Main Article Content

Abstract

Information of texture to distinguish between the types of terrains in the environment are not defined by clear boundaries. In this paper we illustrate that an image consists of a composite texture of regions. Using Image Processing Algorithms, the type of the terrain is identified, and accordingly the appropriate velocity of the robot is derived, so that the robot can traverse over that particular terrain. It’s a real time process, and the speed of the robot changes with a change in the terrain in the environment. A video camera will be mounted on the robot, with a similar perspective to the driver, which takes the video of the road, with different classes of textures when the car is in motion. These textures (loose stones, grass, ground, concrete, asphalt, slopes) will then be processed using Image Processing Algorithms. Based on the results obtained after applying the algorithms, the velocity estimations are done and the speed of the robot changes accordingly.

Keywords

Wavelet transform WCF FIS

Article Details

How to Cite
Nanavaty, A., Patel, R., & Kandoi, A. (2015). SPEED CONTROL MECHANISM USING TERRAIN DETECTION. International Journal of Students’ Research in Technology & Management, 1(2), 97–108. Retrieved from https://mgesjournals.com/ijsrtm/article/view/49

References

  1. “Reactive speed control system based on terrain roughness detection†by Mattia Castelnovi,
  2. Laboratorium Dist., University of Genova; Ronald Arkin, College of Computing Georgia Institute
  3. of Technology; Thomas R Collins, School of ECE/GTRI, Georgia Institute of Technology
  4. “Terrain characterization and roughness estimation for simulation and control of unmanned
  5. ground vehicles†by Jeremy James Dawkins -December 12, 2011.
  6. “Wheeled-robot’s velocity updating and odometry based localization by navigating on outdoor
  7. terrains†by M. en C. Farid García Lamont. Thesis advisor: José Matías Alvarado Mentado-
  8. November 2010.
  9. “Unsupervised texture segmentation using discrete wavelet frames†by S. Liapis, N. Alvertos, and
  10. G. Tziritas Institute of Computer Science - FORTH, and, Department of Computer Science,
  11. University of Crete, P.O. Box 1470, Heraklion, Greece.
  12. “Texture segmentation using wavelet transform†by S. Arivazhagan, Department of Electronics
  13. and Communication Engineering, Mepco Schlenk Engineering College, Amathur (P.O.), Sivakasi
  14. 005, Tamil Nadu, India; L. Ganesan, Department of Electronics and Communication Engineering, Mepco Schlenk Engineering College, Amathur (P.O.), Sivakasi 626 005, Tamil
  15. Nadu, India, 4 February 2003; received in revised form 31 July 2003.
  16. “Digital image processingâ€, Second Edition by Rafael C. Gonzalez and Richard E. Woods.
  17. “Wavelet-based histograms for selectivity estimation†by Yossi Matias, Department of Computer
  18. Science Tel Aviv University, Israel: Jerey Scott Vittery Department of Computer Science, Duke
  19. University; Min Wangz Department of Computer Science,Duke University.
  20. “Design of feature extraction in content based image retrieval (CBIR) using color and textureâ€,
  21. Swati V. Sakhare & Vrushali G. Nasre Dept. of Electronics Engg., Bapurao Deshmukh College
  22. of Engg., Sevagram, Wardha (India).
  23. “Wavelet based image segmentationâ€, Andrea Gavlasov´a, Aleˇs Proch´azka, and Martina
  24. Mudrov´a Institute of Chemical Technology, Department of Computing and Control Engineering.
  25. “Image segmentation using wavelet domain classificationâ€, Hyeokho Choi and Richard Baraniuk,
  26. Department of Electrical and Computer Engineering, Rice University, Houston, Tx77005, USA.