Mars terrain image classification using Cartesian genetic programming

Automatically classifying terrain such as rocks, sand and gravel from images is a challenging machine vision problem. In addition to human designed approaches, a great deal of progress has been made using machine learning techniques to perform classification from images. In this work, we demonstrate the first known use of Cartesian Genetic Programming (CGP) to this problem. Our CGP for Image Processing (CGP-IP) system quickly learns classifiers and detectors for certain terrain types. The learned program outperforms currently used techniques for classification tasks performed on a panorama image collected by the Mars Exploration Rover Spirit.

[1]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[2]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[3]  T.T. Nguyen,et al.  Experiences with operations and autonomy of the Mars Pathfinder Microrover , 1998, 1998 IEEE Aerospace Conference Proceedings (Cat. No.98TH8339).

[4]  J. Miller.  An empirical study of the efficiency of learning boolean functions using a Cartesian Genetic Programming approach , 1999 .

[5]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[6]  I. L. Shevalev,et al.  Lunar and Planetary Robotic Exploration Missions in the 20th Century , 2003 .

[7]  TomasM art ´ inek.  An Evolvable Image Filter: Experimental Evaluation of a Complete Hardware Implementation in FPGA , 2005 .

[8]  Julian Francis Miller,et al.  Redundancy and computational efficiency in Cartesian genetic programming , 2006, IEEE Transactions on Evolutionary Computation.

[9]  Karl Iagnemma,et al.  Terrain Classification and Classifier Fusion for Planetary Exploration Rovers , 2008, 2007 IEEE Aerospace Conference.

[10]  Alex S. Fukunaga,et al.  Automatic detection of dust devils and clouds on Mars , 2008, Machine Vision and Applications.

[11]  Tomoharu Nagao,et al.  Feed Forward Genetic Image Network: Toward Efficient Automatic Construction of Image Processing Algorithm , 2007, ISVC.

[12]  Wolfgang Banzhaf,et al.  Genetic programming on GPUs for image processing , 2008, Int. J. High Perform. Syst. Archit..

[13]  Simon Harding,et al.  Evolution of image filters on graphics processor units using Cartesian Genetic Programming , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[14]  Daniel M. Helmick,et al.  Autonomy for Mars Rovers: Past, Present, and Future , 2008, Computer.

[15]  Javier A. Montoya-Zegarra,et al.  Fast interactive segmentation of natural images using the image foresting transform , 2009, 2009 16th International Conference on Digital Signal Processing.

[16]  Cartesian genetic programming , 2010, GECCO.

[17]  Qiang Shen,et al.  Facilitating efficient Mars terrain image classification with fuzzy-rough feature selection , 2011, Int. J. Hybrid Intell. Syst..

[18]  C. Shang,et al.  Classification of Mars McMurdo panorama images using machine learning techniques , 2011 .

[19]  Wolfgang Banzhaf,et al.  Distributed genetic programming on GPUs using CUDA , 2011 .

[20]  Julian F. Miller,et al.  A Survey of Self Modifying Cartesian Genetic Programming , 2011 .

[21]  Wolfgang Banzhaf,et al.  Image Processing and CGP , 2011, Cartesian Genetic Programming.

[22]  Jürgen Leitner,et al.  icVision: A modular vision system for cognitive robotics research , 2012 .

[23]  Jürgen Leitner,et al.  MT-CGP: mixed type cartesian genetic programming , 2012, GECCO '12.

[24]  Jürgen Leitner,et al.  Cartesian Genetic Programming for Image Processing , 2013 .

[25]  Yong Wang,et al.  Machine Vision and Applications , 2013 .