Edge Detection of Laser Range Image Based on a Fast Adaptive Ant Colony Algorithm
Laser range imaging is the current priority research areas of airborne lidar. And realizing accurate edge detection of laser range image is the key of completing the subsequent three-dimensional reconstruction. Based on the characteristics of laser range image and the deficiencies of traditional edge detection methods, a new improved fast adaptive ant colony algorithm for edge detection of laser range image has been proposed in this paper. Due to the initial cluster center and the heuristic guiding function used in the algorithm, the randomness and blindness of ants walking are eliminated thoroughly, and the speed of image edge detection is also greatly increased. Meanwhile, thanks to the applied ants’ selection mechanism and updating mechanism varying in contents, the error detection rate and omission factor of edge points as well as noise interference are all avoided, and the accuracy and adaptability of laser range image edge detection are greatly improved as well. Experimental results have shown that, this algorithm is more effective than other edge detection methods, and can meet the requirements of three-dimensional reconstruction.
KeywordsAnt Colony Algorithm Edge Detection Laser Range Image Three-Dimensional Reconstruction Contrast Experiment
Unable to display preview. Download preview PDF.
- 2.Chevrier, C., Perrin, J.P.: Interactive parametric modeling: POG a tool the cultural heritage monument 3D reconstruction. In: CAADRIA conference, Chiang Mai (2008)Google Scholar
- 3.Kolomenkin, M., Shimshoni, I., Tal, A.: On edge detection on surfaces. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2767–2774 (2009)Google Scholar
- 4.Ren, C., Wu, S.-l., Jiao, L.-c.: Edge Detection Algorithm of SAR Images with Wedgelet Filter. J. Journal of Beijing Institute of Technology 3, 346–350 (2008)Google Scholar
- 5.Zhang, X.-h.: Airborne laser radar measurement theory and method, pp. 43–44. Wuhan University Press, Wuhan (2007)Google Scholar
- 7.Caldeira, J., Azevedo, R., Silva, C.A., Sousa, J.M.C.: CP with ACO. In: Supply-Chain Management Using ACO and Beam-ACO Algorithms, pp. 1–6. IEEE Press, Los Alamitos (2008)Google Scholar
- 8.Socha, K., Dorigo, M.: Ant colony optimization for continuous domains. J. European Journal of Operational Research (2006) (in press) (Corrected Proof)Google Scholar
- 10.Haibin, D.: Principle and application of ant colony algorithm, pp. 303–304. Science Press, Beijing (2005)Google Scholar
- 11.Ouadfel, S., Batouche, M.: Ant colony system to image texture classification. In: Proceedings of International Conference on Machine Learning and Cybernetics, pp. 1491–1495 (2003)Google Scholar
- 13.Zhuang, X.-H.: Image feature extraction with the perceptual graph based on the ant colony system. In: Proceedings of the IEEE International Conference on Systems Man, and Cybeinetics (SMC 2004), Washington, DC, pp. 6354–6359. IEEE Computer Society, Los Alamitos (2004)Google Scholar