Object Detection for Robotic Applications Using Perceptual Organization in 3D

详细信息    查看全文

• 作者：Andreas Richtsfeld (1)
  Michael Zillich (1)
  Markus Vincze (1)
  
  1. Vienna University of Technology ; Vienna ; Austria
  
• 关键词：Object segmentation ; Perceptual organization
• 刊名：KI - Künstliche Intelligenz
• 出版年：2015
• 出版时间：February 2015
• 年：2015
• 卷：29
• 期：1
• 页码：95-99
• 全文大小：289 KB
• 参考文献：1. Boyer KL, Mirza MJ, Ganguly G (1994) The robust sequential estimator : a general approach and its application to surface organization in range data. IEEE Trans Pattern Anal Mach Intell (PAMI) 16(10):987鈥?001 CrossRef
  2. Boyer KL, Sarkar S (1999) Perceptual organization in computer vision: status, challenges, and potential. Comput Vision Image Underst 76(1):1鈥? CrossRef
  3. Campbell N, Vogiatzis G, Hern谩ndez C, Cipolla R (2007) Automatic 3D object segmentation in multiple views using volumetric graph-cuts. Br Mach Vision Conf 28:530鈥?39
  4. Chang CC, Lin CJ (2011) LIBSVM : a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1鈥?7 CrossRef
  5. Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vision 59(2):167鈥?81 CrossRef
  6. Koffka K (1935) Principles of Gestalt psychology, international library of psychology, philosophy, and scientific method, vol 20. Harcourt, Brace and World
  7. K枚hler W (1959) Gestalt psychology today. Am Psychol 14(12):727鈥?34 CrossRef
  8. Leonardis A, Gupta A, Bajcsy R (1995) Segmentation of range images as the search for geometric parametric models. Int J Comput Vis 14(3):253鈥?77 CrossRef
  9. Metzger W (1936) Laws of seeing. The MIT Press
  10. Mishra AK, Shrivastava A, Aloimonos Y (2012) Segmenting simple objects using RGB-D. In: International conference on robotics and automation (ICRA), pp 4406鈥?413
  11. M枚rwald T (2013) Object modelling for cognitive robotics. Ph.D. thesis, Vienna University of Technology
  12. Richsfeld A (2013) Robust object detection for robotics using oerceptual organization in 2D and 3D. Ph.D. thesis
  13. Richtsfeld A (2012) The object segmentation database (OSD). http://www.acin.tuwien.ac.at/?id=289
  14. Richtsfeld A, M枚rwald T, Prankl J, Balzer J, Zillich M, Vincze M (2012) Towards scene understanding object segmentation using RGBD-images. In: Proceedings of the 2012 computer vision winter workshop (CVWW). Mala Nedelja, Slovenia
  15. Richtsfeld A, M枚rwald T, Prankl J, Zillich M, Vincze M (2012) Segmentation of unknown objects in indoor environments. In: IEEE/RSJ international conference on intelligent robots and systems, pp 4791鈥?796
  16. Richtsfeld A, M枚rwald T, Prankl J, Zillich M, Vincze M (2013) Learning of perceptual grouping for object segmentation on RGB-D data. J Vis Commun Image Represent
  17. Richtsfeld A, Zillich M, Vincze M (2012) Implementation of Gestalt principles for object segmentation. In: 21st international conference on pattern recognition (ICPR). Tsukuba, Japan
  18. Sarkar S, Boyer KL (1993) Perceptual organization in computer vision鈥攁 review and a proposal for a classificatory structure. IEEE Trans Syst Man Cybern 23(2):382鈥?99 CrossRef
  19. Sedlacek D, Zara J (2009) Graph cut based point-cloud segmentation for polygonal reconstruction. In: 7th international conference on computer vision systems, pp 218鈥?27
  20. Strom J, Richardson A, Olson E (2010) Graph-based segmentation for colored 3D laser point clouds. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), pp 2131鈥?136
  21. 脺ckermann A, Haschke R, Ritter H (2012) Real-time 3D segmentation of cluttered scenes for robot grasping. In: 12th IEEE-RAS international conference on humanoid robots
  22. Wertheimer M (1923) Untersuchungen zur Lehre von der Gestalt II. Psychol Res 4(1):301鈥?50 CrossRef
  23. Wertheimer M (1958) Principles of perceptual organization. In: a source book of Gestalt psychology, pp 115鈥?35
  24. Wu TF, Lin CJ (2004) Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res 5:975鈥?005
  
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Software Engineering, Programming and Operating Systems
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1610-1987

文摘

Object segmentation of unknown objects with arbitrary shape in cluttered scenes is still a challenging task in computer vision. A framework is introduced to segment RGB-D images where data is processed in a hierarchical fashion. After pre-segmentation and parametrization of surface patches, support vector machines are used to learn the importance of relations between these patches. The relations are derived from perceptual grouping principles. The proposed framework is able to segment objects, even if they are stacked or jumbled in cluttered scenes. Furthermore, the problem of segmenting partially occluded objects is tackled.