits, vol. 50, no. 1, pp. 102-112, Jan. 2015.
S. Gunter and H. Bunke, “HMM-based handwritten word recognition: On the optimization of the number of states, training iterations and Gaussian components,” Pattern Recognition, vol. 37, no. 10, pp. 2069?2079, Apr. 2004.
N. Farra, G. Raffa, L. Nachman, and H. Hajj, “Energy-Efficient Mobile Gesture Recognition with Computation Offloading,” Proc. Int. Conf. Energy Aware Comput., pp. 1-6, 2011.
S. A. Fahmy, P. Y. K. Cheung, and W. Luk, “Hardware Acceleration of Hidden Markov Model Decoding for Person Detection,” in Proc. Conf. Des., Autom. Test Eur. (DATE), vol. 3, pp. 8-13, 2005.
M. Price, J. Glass, and A. P. Chandrakasan, “A 6 mW, 5,000-Word Real-Time Speech Recognizer Using WFST Models,” IEEE J. Solid-State Circuits, vol. 50, no. 1, pp. 102-112, Jan. 2015.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
개선된 HMM알고리즘을 이용한 제스쳐 인식
한국생산제조학회 학술발표대회 논문집
2015 .10
-
2단계 히든마코프 모델을 이용한 제스쳐의 성능향상 연구
제어로봇시스템학회 논문지
2015 .11
-
변형된 HMM 알고리즘을 이용한 제스처 인식
정보 및 제어 논문집
2019 .10
-
HMM을 이용한 연속적인 영상에서의 제스처 인식 방법
대한전자공학회 학술대회
2015 .06
-
Proposal of Camera Gesture Recognition System Using Motion Recognition Algorithm
전기전자학회논문지
2022 .03
-
Continuous gesture recognition by using gesture spotting
제어로봇시스템학회 국제학술대회 논문집
2016 .10
-
IMU와 EMG센서에 2-stage HMM을 사용한 제스쳐 인식
제어로봇시스템학회 국내학술대회 논문집
2015 .05
-
시 공간 정규화를 통한 딥 러닝 기반의 3D 제스처 인식
멀티미디어학회논문지
2018 .05
-
Hand based Gesture Recognition inside a car through IR-UWB Radar
대한전자공학회 학술대회
2017 .01
-
[조흡의 영화이야기] <최악의 하루>: 소통을 가능케 하는 몸짓
대한토목학회지
2017 .03
-
Hand Gesture Recognition Suitable for Wearable Devices using Flexible Epidermal Tactile Sensor Array
Journal of Electrical Engineering & Technology
2018 .07
-
Recognition of Natural Hand Gestures Using Bidirectional Long Short-Term Memory Model
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2018 .12
-
게임 어플리케이션을 위한 컨볼루션 신경망 기반의 실시간 제스처 인식 연구
멀티미디어학회논문지
2017 .05
-
Proposal of Image Detection Algorithm to Implement Hand Gestures
전기전자학회논문지
2018 .12
-
불완전 시계열 데이터를 위한 이산 HMM 학습 알고리듬
멀티미디어학회논문지
2016 .01
-
딥러닝 기반 실시간 손 제스처 인식
멀티미디어학회논문지
2019 .04
-
실내 모바일 로봇 조작을 위한 손 제스처 조작 방식 제안 및 구현
제어로봇시스템학회 논문지
2025 .01
-
Investigating Smart TV Gesture Interaction Based on Gesture Types and Styles
대한인간공학회지
2017 .04
-
컴퓨터 제어를 위한 딥러닝 기반의 Hand-gesture 인식 시스템
Proceedings of KIIT Conference
2022 .12
-
스마트 워치를 이용한 HMM 기반의 위치추적 경로 패턴인식 모델에 관한 연구
한국정보통신학회 종합학술대회 논문집
2019 .10
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2019-569-000961818