지능형 휠체어 적용을 위한 기울기 히스토그램의 상관계수를 이용한 도로위의 이륜차 인식
Two Wheeler Recognition Using the Correlation Coefficient for Histogram of Oriented Gradients to Apply Intelligent Wheelchair
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This article describes a new recognition algorithm using correlation coefficient for intelligent wheelchair to avoid collision for elderly or disabled people. The correlation coefficient can be used to represent the relationship of two different areas. The algorithm has three steps: Firstly, we extract an edge vector using the Histogram of Oriented Gradients(HOG) which includes gradient information and unique magnitude for each cell. From this result, the correlation coefficients are calculated between one cell and others. Secondly, correlation coefficients are used as the weighting factors for normalizing the HOG cell. And finally, these features are used to classify or detect variable and complicated shapes of two wheelers using Adaboost algorithm. In this paper, we propose a new feature vectors which is calculated by weighted cell unit to classify with multiple view-based shapes: frontal, rear and side views(60o, 90o and mixed angle). Our experimental results show that two wheeler detection system based on a proposed approach leads to a higher detection accuracy than the method using traditional features in a similar detection time.
Abstract
This article describes a new recognition algorithm using correlation coefficient for intelligent wheelchair to avoid collision for elderly or disabled people. The correlation coefficient can be used to represent the relationship of two different areas. The algorithm has three steps: Firstly, we extract an edge vector using the Histogram of Oriented Gradients(HOG) which includes gradient information and unique magnitude for each cell. From this result, the correlation coefficients are calculated between one cell and others. Secondly, correlation coefficients are used as the weighting factors for normalizing the HOG cell. And finally, these features are used to classify or detect variable and complicated shapes of two wheelers using Adaboost algorithm. In this paper, we propose a new feature vectors which is calculated by weighted cell unit to classify with multiple view-based shapes: frontal, rear and side views(60o, 90o and mixed angle). Our experimental results show that two wheeler detection system based on a proposed approach leads to a higher detection accuracy than the method using traditional features in a similar detection time.
참고문헌 (11)
- D. P. Miller, "Design and testing of a lowcost robotic wheelchair prototype", Autonomous Robotics, 2, pp.77~88 (1995)
- R. C. Simpson, "Adaptive shared control of a smart wheelchair operated by voice control", Proc. IROS 97, pp.622~626 (1997)
- H. A. Yanco, "Preliminary investigation of a semi-autonomous robotic wheelchair directed through electrodes", Proc. Rehabilitation Engineering Society of North America 1997 Annual Conference, pp.414~416 (1997)
- T. Gomi, "Developing intelligent wheelchairs for the handicapped", Assistive Technology and Artificial Intelligence, Lecture Notes in AI, 1458, pp.150~178 (1998)
- Murakami. Y, "Intelligent wheelchair moving among people based on their observations", 2000 IEEE International Conference, pp.1466~1471 (2000)
- M. Enzweiler, "Monocular pedestrian detection: survey and experiments", IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(12), pp.2179~2195 (2009)
- 이영학, "곡률과 HOG에 의한 연속 방법에 기반한 아다부스트 알고리즘을 이용한 보행자 인식", 정보과학회논문지 : 컴퓨팅의 실제 및 레터, 16(6), pp.654~662 (2010), 한국정보과학회
- 人檢出のための real adaboost に基づくHOG特徵量の效率的な削減法, "松島千佳", 情報 處理學會硏究報告, 1~8 (2009)
- P. Viloa, "Detecting pedestrians using patterns of motion and appearance", The 9th ICCV, pp.153~161 (2003)
- J. B. Tilbury, "Receiver operating characteristic analysis for intelligent medical system-a new approach for finding confidence intervals", IEEE Transactions on Biomedical Engineering, 47(7), pp.952~963 (2000)