Evolving Cellular Automata to Segment Hyperspectral Images Using Low Dimensional Images for Training

This paper describes a hyperspectral image segmentation approach that has been developed to address the issues of lack of adequately labeled images, the computational load induced when using hyperspectral images in training and, especially, the adaptation of the level of segmentation to the desires of the users. The algorithm used is based on evolving cellular automata where the fitness is established based on the use of synthetic RGB images that are constructed on-line according to a set of parameters that define the type of segmentation the user wants. A series of segmentation experiments over real hyperspectral images are presented to show this adaptability and how the performance of the algorithm improves over other state of the art approaches found in the literature on the subject.

[1]  Jon Atli Benediktsson,et al.  A new approach for the morphological segmentation of high-resolution satellite imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[2]  Jon Atli Benediktsson,et al.  Segmentation and classification of hyperspectral images using watershed transformation , 2010, Pattern Recognit..

[3]  Guy Flouzat,et al.  Spatial and spectral segmentation of satellite remote sensing imagery using processing graphs by mathematical morphology , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[4]  Richard J. Duro,et al.  Hyperspectral image segmentation through evolved cellular automata , 2013, Pattern Recognit. Lett..

[5]  Jean-Yves Tourneret,et al.  Markov random fields for joint unmixing and segmentation of hyperspectral images , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[6]  Antonio J. Plaza,et al.  Hyperspectral Image Segmentation Using a New Bayesian Approach With Active Learning , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Richard J. Duro,et al.  Computational Intelligence for Remote Sensing , 2008 .

[8]  Richard J. Duro,et al.  Using Gaussian Synapse ANNs for Hyperspectral Image Segmentation and Endmember Extraction , 2008 .

[9]  Tiziana Veracini,et al.  Robust hyperspectral image segmentation based on a non-Gaussian model , 2010, 2010 2nd International Workshop on Cognitive Information Processing.

[10]  Peijun Li,et al.  Evaluation of multiscale morphological segmentation of multispectral imagery for land cover classification , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[11]  Jon Atli Benediktsson,et al.  Classification and feature extraction for remote sensing images from urban areas based on morphological transformations , 2003, IEEE Trans. Geosci. Remote. Sens..

[12]  Pablo Quesada-Barriuso,et al.  Efficient segmentation of hyperspectral images on commodity GPUs , 2012, KES.

[13]  Jon Atli Benediktsson,et al.  Automatic Generation of Standard Deviation Attribute Profiles for Spectral–Spatial Classification of Remote Sensing Data , 2013, IEEE Geoscience and Remote Sensing Letters.

[14]  Aly A. Farag,et al.  A unified framework for MAP estimation in remote sensing image segmentation , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[15]  J. Tilton,et al.  Analysis of hierarchically related image segmentations , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[16]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[17]  Francisco Argüello,et al.  Efficient ELM-Based Techniques for the Classification of Hyperspectral Remote Sensing Images on Commodity GPUs , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Wolfgang Reinhardt,et al.  Image segmentation for the purpose of object-based classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).