Use of artificial living system for pavement distress survey

Automation of pavement surface distress survey is of considerable interest since it facilitates road maintenance. Pavement distress detection algorithm is proposed, which includes preprocessing and artificial life algorithm. In nature, bee population consists of different species of bees. Different species of bees cooperate with others and build combs. The process of building combs is based on a bottom-up structure instead of a top-down centralized controller like expert system and exhibits the emergent properties of bee population. Artificial living system in artificial life algorithm is very similar to bee population. In artificial life algorithm, artificial living system is an artificial population, which is composed of different species of artificial organisms. Artificial living system is based on a bottom-up synthetic approach and exhibits its emergent properties for distress detection. Experimental results demonstrate the proposed method has strong effect on noise removal, oilstains elimination and the rid of dark spots.

[1]  William R. Oliver.  Artificial life approach to color contrast manipulation , 1999, Other Conferences.

[2]  Christian Smith,et al.  Automating Inspection of Highway Pavement Surfaces , 1993 .

[3]  JaChing Chou,et al.  Pavement distress classification using neural networks , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[4]  Bo-Suk Yang,et al.  Optimum design of short journal bearings by artificial life algorithm , 2001 .

[5]  M. A. Wirth,et al.  Segmentation: artificial life and watershed transform approach , 1997 .

[6]  Hao He,et al.  Artificial Life for Image Segmentation , 2001, Int. J. Pattern Recognit. Artif. Intell..

[7]  Kelvin C. P. Wang.  Designs and Implementations of Automated Systems for Pavement Surface Distress Survey , 2000 .

[8]  Dominique Barba,et al.  A Markov random field for rectilinear structure extraction in pavement distress image analysis , 1995, Proceedings., International Conference on Image Processing.

[9]  J.-C. Heudin,et al.  Artificial life and evolutionary computing in machine perception , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[10]  Hironori Okii.  Featuring Extraction for Classification of Breast Tumor Images Using Artificial Organisms , 2001 .

[11]  João Eduardo Kögler,et al.  An artificial life approach for the animation of cognitive characters , 2001, Comput. Graph..

[12]  Jiming Liu,et al.  ALIFE: A Multiagent Computing Paradigm for Constraint Satisfaction Problems , 2001, Int. J. Pattern Recognit. Artif. Intell..

[13]  Robert L. Lytton,et al.  Flexible pavement distress evaluation using image analysis , 1991 .

[14]  Heng-Da Cheng,et al.  Automatic Pavement Distress Setection System , 1998, Inf. Sci..

[15]  Masafumi Hagiwara,et al.  Image segmentation by artificial life approach using autonomous agents , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).