Journal of Digital Contents Society (디지털콘텐츠학회 논문지)

Digital Contents Society (한국디지털콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Illumination Influence Minimization Method for Efficient Object

영상에서 효율적인 객체 추출을 위한 조명 영향 최소화 기법

  • Received : 2013.02.25
  • Accepted : 2013.03.29
  • Published : 2013.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper suggests the robust method of extraction for moving objects in illumination variation by using image sequence from an immovable camera. The most difficult part of the implication is the effect by illumination and noise. The object area is hardly estimated when the dusky area occurs in illumination variation by time change. This thesis describes the extraction of moving objects employed by Gaussian mixture model which is noise robust measure. Also, the report suggests the elimination method of illumination part in input image by the representative illumination image which is defined to minimize the illumination influence.

본 논문에서는 고정된 카메라로부터 획득한 연속된 이미지 시퀀스를 이용하여 조명 변화에 강건한 운동 객체를 추출하는 방법을 제안한다. 운동 객체 추출 시 가장 문제가 되는 것은 조명과 잡음에 의한 영향이다. 시간의 변화에 따른 조명의 변화로 어두운 영역에 의한 가려짐 현상이 발생할 경우 객체 영역을 판단하기가 쉽지 않다. 본 논문에서는 잡음에 강건한 방법인 가우시안 혼합 모델을 이용하여 운동객체를 추출 하였으며, 조명에 대한 영향을 최소화 하고자 대표 조명 영상을 정의하고 이를 통하여 입력 영상에 대한 조명 성분을 제거하는 방법을 제안한다.

Keywords

References

  1. Ming-Shou An, Dae-Seong Kang, "A Study of Real-time Detecting and Tracking Moving Object Using Improved MOG and Predict Method", Korean Institute Of Information Technology, Vol.7, No.4 pp.102-107, 2009.
  2. Y. Ricquebourg and P. Bouthemy, "Real-time tracking of moving persons by exploiting spatio-temporal image slices," IEEE trans. on PAMI, Vol.8, No.22, pp.797-808, 2000.
  3. Je-Hyuk Choi, Hyochoong Bang, "Target Tracking Algorithm for UAV based on Optical Flow", Korean Society for Aeronautical & Space Sciences, pp.522-526, 2011.
  4. Chris.Staffer and W.E.L Grimson, "Adaptive background mixture models for real-time tracking", Computer Vision and Pattern Recognition, Vol.2, pp.244-252, 1999.
  5. Dae-Yong Park, Jae-Min Kim, Seong-Won Cho, Jun-Beom Kim, "Advanced Gaussian Mixture Learning for Complex Environment", Proceeding of KFIS Autumn Conference, Vol.20, No.1, pp.193-196, 2010.
  6. Yair Weiss, "Deriving intrinsic images from image sequences", Computer Vision, Proceedings. Eighth IEEE International Conference, Vol.2, pp.68-75, 2001.
  7. Matsushita, Y, "Illumination Normalization with Time-Dependent Intrinsic Images for Video Surveillance", Pattern Analysis and Machine Intelligence, IEEE Transactions, Vol.26, pp.1336-1347, 2004. https://doi.org/10.1109/TPAMI.2004.86
  8. Porikli Fatih, "Multiplicative Background-Foreground Estimation Under Uncontrolled Illumination using Intrinsic Images", Application of Computer Vision, Vol.1, pp.20-27, 2005.
  9. Tae-Eun Kim, "Edge Extraction Method Based on Color Image Model", Koran Digital Contents Society, Vol. 4, No. 1, pp.11-21, 2003.
  10. Jin-Yun Chung, Hyun-Seung Yang, "Comparative Study on Illumination Compensation Performance of Retinex model and Illumination-Reflectance model", Korean Institute of Information Scientists and Engineers, Vol.33, No.11, pp.936-941, 2006.
  11. Kyoung-Mi Lee, Youn-Mi Lee, "Adaptive Model-based Multi-object Tracking Robust to Illumination Changes and Overlapping", Korean Institute of Information Scientists and Engineers, Vol.32, No.5, pp.449-460, 2005.

Cited by

  1. Codebook-Based Foreground Extraction Algorithm with Continuous Learning of Background vol.15, pp.4, 2014, https://doi.org/10.9728/dcs.2014.15.4.449
  2. A Recognition Method for Moving Objects Using Depth and Color Information vol.19, pp.4, 2016, https://doi.org/10.9717/kmms.2016.19.4.681
  3. Urban spatial structure change detection in land cover map using time-series patch mapping vol.19, pp.9, 2018, https://doi.org/10.9728/dcs.2018.19.9.1727
  4. 배경 모델 갱신을 통한 코드북 기반의 전배경 분할 vol.17, pp.5, 2016, https://doi.org/10.9728/dcs.2016.17.5.375