Please use this identifier to cite or link to this item:
標題: 基於視覺之雙足機器人定位與尋標
Vision-based Biped Robot Localization and Target Seeking
作者: 隋立漢
Suei, Li-Han
關鍵字: Biped Robot;雙足機器人;Localization;Target Seeking;定位;尋標
出版社: 電機工程學系所
引用: [1] S. Makrogiannis, Ch. Theoharatos, G. Economau, S. Fotopoulos, “Color image segmentation using multiscale fuzzy C-means and graph theoretic merging,” in Proceedings 2003 International Conference on Image Processing, vol. 1, pp. 14-17, Sep. 2003. [2] H. D. Cheng, X. H. Jiang, Y. Sun, and J. Wang, “Color Image Segmentation: Advances and Prospects,” International Journal on Pattern Recognition, vol. 34, no. 12, pp. 2259-2281, Sep. 2000. [3] R.C. Gonzalez and R.E. Wooks, “Digital image processing,” 2002. [4] H.D. Cheng and Y. Sun, “A hierarchical approach to color image segmentation using homogeneity,” IEEE Transactions on Image Processing, vol. 9, pp. 2071-2082, Dec. 2000. [5] K. S. Chong and L. Kleeman, “Feature-based mapping in real, large scale environments using an ultrasonic array,” International Journal of Robotics Research, vol. 18, no. 2, pp. 3-19, Jan. 1999. [6] S. Thrun, D. Fox and W. Burgard, “A probabilistic approach to concurrent mapping and localization for mobile robots,” in Machine Learning and Autonomous Robots, vol. 31, pp. 29-53, 1998. [7] [8] J. F. Li, K. Q. Wang, and Z. D., “A new equation of saturation in RGB-to-HSI conversion for more rapidity of computing,” in Proceedings of the International Conference on Machine Learning and Cybernetics, pp. 1493-1497, 2002. [9] T. Kawanishi, T. Kurozumi, K. Kashino, S. Takagi, “A fast template matching algorithm with adaptive skipping using inner-subtemplate's distance,” in Proceedings of the IEEE Internation Conference on Pattern Recognition, pp. 654-657, 2004. [10] T. Kawanishi, T. Kurozumi, K. Kashino, S. Takagi, “Dynamic active search for quick object detection with pan-tilt-zoom camera,” in Proceedings of the IEEE International Conference on Image Processing, pp. 716-719, 2001.
早期工業界對於自動化機器的應用都是使用順序控制為主,而目前的先進自動化機器的應用主流則是智慧型控制。本論文利用所提出的視覺處理目標物辨認與定位演算法,發展出一套結合視覺處理技術的雙足機器人行動控制機制,使機器人可以準確抵達目標物地點。所提出的方法能透過由攝影設備取得的影像來辨別目標物,並計算出正確的角度和距離以準確到達定位。此方法分成兩階段:在第一階段,我們用HSV色域之非均切割判別辨認出目標物;而在第二階段則用 RGB色域以確認相應的角度和距離。透過我們所提出的這個視覺處理目標物辨認與定位法,我們能讓雙足機器人精確的到達目的地;而這個方法更可進一步應用到其他領域,例如目標物追蹤、障礙物迴避和危險物偵測與移除等。

In the early stages of industry, sequential control is used to be the main application of automation robotics; however, the current trend of advanced applications in this field is intelligent control. This thesis aims to develop vision-based human biped robot control capable of navigating a robot to reach target accurately by taking advantage of the proposed vision-based object recognition and robot localization algorithm. The proposed method can recognize the target object from an image captured by camera and calculate the right angle and distance for robot navigation. The proposed method includes two phases: First, the non-uniform HSV-based region segmentation method is used to match the target object. Second, a simple RGB-based method is utilized to determine the angle and the distance between the target object and the robot for localization. Through the vision-based object recognition and localization method, we can control the biped robot to reach the target successfully. The proposed technique can be further applied to other fields such as target tracking, obstacle avoidance and dangerous object detection/removal.
其他識別: U0005-1208201015561000
Appears in Collections:電機工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.