KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

3D Object Recognition Using Appearance Model Space of Feature Point

특징점 Appearance Model Space를 이용한 3차원 물체 인식

  • 주성문 (전남대학교 컴퓨터공학과) ;
  • 이칠우 (전남대학교 전자컴퓨터공학부)
  • Received : 2013.12.17
  • Accepted : 2014.01.22
  • Published : 2014.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

3D object recognition using only 2D images is a difficult work because each images are generated different to according to the view direction of cameras. Because SIFT algorithm defines the local features of the projected images, recognition result is particularly limited in case of input images with strong perspective transformation. In this paper, we propose the object recognition method that improves SIFT algorithm by using several sequential images captured from rotating 3D object around a rotation axis. We use the geometric relationship between adjacent images and merge several images into a generated feature space during recognizing object. To clarify effectiveness of the proposed algorithm, we keep constantly the camera position and illumination conditions. This method can recognize the appearance of 3D objects that previous approach can not recognize with usually SIFT algorithm.

카메라의 시선 방향에 따라 다른 영상을 생성하는 3차원 물체를 2차원 영상만으로 인식하는 것은 어려운 일이다. 특히 영상 생성 시 강한 투영변환(perspective transformation) 이 발생할 경우 투영된 물체의 이미지에 대한 국소 특징을 정의하는 SIFT(Scale-Invariant Feature Transform) 알고리즘은 물체 인식에 한계가 있다. 본 논문에서는 3차원 물체를 하나의 특정 축을 중심으로 회전시키면서 얻은 복수의 영상을 학습 데이터로 활용한 물체인식 방법을 제안한다. 이 방법을 이용하여 복수 영상의 특징 점들을 하나의 특징 공간으로 합성하고 영상들 간의 기하학적인 관계를 이용하여 중복된 영역을 제거한 모델을 생성하면 임의의 3차원 회전이 적용된 물체를 인식할 수 있다. 실험에서는 알고리즘의 유용성을 먼저 확인하기 위해 조명조건과 카메라의 위치를 일정하게 유지하였다. 이 방법에 의해 SIFT 알고리즘만으로 인식이 힘들었던 3차원 물체의 다양한 외관(appearance) 인식이 가능하게 되었다.

Keywords

References

  1. Mu Li, Shantanu Rane, and Petros Boufounos, "Quantized embeddings of scale-invariant image features for mobile augmented reality", IEEE International Workshop on Multimedia Signal Processing(MMSP 2012), September, 2012, pp.1-6.
  2. Xiaoou Tang, "IntentSearch: Capturing User Intention for One-Click Internet Image Search", IEEE Transactions on pattern analysis and machine intelligence, Vol.34, No.7, July, 2012, pp.1342-1353. https://doi.org/10.1109/TPAMI.2011.242
  3. Junji Satake, Masaya Chiba, and Jun Miura, "A SIFT-Based Person Identification using a Distance-Dependent Appearance Model for a Person Following Robot", Robotics and Biomimetics(ROBIO), 2012 IEEE International Conference on, pp.962-967.
  4. Seung-Ho Baeg, Jae-Han Park, "An Object Recognition System for a Smart Home Environment on the Basis of Color and Texture Descriptors", Intelligent Robots and Systems, 2007 IEEE/RSJ International Conference on, pp.901-906.
  5. Yichen Fan, Max Q.-H. Meng, "3D reconstruction of the WCE images by affine SIFT method", 8th World Congress on Intelligent Control and Automation(WCICA), pp.943-947.
  6. D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, Vol.60, Issue 2, November, 2004, pp.91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  7. Hamit Soyel and Hasan Demirel, "Improved SIFT Matching for Pose Robust Facial Expression Recognition", Automatic Face& Gesture Recognition and Workshops, 2011 IEEE International Conference on, pp.585-590.
  8. Ran Zhou, Jie Wu, Qing He, Chao Hu and Zhuliang Yu, "Approach of Human Face Recognition Based on SIFT Feature Extraction and 3D Rotation Model", Information and Automation(ICIA), 2011 IEEE International Conference on, pp.476-479.
  9. Yutaka Usui, Katsuya Kondo, "3D Object Recognition Based on Confidence LUT of SIFT Feature Distance", 2010 Second World Congress on Nature and Biologically Inspired Computing, pp.293-297.
  10. Keju Peng, Xin Chen, "3D Reconstruction Based on SIFT and Harris Feature Points", 2009 IEEE International Conference on Robotics and Biomimetics, pp.960-964.
  11. Yi Ma, Stefano Soatto, Jana Kosecka and S. Shankar Sastry, "An Invitation to 3-D Vision", Springer - Verlag New York Pub, pp.110-116, 177-181, 2004.

Cited by

  1. Changes in the Number of Matching Points in CCTV's Stereo Images by Indoor/Outdoor Illuminance vol.23, pp.1, 2015, https://doi.org/10.7319/kogsis.2015.23.1.129