The Integration of Image Segmentation Maps using Region and Edge Information

We present an algorithm that integrates multiple region segmentation maps and edge maps. It operates independently of image sources and specific region-segmentation or edge-detection techniques. User-specified weights and the arbitrary mixing of region/edge maps are allowed. The integration algorithm enables multiple edge detection/region segmentation modules to work in parallel as front ends. The solution procedure consists of three steps. A maximum likelihood estimator provides initial solutions to the positions of edge pixels from various inputs. An iterative procedure using only local information (without edge tracing) then minimizes the contour curvature. Finally, regions are merged to guarantee that each region is large and compact. The channel-resolution width controls the spatial scope of the initial estimation and contour smoothing to facilitate multiscale processing. Experimental results are demonstrated using data from different types of sensors and processing techniques. The results show an improvement over individual inputs and a strong resemblance to human-generated segmentation. >

[1]  Harry L. Van Trees,et al.  Detection, Estimation, and Modulation Theory: Radar-Sonar Signal Processing and Gaussian Signals in Noise , 1992 .

[2]  A. Gualtierotti.  H. L. Van Trees, Detection, Estimation, and Modulation Theory, , 1976 .

[3]  C. G. Bachman.  Laser radar systems and techniques , 1979 .

[4]  B.W. Dickinson,et al.  An introduction to statistical signal processing with applications , 1979, Proceedings of the IEEE.

[5]  R. Kohler.  Integrating non-semantic knowledge into image segmentation processes , 1983 .

[6]  Martin D. Levine,et al.  Low Level Image Segmentation: An Expert System , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Pascal Fua,et al.  Using Generic Geometric Models for Intelligent Shape Extraction , 1987, AAAI.

[8]  David Sher.  Evidence Combination Using Likelihood Generators. , 1987 .

[9]  Steven K. Rogers,et al.  Multisensor Data Fusion Of Laser Radar And Forward Looking Infrared (FLIR) For Target Segmentation And Enhancement , 1987, Other Conferences.

[10]  Ren C. Luo,et al.  The issues and approaches of a robot multi-sensor integration , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[11]  Theodosios Pavlidis,et al.  Integrating region growing and edge detection , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Alan C. Bovik,et al.  On detecting edges in speckle imagery , 1988, IEEE Trans. Acoust. Speech Signal Process..

[13]  D.J. Anderson,et al.  Optimal Estimation of Contour Properties by Cross-Validated Regularization , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  J. K. Aggarwal,et al.  Detection and segmentation of man-made objects in outdoor scenes: concrete bridges , 1989 .

[15]  Yoshihiko Nakamura,et al.  Geometrical fusion method for multi-sensor robotic systems , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[16]  Jake K. Aggarwal,et al.  The integration of region and edge-based segmentation , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[17]  John F. Haddon,et al.  Image Segmentation by Unifying Region and Boundary Information , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Jake K. Aggarwal,et al.  Image segmentation using laser radar data , 1990, Pattern Recognit..

[19]  Bir Bhanu,et al.  Model-based segmentation of FLIR images , 1990 .

[20]  C.-C. Chu,et al.  Multi-sensor image interpretation using laser radar and thermal images , 1991, [1991] Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application.