KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of Motion Detection based on Extracting Reflected Light using 3-Successive Video Frames

3개의 연속된 프레임을 이용한 반사된 빛 영역추출 기반의 동작검출 알고리즘 구현

  • 김창민 (상지대학교 컴퓨터정보공학부) ;
  • 이규웅 (상지대학교 컴퓨터정보공학부)
  • Received : 2015.09.08
  • Accepted : 2015.12.23
  • Published : 2016.03.15
⟨ Previous Next ⟩

Abstract

Motion detection algorithms based on difference image are classified into background subtraction and previous frame subtraction. 1) Background subtraction is a convenient and effective method for detecting foreground objects in a stationary background. However in real world scenarios, especially outdoors, this restriction, (i.e., stationary background) often turns out to be impractical since the background may not be stable. 2) Previous frame subtraction is a simple technique for detecting motion in an image. The difference between two frames depends upon the amount of motion that occurs from one frame to the next. Both these straightforward methods fail when the object moves very "slightly and slowly". In order to efficiently deal with the problem, in this paper we present an algorithm for motion detection that incorporates "reflected light area" and "difference image". This reflected light area is generated during the frame production process. It processes multiplex difference image and AND-arithmetic of bitwise. This process incorporates the accuracy of background subtraction and environmental adaptability of previous frame subtraction and reduces noise generation. Also, the performance of the proposed method is demonstrated by the performance assessment of each method using Gait database sample of CASIA.

실시간 동작영역 검출 알고리즘의 차영상 기법은 배경프레임을 이용한 방식과 이전프레임을 이용한 방식으로 구분된다. 배경프레임을 이용한 방식은 사전에 분석한 배경정보를 기반으로 정확한 동작영역을 검출할 수 있는 방법이다. 하지만 배경정보가 변경될 경우 정보갱신이 요구되므로, 실시간 응용분야에 제한적이다. 이전프레임을 이용한 방식은 현재프레임과 시차간격이 존재하는 이전프레임을 취득하여 동작의 윤곽선을 검출한다. 하지만 실제 윤곽선과 오차를 보여 보정이 필요하다는 단점을 가지고 있다. 본 논문이 제안하는 3 way-diff 알고리즘은 프레임 제작과정 중 발생되는 반사된 빛 영역과 차영상 기법을 이용해 동작의 윤곽선을 구하므로, 기존 방식들에 배경의존성 및 부정확성을 보완한다. 다중 차영상 기법 및 비트단위의 AND 연산으로 수행되며, 이 과정으로 배경프레임을 이용한 방식의 정확성과 이전프레임을 이용한 방식의 환경적응력을 융합하며 노이즈의 발생을 감소시킨다. 또한 제안하는 기법의 성능은 CASIA의 Gait 데이터베이스 샘플을 이용해 각 기법에 대한 성능평가로 증명한다.

Keywords

Acknowledgement

Supported by : 상지대학교

References

  1. Kyu-Woong Lee, "Implementation of Video Surveillance System with Motion Detection based on Network Camera Facilities," Journal of the IIBC, Vol. 14, No. 1, pp. 169-177, Feb. 2014. (in Korean)
  2. Seok-Woo Jang and Jin-Uk Kim, "Analysis of Moving Object Trajectories Using Difference Images," Journal of the Korean Institute of Information Technology, Vol. 4, No. 3, pp. 19-28, Jul. 2005. (in Korean)
  3. R. T. Collins, A. J. Lipton, and T. Kanade, "Introduction to the special section on video surveillance," IEEE Trans. Pattern Anal. Machine Intelligence, Vol. 22, pp. 745-746, Aug. 2000. https://doi.org/10.1109/TPAMI.2000.868676
  4. Y. Kameda and M. Minoh, "A human motion estimation method using 3-successive video frames," Proc. of the International Conference on Virtual Systems and Multimedia, pp. 135-140, Sep. 1996.
  5. R. Collins, A. Lipton, and T. Kanade, "A System for Video Surveillance and Monitoring," Proc. of the ANS 8th International Topical Meeting Robotic and Remote Systems, Apr. 1999.
  6. W.M. Hu, T.N. Tan, L. Wang, and S.J. Maybank, "A Survey on Visual Surveillance of Object Motion and Behaviors," IEEE Trans. Systems, Man, and Cybernetics, Part C: Applications and Reviews, Vol. 34, No. 3, pp. 334-352, 2004. https://doi.org/10.1109/TSMCC.2004.829274
  7. Ji-nyun Chung and Hyun Seung Yang, "Comparison between Retinex model and Illumination-reflectance model for object recognition," Proc. of the Korea Multimedia Society Spring Conference, pp. 28-31, 2005. (in Korean)
  8. Jihye Jeon, Daehee Kim, Yoongi Yang, Joonki Paik, and Changsu Lee, "Image Distortion Compensation for Improved Gait Recognition," Journal of the Institute of Electrical and Electronics Engineers, Vol. 46, No. 4, pp. 97-107, Jul. 2009. (in Korean)
  9. Joungwook Park, Kwan H.Lee, "Noise elimination in difference image for object detection," Proc. of the HCI Society of korea, pp. 1207-1211, Feb. 2004. (in Korean)
  10. Chang Min Kim, Kyu Woong Lee, "The Implementation of Motion Detection Algorithm using Image Difference Technique and Light Reflected Area by Objects," Proc. of the KIISE:Korea Computer Conference, ISSN 2288-5951, pp. 1395-1397, 2015. (in Korean)
  11. CASIA database, available: http://www.sinobiometrics.com(downloaded 2014, Jan. 14)