Abstract
Terrain perception technology using passive sensors plays a key role in enhancing autonomous mobility for military unmanned ground vehicles in off-road environments. In this paper, an effective method for classifying terrain cover based on color and texture features of an image is presented. Discrete wavelet transform coefficients are used to extract those features. Furthermore, spatial coordinates, where a terrain class is located in the image, are also adopted as additional features. Considering real-time applications, we applied a neural network as classifier and it is trained using real off-road terrain images. Through comparison of the classification performance according to applied feature sets and color space changes, we can find that the feature vectors with spatial coordinates extracted using the Daub2 wavelet in the HSI color space have the best classification performance. Experiments show that using the wavelet features and spatial coordinates features improves the terrain cover classification performance. The proposed algorithm has a promising results and potential applications for autonomous navigation.
Similar content being viewed by others
References
Manduchi, R., Castano, A., Talukder, A., Matthies, L.: Obstacle detection and terrain classification for autonomous off-road navigation. Auton. Robot. 18, 81–102 (2005)
Bellutta, P., Manduchi, R., Matthies, L., Owens, K., Rankin, A.: Terrain perception for demo III. In: Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 326–331. Dearborn, MI (2000)
Rankin, A.L., Bergh, C.F., Goldberg, S.B., Bellutta, P., Huertas, A., Matthies, L.H.: Passive perception system for day/night autonomous off-road navigation. Proc. SPIE 5804, 342–358 (2005)
Matthies, L., Kelly, A., Litwin, T., Tharp, G.: Obstacle detection for unmanned ground vehicles: a progress report. Robotics Research 7, 475–486 (1996)
Matthies, L., Litwin T., Owens, K., Rankin, A., Murphy, K., Coombs, D., Gilsinn, J., Hong, T., Legowik, S., Nashman, M., Yoshimi, B.: Performance evaluation of UGV obstacle detection with CCD/FLIR stereo vision and LADAR. In: Proceedings of the 1998 IEEE ISIC/CIRA/ISAS Joint Conference, pp. 658–670. Gaithersburg, MD (1998).
Jansen, P., van der Mark, W., van den Heuvel, J.C., Groen, F.C.A.: Colour based Off-Road Environment and Terrain type Classification. In: Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, pp. 216–221. Vienna, Austria (2005)
Manduchi, R.: Learning outdoor color classification. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1713–1723 (2006)
Buluswar, S.D., Draper, B.A.: Color machine vision for autonomous vehicles. Int. J. Eng. Appl. Artif. Intell. 11(2), 245–256 (1998)
Castano, R., Manduchi, R., Fox, J.: Classification experiments on real-world texture. In: Workshop on Empirical Evaluation in Computer Vision, Kauai, HI (2001)
Manduchi, R.: Bayesian fusion of color and texture segmentations. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 2, pp. 956–962 (1999)
Shi, X., Manduchi, R.: A study on Bayes feature fusion for image classification. In: Proceedings of the 2003 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW’03), vol. 3, p. 95 (2003)
Commission Internationale de L’Eclairge (CIE), Official Recommendations on Uniform Color Spaces, Color Difference Equations, and Metric Color Terms, Pub. No. 15, Supp. Num. 2 (E-1.3.1) (1976)
Ingrid Daubechies, Ten Lectures on Wavelets, Society for Industrial and Applied Mathematics (1992)
Misiti, M., Misiti, Y., Oppenheim, G., Poggi, J.M.: Wavelet toolbox user’s guide. MathWork Inc
Neural Network Toolbox. MathWork Inc
Shima, Y., Murakami, T., Koga, M., Yashiro, H., Fujisawa, H.: A high speed algorithm for propagation-type labeling based on block sorting of runs in binary images. Proceedings of 10th International Conference on Pattern Recognition 1, 655–658 (1990)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sung, GY., Kwak, DM. & Lyou, J. Neural Network Based Terrain Classification Using Wavelet Features. J Intell Robot Syst 59, 269–281 (2010). https://doi.org/10.1007/s10846-010-9402-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-010-9402-2