A Region Depth Estimation Algorithm using Motion Vector from Monocular Video Sequence

단안영상에서 움직임 벡터를 이용한 영역의 깊이추정

  • 손정만 (강릉영동대학 디지털미디어계열) ;
  • 박영민 (경운대학교 멀티미디어공학부) ;
  • 윤영우 (영남대학교 전자정보공학부)
  • Published : 2004.04.01

Abstract

The recovering 3D image from 2D requires the depth information for each picture element. The manual creation of those 3D models is time consuming and expensive. The goal in this paper is to estimate the relative depth information of every region from single view image with camera translation. The paper is based on the fact that the motion of every point within image which taken from camera translation depends on the depth. Motion vector using full-search motion estimation is compensated for camera rotation and zooming. We have developed a framework that estimates the average frame depth by analyzing motion vector and then calculates relative depth of region to average frame depth. Simulation results show that the depth of region belongs to a near or far object is consistent accord with relative depth that man recognizes.

2차원 이미지로부터 3차원 이미지 복원은 각 픽셀까지의 깊이 정보가 필요하고, 3차원 모델의 복원에 관한 일반적인 수작업은 많은 시간과 비용이 소모된다. 본 논문의 목표는 카메라가 이동하는 중에, 획득된 단안 영상에서 영역의 상대적인 깊이 정보를 추출하는 것이다. 카메라 이동에 의한 영상의 모든 점들의 움직임은 깊이 정보에 종속적이라는 사실에 기반을 두고 있다. 전역 탐색 기법을 사용하여 획득한 움직임 벡터에서 카메라 회전과 배율에 관해서 보상을 한다. 움직임 벡터를 분석하여 평균 깊이를 측정하고, 평균 깊이에 대한 각 영역의 상대적 깊이를 구하였다. 실험결과 영역의 상대적인 깊이는 인간이 인식하는 상대적인 깊이와 일치한다는 것을 보였다.

Keywords

References

  1. H.261 ITU-T Recommendation H.261 Vidoe codec for audiovisual services at p×64 kbit/s
  2. MPEG-1 ISO/IEC 11172-2 Information Technology-Coding of Moving Picture and Associated Audio for Digitan Storage Mediaa at up to about 1.5/mbit/s : Part 2 Video
  3. MPEG-1 ISO/IEC 13818-2 Information Technology-Genetic coding of Moving Picture and Associated Audio Information : Video
  4. ISPRS '92 v.29 Model-Based 3D Scene Analysis from Stereoscopic Image Sequences R.Koch
  5. European Workshop on Combined Real And Synthetic ImageProceeding For Broadcast And Video Productions Automatic Modeling fo 3D Natural Objects from Multiple Views Niem W. Buschmann
  6. 3D Structure from 2D Motion Tony Jebara;Ali Azarbayejani;Alex Pentland
  7. Image and Vision Computing v.14 Estimation Of Depth And 3D Motion Parameter Of Moving Object With Multiple Stereo Images Jae-Woong Yi;Jun-Ho Oh
  8. Image Processing, Analysis and Machine Mulan Sonka;Valcav Hlavac;Roger Boyle
  9. Photogrammetria v.23 no.1 The Objective Theory Of Reletive Orientation E.Thoomson
  10. Science v.194 Cooperative Computation Of Stereo Disparity D.Marr;T.Poggio
  11. Handbook of Pattern Recignition and Computer Vision Projective Geometry And Computer Vision R.Mohr
  12. CISST 2000 v.Ⅰ Estimation of the Dept Information from Single View Image Seqyence with Camera Translation Joon-Woo Yoon;Dae-Seong Jeoune;Sang-Gon Kim;Young-Min Yoon
  13. CISST 2000 v.Ⅰ Global Motion Estimation by Analyzing the Panning/Tilting Angles of Camera Rotation and Zooming Factor Dae-Seong Jeoune;Zi-Yoon Song;Joon-Ho Park;Young-Min Park;Young-Woo Yoon
  14. Machine Vision Ramesh Jain;Rangachar Kasturi;Brian G. Schunch