Region Segmentation of Outdoor Scene Using Multiple Features and Context Information
This paper presents a method to segment the region of objects in outdoor scene for autonomous robot navigation. The proposition of the method segments from an image taken by moving robot on outdoor Scene. The method begins with object segmentation, which uses multiple features to obtain the object of segmented region. Multiple features are color, edge, line segments, Hue Co-occurrence Matrix (HCM), Principal Components (PCs) and Vanishing Points (VPs). Model the objects of outdoor scene that define their characteristics individually. We segment the region as mixture using the proposed features and methods. Objects can be detected when we combine predefined multiple features. Next, the stage classifies the object into natural and artificial ones. We detect sky and trees of natural object and building of artificial object. Finally, the last stage shows the combination of appearance and context information. We confirm the result of object segmentation through experiments by using multiple features and context information.
Keywordsobject segmentation outdoor scene multiple features context information
Unable to display preview. Download preview PDF.
- 2.Li, J., Wang, J.Z., Wiederhold, G.: Classification of Textured and Non-textured Images Using Region Segmentation. Int’l, Conf. on Image Processing, pp. 754–757 (2000)Google Scholar
- 3.Zhang, C., Wang, P.: A New Method of Color Image Segmentation Based on Intensity and Hue Clustering. Int’l Conf. on Pattern Recognition 3, 613–616 (2000)Google Scholar
- 4.Partio, M., Cramariuc, B., Gabbouj, M., Visa, A.: Rock Texture Retrieval Using Gray Level Co-occurrence Matrix. In: Proc. of 5th Nordic Signal Processing Symposium (2002)Google Scholar
- 5.Singhal, A., Jiebo, L., Weiyu, Z.: Probabilistic spatial context models for scene content understanding. In: IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 235–241 (2003)Google Scholar
- 7.Xuming He., Zemel R. S., Carreira-Perpinan, M. A.: Multiscale conditional random fields for image labeling. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 695–702(2004)Google Scholar
- 8.Zhang, W., Kosecka, J.: Localization based on building recognition. In: Int’l Conf. on Computer Vision and Pattern Recognition, vol. 3, pp. 21–28 (2005)Google Scholar