RHSeg is a recursive approximation of HSeg. RHSeg is implemented in a software package that can optionally utilize parallel computing for increased processing speed.

HSWO is an implementation of the hierarchical step-wise region growing approach to image segmentation. The HSeg algorithm is an augmentation of HSWO which (i) provides for the merging of non-adjacent regions (effectively classifying groups of connected region objects into spatially disjoint region classes), and (ii) provides approaches for selecting region growing iterations from which segmentation results are saved to form a segmentation hierarchy.

[1] J-M. Beaulieu and M. Goldberg, “Hierarchy in picture segmentation: A stepwise optimal approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 2, pp. 150-163, Feb. 1989. [2] James C. Tilton, “Image Segmentation by Region Growing and Spectral Clustering with a Natural Convergence Criterion,” Proceedings of the 1998 International Geoscience and Remote Sensing Symposium, Seattle, WA, pp. 1766-1768, July 6-10, 1998. [3] James C. Tilton, Yuliya Tarabalka, Paul M. Montesano and Emanuel Gofman, “Best Merge Region Growing Segmentation with Integrated Non-Adjacent Region Object Aggregation,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 11, November 2012, pp. 4454-4467. [4] J. C. Tilton, “Refinement of the HSeg Algorithm for Improved Computational Processing Efficiency,” Disclosure of Invention and New Technology: NASA Case No. GSC 16,024-1, March 2, 2010. [5] J. C. Tilton, “Further refinement of the computationally efficient HSeg algorithm,” Disclosure of Invention and New Technology: NASA Case No. GSC 16,250-1, Feb. 21, 2011. [6] J. C. Tilton, “D-dimensional formulation and implementation of recursive hierarchical segmentation,” Disclosure of Invention and New Technology: NASA Case No. GSC 15199-1, May 26, 2006. [7] J. C. Tilton, “Parallel Implementation of the Recursive Approximation of an Unsupervised Hierarchical Segmentation Algorithm,” Chapter 5 of High Performance Computing in Remote Sensing, C.-I. Chang and A. J. Plaza, editors, CRC Press, pp. 133-144, 2007.0 [8] J. L. Muerle and D. C. Allen, “Experimental evaluation of techniques for automatic segmentation of objects in a complex scene,” in G. C. Chen, et al. (eds), Pictorial Pattern Recognition, Thompson:Washington, DC, pp. 3-13, 1968. [9] James C. Tilton, “A split-remerge method for eliminating processing window artifacts in recursive hierarchical segmentation,” Disclosure of Invention and New Technology: NASA Case No. GSC 14,994-1, March 9, 2005. NOTE: U. S. Patent No. 7,697,759 was awarded to this technology on April 13, 2010. [10] James C. Tilton, “A Region Labeling Tool for use with Hierarchical Segmentation,” Disclosure of Invention and New Technology: NASA Case No. GSC 14,331-1, February, 29, 2000.

Wei Wan

James C. Tilton

Researchers should cite this work as follows:

• Wei Wan; Lexie Yang (2015), "RHSeg," https://mygeohub.org/resources/rhseg.

  BibTex | EndNote

1. Hyperspectral image
2. Remote Sensing
3. segmentation