복도 주행 로봇을 위한 단일 카메라 영상에서의사람 검출
Human Detection in the Images of a Single Camera for a Corridor Navigation Robot
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
In this paper, a robot vision technique is presented to detect obstacles, particularly approaching humans, in the images acquired by a mobile robot that autonomously navigates in a narrow building corridor. A single low-cost color camera is attached to the robot, and a trapezoidal area is set as a region of interest (ROI) in front of the robot in the camera image. The lower parts of a human such as feet and legs are first detected in the ROI from their appearances in real time as the distance between the robot and the human becomes smaller. Then, the human detection is confirmed by detecting his/her face within a small search region specified above the part detected in the trapezoidal ROI. To increase the credibility of detection, a final decision about human detection is made when a face is detected in two consecutive image frames. We tested the proposed method using images of various people in corridor scenes, and could get promising results. This method can be used for a vision-guided mobile robot to make a detour for avoiding collision with a human during its indoor navigation.
Abstract
In this paper, a robot vision technique is presented to detect obstacles, particularly approaching humans, in the images acquired by a mobile robot that autonomously navigates in a narrow building corridor. A single low-cost color camera is attached to the robot, and a trapezoidal area is set as a region of interest (ROI) in front of the robot in the camera image. The lower parts of a human such as feet and legs are first detected in the ROI from their appearances in real time as the distance between the robot and the human becomes smaller. Then, the human detection is confirmed by detecting his/her face within a small search region specified above the part detected in the trapezoidal ROI. To increase the credibility of detection, a final decision about human detection is made when a face is detected in two consecutive image frames. We tested the proposed method using images of various people in corridor scenes, and could get promising results. This method can be used for a vision-guided mobile robot to make a detour for avoiding collision with a human during its indoor navigation.
참고문헌 (26)
- W. P. Yu, "Robot navigation technology and its standardization trends", Electronics and Telecommunications Trends, 26(6), pp.108~119 (2011)
- I. Ulrich, "Appearance-based obstacle detection with monocular color vision", Proc. AAAI (2000)
- S. Kim, "Robot vision technology trends for intelligent mobile robots", Magazine of Korea Robotics Society, 9(1), pp.26~35 (2012)
- N. A. Ogale, "A survey of techniques for human detection from video" (2006), Survey, University of Maryland
- 최윤규, "지향각이 넓은 저가의 초음파센서를 이용한 이동로봇의 장애물 회피", 제어.로봇.시스템학회 논문지, 15(11), pp.1102~1107 (2009), 제어·로봇·시스템학회
- S. Kim, "Simple and complex obstacle detection using an overlapped ultrasonic sensor ring", Int. Conf. on Control, Automation and Systems, pp.2148~2152 (2012)
- A System for video surveillance and monitoring, "R. Collins", Carnegie Mellon University Robotics Institute, ~, pp.CMU-RI-TR-00-12 (2000)
- M. Heikkila, "A texture-based method for modeling the background and detecting moving objects", IEEE Trans. on Pattern Analysis and Machine Intelligence, 28, pp.657~662 (2006)
- C. Grana, "Detecting moving objects, ghosts, and shadows in video streams", IEEE Trans. on Pattern Analysis and Machine Intelligence, 25(10), pp.1337~1342 (2003)
- I. Haritaoglu, "W4 : Realtime surveillance of people and their activities", IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8), pp.809~830 (2000)
- Y. Do, "Counting people from image sequences", Proc. Int. Conf. on Imaging Science, Systems and Technology, pp.185~190 (2000)
- H. Fujiyoshi, "Real-time human motion analysis by image skeletonization", IEICE Transactions on Information and Systems, E87-D(1), pp.113~120 (2004)
- N. dalal, "Histograms of oriented gradients for human detection", IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1, pp.886~893 (2005)
- Q. Zhu, "Fast human detection using a cascade of histograms of oriented gradients", IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2, pp.1491~1498 (2006)
- Y. Cui, "Pedestrian detection using improved histogram of oriented gradients", VIE 2008 5th Int. Conf. on IET, pp.288~392 (2008)
- Y. Pang, "Robust CoHOG feature extraction in human-centered image", video management system, 2012, pp.42(2), 458~568
- P. Dollar, "Pedestrian detection : An evaluation of the state of the art", IEEE Trans. on Pattern Analysis and Machine Intelligence, 34(4), pp.743~761 (2012)
- N. Tada, "Mobile robot navigation by center following using monocular vision", SICE Annual Conf (2007)
- R. Derhgawen, "Vision based obstacle detection using 3D HSV histograms", 2011 Annual IEEE, India Conf. (INDICON), pp.1~4 (2011)
- J. Kim, "Moving obstacle avoidance of robot using a single camera", Proc. Int. Symp. on Robotics and Intelligent Sensors, 41, pp.911~916 (2012)
- C. Hu, "Reliable people tracking approach for mobile robot in indoor environments", Robotics and Computer-Integrated Manufacturing, 26(2), pp.174~179 (2010)
- K. S. Ong, "Sensor fusion based human detection and tracking system for humanrobot interaction", 2012 IEEE, 2012, 4835~4840
- N. Bellotto, "Multisensor-based human detection and tracking for mobile service robots", IEEE Trans. on Systems, Man, and Cybernetics, Part B : Cybernetics, 39(1), pp.167~181 (2009)
- A. Fernández-Caballero, "Optical flow or image subtraction in human detection from infrared camera on mobile robot", Robotics and Autonomous Systems, 58(12), pp.1273~1281 (2010)
- P. Viola, "Robust real-time face detection", Int. Journal of Computer Vision, 57(2), pp.137~154 (2004)
- R. Lienhart, "An extended set of haar-like features for rapid object detection", Int. Conf. on Image Processing 2002, 1, pp.903~903 (2002)