Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지

A Method for Terrain Cover Classification Using DCT Features

DCT 특징을 이용한 지표면 분류 기법

  • Received : 2010.04.30
  • Accepted : 2010.07.12
  • Published : 2010.08.05
Download PDF
⟨ Previous Next ⟩

Abstract

The ability to navigate autonomously in off-road terrain is the most critical technology needed for Unmanned Ground Vehicles(UGV). In this paper, we present a method for vision-based terrain cover classification using DCT features. To classify the terrain, we acquire image from a CCD sensor, then the image is divided into fixed size of blocks. And each block transformed into DCT image then extracts features which reflect frequency band characteristics. Neural network classifier is used to classify the features. The proposed method is validated and verified through many experiments and we compare it with wavelet feature based method. The results show that the proposed method is more efficiently classify the terrain-cover than wavelet feature based one.

Keywords

References

  1. R. Manduchi, "Obstacle Detection and Terrain Classification for Autonomous Off-road Navigation", Autonomous Robots, Vol. 18, pp. 81-102, 2005. https://doi.org/10.1023/B:AURO.0000047286.62481.1d
  2. Talukder, et. al., "Autonomous Terrain Characterization and Modeling for Dynamic Control of Unmanned Vehicles", International Conference on Intellignet Robots and Systems, 2002.
  3. P. Bellutta, et. al., "Terrain Perception for DEMO III", Procedings of the 2000 Intelligent Vehicles Conference, 2000.
  4. Paul Jansen, et. al., "Colour Based Off-road Environment and Terrain Type Classification", Proceedings of the 8th International IEEE Conference on Intellignet Transportation Systems, 2005.
  5. Gi-Yeul Sung, Dong-Min Kwak, Do-Jong Kim, Joon Lyou, "Terrain Cover Classification Based on Wavelet Features and Neural Networks", International Conference on Control, Automation and Systems, 2008.
  6. Tanaka, M. and Goto, H., "Autonomous Text Capturing Robot Using Improved DCT Feature and Text Tracking", Document Analysis and Recognition, Vol. 2, pp. 1178-1182, 2007.
  7. Xiao-Yuan Jing and Zhang, D., "A Face and Palmprint Recognition Approach Based on Discriminant DCT fEature Extraction", Systems, Man, and Cybernetics, Part B, Vol. 34, pp. 2405-2415, 2004. https://doi.org/10.1109/TSMCB.2004.837586
  8. Hee-Jung Bae and Sung-Hwan Jung, "Image Retrieval using Texture Based on DCT", Information, Communications and Signal Processing, Vol. 2, pp. 1065-1068, 1997.
  9. Xiang-Yu Huang, Yu-Jin Zhong, Dong Hu, "Image Retrieval Based on Weighted Texture Features using DCT Coefficients of JPEG Images", Information, Communications and Signal Processing, Vol. 3, pp. 1571-1575, 2003.
  10. Yu-Len Huang, Ruey-Feng Chang, "Texture Features for DCT-coded Image Retrieval and Classification", Acoustics, Speech, and Signal Processing, Vol. 6, pp. 3013-3016, 1999.
  11. Seung-Youn Lee, Dong-Min Kwak, Gi-Yeol Sung, Do-Jong Kim, "Modified Component-Labeling Algortihms Applied to Grayscale Images", International Conference on Control, Automation and Systems, Vol. 1, pp. 2171-2175, 2008.