立體影像伺服控制自走車研製

Development of Stereo Vision-Guided Autonomous Cart

林哲賢(Jer-Shyan Lin)

指導教授 ： 邱國慶

國立虎尾科技大學/工程學院/機械與機電工程研究所/碩士(2011年)

https://doi.org/10.6827/NFU.2011.00145

摘要

本文的研究目的主要在發展一套立體影像伺服自走車系統。整體架構分為四個系統，分別為影像處理系統、微控制處理系統、動力驅動系統與無線傳輸系統。整體架構分為四個系統，分別是人機控制介面系統、嵌入式影像處理系統、微控制器，及馬達驅動系統。人機控制介面系統係由LabVIEW套裝軟體發展而成，且可透過無線通訊網路將影像處理程式藉由筆記型電腦傳送至嵌入式系統。當系統在執行運動目標追蹤時，自走車上的兩組CCD攝影機所擷取的影像資訊可經由IEEE1394通訊介面傳輸至嵌入式系統，立體影像資訊經嵌入式影像處理系統以立體視覺演算法處理後可求得到目標物與CCD影像畫面中心點之相對誤差，接著，嵌入式系統將此誤差訊號以並列通訊方式傳給PIC18F252徵控制器。
本文運用Lyapunov穩定準則推導出「適應模糊滑動模式控制技術」，將其植入PIC18F252中運算，並送出適當的PWM馬達控制訊號，透過橋式驅動電路控制左右輪馬達，使自走車可以平滑地追隨前方移動中的目標物。

關鍵字

立體影像 ； 自走車影像處理適應模糊滑動模式控制

並列摘要

In this paper, a visual servoing control system is developed for an autonomous cart by using a stereo vision. The proposed system is composed of a human-machine controlled interface, an embedded image processing system, a microcontroller, and a motors controlled system. Based on LabVIEW tool, The human-machine controlled interface is developed in a notebook which takes a wireless communication with the embedded image processing system. When tracking the moving object, the embedded image processing system uses two CCD cameras to obtain the object images for feedbacking the environment information to embedded image processing system by protocol IEEE1394. After extracting the object images, the 3-D distance information between the target object and the cart can be calculated by stereo vision algorithm. Based on this distance information, the error which defined in image plane will be obtained, and can be transmitted from the embedded system to the microcontroller (PIC18f252) by parallel port communication. Using the error signals, the AFSMC algorithm can be derived from the Lyapunov stability theory by the MCU(PIC18f252) to produce the control command( PWM signal) for H-bridge motor drivers which can drive the motors to track the object at center of the image plane.
A comparative analysis with experimental results soundly confirmed that the performance of developed AFSMC is better than those of classical PID controllers.

並列關鍵字

stereo vision ； autonomous cart ； image processing ； adaptive fuzzy

參考文獻

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

[5]Amar Mitiche and Abdol-Reza Mansouri , “On Convergence of the Horn and Schunck Optical-Flow Estimation Method” , IEEE Transactions on image processing, Vol.13 , pp.848-852 , 2004

[6]Fuh, C. S. and Maragos, P., “Region-Based Optical Flow Estimation,” Proceedings of IEEE conference on Computer Vision and Pattern Recognition, SanDiego, C. A., pp. 130-133, 1989.

[7]Ando, Y., and Yuta, S., 1995, “Following a Wall by an Autonomous Mobile Robot with a Sonar-Ring,” IEEE International Conference on Robotics and Automation, May, Nagoya, Japan, 3, 2599-2606

[8]Tsai, C. -C., 1998, “A Localization System of a Mobile Robot by FusingDead-Reckoning and Ultrasonic Measurements,” IEEE Transactions on Instrumentation and Measurement, 47(5), pp. 1399-1404