This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Edge-Region-Based Segmentation of Range Images
March 1994 (vol. 16 no. 3)
pp. 314-319

In this correspondence, we present a new computationally efficient three-dimensional (3-D) object segmentation technique. The technique is based on the detection of edges in the image. The edges can be classified as belonging to one of the three categories: fold edges, semistep edges (defined here), and secondary edges. The 3-D image is sliced to create equidepth contours (EDCs). Three types of critical points are extracted from the EDCs. A subset of the edge pixels is extracted first using these critical points. The edges are grown from these pixels through the application of some masks proposed in this correspondence. The constraints of the masks can be adjusted depending on the noise present in the image. The total computational effort is small since the masks are applied only over a small neighborhood of critical points (edge regions). Furthermore, the algorithm can be implemented in parallel, as edge growing from different regions can be carried out independently of each other.

[1] S. Aubry and V. Hayward, "Range image analysis using level contours," inProc. 5th Scandinavian Conf. Image Anal., Stockholm, 1987, pp. 661-668.
[2] P. J. Besl and R. C. Jain, "Segmentation through symbolic surface descriptions," inProc. IEEE Computer Vision and Pattern Recognition Conf., Miami Beach, FL, June 1986, pp. 77-85.
[3] B. Bhanu, S. Lee, C. C. Ho, and T. Henderson, "Range data Processing: Representation of surfaces by edges," inProc. 8th Int. Conf. on Pattern Recognition, pp. 236-238, Oct. 1986.
[4] M. Brady, J. Ponce, A. Yuille, and H. Asada, "Describing surfaces," inProc. 2nd Int. Symp. Robotics Research, H. Hanafusa and H. Inoue, Eds. Cambridge, MA: MIT Press, 1985.
[5] T.-J. Fan, G. Medioni, and R. Nevatia, "Segmented description of 3-D surfaces,"IEEE J. Robotics Automat., Dec. 1987, pp. 527-538.
[6] R. Hoffman and A. K. Jain, "Segmentation and classification of range images,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 608-619, 1987.
[7] S. Inokuchi, T. Nita, F. Matsuka, and Y. Sakurai, "A three dimensional edge-region operator for range images," inProc. Int. Joint Conf. Pattern Recognition-6, Oct. 1982.
[8] D. J. Langridge, "Detection of discontinuities in the first derivatives of surfaces,"Comput. Vision Graphics Image Proceesing, vol. 27, pp. 291-308, 1984.
[9] J.-G. Leu, I. K. Sethi, and G. Yu, "Range image segmentation from equidistance contours," inProc. IEEE Computer Vision Workshop, Miami, FL, pp. 339-341, Dec. 1987.
[10] A. Mitiche and J. K. Aggarwal, "Detection of edges using range information,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 174-178, Mar. 1983.
[11] M. Oshima and Y. Shirai, "A scene description method using three-dimensional information,"Pattern Recogn., vol. 11, pp. 9-17, 1979.
[12] T. Pavlidis,Algorithms for Graphics and Image Processing. Rockville, MD: Computer Science Press, 1982.

Index Terms:
edge detection; computational complexity; image segmentation; edge-region-based segmentation; range images; computationally efficient 3-D object segmentation; fold edges; semistep edges; occlusion; secondary edges; equidepth contours
Citation:
M.A. Wani, B.G. Batchelor, "Edge-Region-Based Segmentation of Range Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 3, pp. 314-319, March 1994, doi:10.1109/34.276131
Usage of this product signifies your acceptance of the Terms of Use.