광 흐름과 학습에 의한 영상 내 사람의 검지
Human Detection in Images Using Optical Flow and Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Human detection is an important aspect in many video-based sensing and monitoring systems. Studies have been actively conducted for the automatic detection of humans in camera images, and various methods have been proposed. However, there are still problems in terms of performance and computational cost. In this paper, we describe a method for efficient human detection in the field of view of a camera, which may be static or moving, through multiple processing steps. A detection line is designated at the position where a human appears first in a sensing area, and only the one-dimensional gray pixel values of the line are monitored. If any noticeable change occurs in the detection line, corner detection and optical flow computation are performed in the vicinity of the detection line to confirm the change. When significant changes are observed in the corner numbers and optical flow vectors, the final determination of human presence in the monitoring area is performed using the Histograms of Oriented Gradients method and a Support Vector Machine. The proposed method requires processing only specific small areas of two consecutive gray images. Furthermore, this method enables operation not only in a static condition with a fixed camera, but also in a dynamic condition such as an operation using a camera attached to a moving vehicle.
Abstract
Human detection is an important aspect in many video-based sensing and monitoring systems. Studies have been actively conducted for the automatic detection of humans in camera images, and various methods have been proposed. However, there are still problems in terms of performance and computational cost. In this paper, we describe a method for efficient human detection in the field of view of a camera, which may be static or moving, through multiple processing steps. A detection line is designated at the position where a human appears first in a sensing area, and only the one-dimensional gray pixel values of the line are monitored. If any noticeable change occurs in the detection line, corner detection and optical flow computation are performed in the vicinity of the detection line to confirm the change. When significant changes are observed in the corner numbers and optical flow vectors, the final determination of human presence in the monitoring area is performed using the Histograms of Oriented Gradients method and a Support Vector Machine. The proposed method requires processing only specific small areas of two consecutive gray images. Furthermore, this method enables operation not only in a static condition with a fixed camera, but also in a dynamic condition such as an operation using a camera attached to a moving vehicle.
참고문헌 (14)
- D. T. Nguyen, "Human detection from images and videos : A survey", Pattern Recognit, 51(3), pp.148~175 (2016)
- M. Sonka, "Image Processing, Analysis, and Machine Vision" (2008), Thomson
- J. K. Baruah, "Advances in Communication, Devices and Networking" (2018), Springer
- N. Dalal, "Histograms of oriented gradients for human detection", Proc. Comput. Vis. Pattern Recognit, 1, pp.886~893 (2005)
- E. J. Alreshidi1, "Characterizing human behaviours using statistical motion descriptor", Signal Image Process, 10(1), pp.15~25 (2019)
- K. Souhila, "Optical flow based robot obstacle avoidance", Int. J. Adv. Robot. Syst, 4(1), pp.13~16 (2007)
- J. Bouguet, "Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm", Tech-nical Report OpenCV Document Intel Microprocessor Research Labs (1999)
- C. Harris, "A combined corner and edge detector", Proc. 4th Alvey Vis. Conf, 15, pp.147~151 (1988)
- V. Vapnik, "Pattern recognition using generalized portrait method", Autom. Remote Control, 24(6), pp.774~780 (1963)
- G. Xu, "Real-time pedestrian detection based on edge factor and Histogram of Oriented Gradient", Proc. IEEE Conf. on Inf. Autom, pp.384~389 (2011)
- 도용태, "영상 내 사람의 검출을 위한 에지 기반 방법", 센서학회지, 25(4), pp.285~290 (2016), 한국센서학회[DOI]
- Haena Yim, "Dielectric Properties of Ca0.8Sr1.2Nb3O10 Nanosheet Thin Film Deposited by the Electrophoretic Deposition Method", 센서학회지, 27(1), pp.1~5 (2018), 한국센서학회[DOI]
- R. Collins, "Introduction to the special section on video surveillance", IEEE Trans. Pattern Anal. Mach. Intell, 22(8), pp.745~746 (2000)