本論文利用FPGA開發板結合兩個CMOS影像感測模組，建立自走車三維空間距離感測以及即時影像追蹤功能。自走車追蹤特定目標物之步驟為，首先藉由兩張成對的影像，經過影像處理找出具有相同特徵點的特定目標物，利用立體影像三角成像原理計算出特定目標物與自走車的距離。經由所得到的特定目標物位置以及距離資訊，系統可自動控制自走車的移動，使自走車追蹤特定目標物，並與特定目標物保持一定距離。操作者也可透過無線藍牙方式以手動控制模式引導自走車移動。

The thesis aims to utilize a FPGA development platform with two CMOS image sensors to build three-dimensional distance estimation function for a mobile robot as well as a real-time image tracking function. The steps for tracking a specific target of a mobile robot are as follows. At first, a pair of images is used to find a specific target which has the same image features. After that the triangular perspective theory of the stereo vision is used to calculate the distance between a specific target and the mobile robot. Furthermore, a mobile robot can also move autonomously by knowing the distance between a specific target and itself, so that it can track the specific target and keep a fixed distance ahead. User can also guide the mobile robot in manual control mode via the Bluetooth wireless.

[1] Leese, J. A., Novak, C. S., and Taylor, V. R. “The Determination of Cloud Motion Patterns from Geosynchronous Satellite Image Data,” Patter Recognition, Clustering, Statistic, Grammars, Learning, Vol. 2, pp. 272-292, 1970.

[2] Horn, K. P. and Schunck, B. G. “Determining Optical Flow,” Artificial Intelligence, Vol. 17, pp. 185-203, 1981.

[3] Fuh, C. S. and Maragos P., “Region-Based Optical Flow Estimation,” Proceedings of IEEE Conference on Computer Vision and attern Recognition, San Diego, CA, pp. 130-133, 1989.

[4] Tan, Y. P., Kulkarni, S. R., and Ramadge, P. J. “A New Method for Camera Motion Paramater Estimation,” IEEE International Conference on Image Processing, Vol. 1, pp. 406-409, 1995.

[5] Masoud, O. and Papanikolopoulos, N. P. “A Novel Method for Tracking and Counting Pedestrians in Real-Time Using a Single Camera,” IEEE Trans. on Vehicukar Technology, Vol. 50, No. 5, pp. 1267-1278, 2001.

[6] Marr, D. and Poggio, T. “Cooperative Computation of Stereo Disparity,” Science, Vol. 194, pp. 283-287, 1976.

[7] Barnard, S. T. and Thompson, W. B., “Disparity Analysis of Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 2, pp. 330-340, 1980.

[8] Tsai, R. Y., “A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses,” IEEE J. of Robotics and Automation, Vol. RA-3, No. 4, pp. 323-344, 1987.

[9] Izaguirre, A., Pu, P., and Summers, J., “A New Development in Camera Calibration: Calibrating a Pair of Mobile Cameras,” Int. J. Robotics Res., Vol. 6, No. 3, pp. 104-116, 1987.

[10] Yau, W. Y. and Wang, H., “Fast Relative Depth Computation for an Active Stereo Vision System,” Real-Time Imaging, Vol. 5, pp. 189-202, 1999.

[11] Murray D., Little J., “Using Real-time Stereo Vision for Mobile Robot Navigation,” Autonomous Robots, 8(2):161-171, 2000.

[12] M. Bertozzi, A. Broggi, “GOLD: a Parallel Real-time Stereo Vision System for Generic Obstacle and Lane Detection,” IEEE Transactions on Image Processing, Vol. 7. No. 1, pp. 62-81, 1998.

[13] Kazuhiro Shimizu, Shinichi Hirai, “Implementing Planar Motion Tracking Algorithms on CMOS+FPGA Vision System,” IEEE International on Intelligent Robots and Systems, pp. 1366-1371, 2006.

[14] Yu-Jen Chen, Yan-Chay Li, Ke-Nung Huang, Ming-Shing, Young; “The Implementation of a Stand-alone Video Tracking and Analysis System for Animal Behavior Measurement in Morris Water Maze,” IEEE 27th Annual International Conference of the Engineering in Medicine and Biology Society, pp. 1766-1768, 2005.

[15] 鐘書明, “以SOPC實現強鍵性彩色影像物體追蹤及移動預測系統,” 碩士論文, 國立成功大學電機工程學系, 民國93年6月.

[16] 錢鉦津, “模糊控制之立體視覺影像追蹤系統,” 碩士論文, 中原大學機械工程系, 民國94年7月.

[17] 陳俊佳, “即時影像追蹤之自走車設計,” 碩士論文, 國立中央大學電機工程學系, 民國96年6月.

[18] 任紹棟, “具立體視覺測距之移動機器人,” 碩士論文, 國立台灣科技大學電機工程系, 民國96年7月.

[19] 鐘國亮, “影像處理與電腦視覺,” 東華書局, 台北市, 1999年9月.

[20] Ming-Bo Lin, “Digital System Designs and Practices: Using Verilog HDL and FPGAs,” Wiley, 2008.