以軟硬體協同設計之目標物移動方向模糊辨識系統

Abstract

本論文利用Altera DE2-70實驗板以及模糊邏輯理論，提出一種以軟硬體協同設計之模糊目標物移動方向辨識系統，在SOPC (System on Program Chip, SOPC)之系統架構下，利用FPGA (Field Programming Gate Array)的硬體電路優勢，以軟硬體協同設計 (HW/SW Co-design)之方式實現硬體加速之功能。作法上係利用硬體電路獲得目標物影像之歷史軌跡，並用Nios II計算上、下、左、右方向的計數，再將此計數傳送到模糊邏輯推論的硬體電路，即可得到目標物體的移動方向。實驗結果證實本方法可以利用機器視覺來辨識目標物的移動方向，實現互動式之人機介面，達到控制機器的運作。論文整體架構大致上可分為： (1)以軟體實現此系統的演算法、 (2)將此系統實現於Altera DE2-70開發版之晶片設計，希望利用硬體平行處理的優勢，加速其演算法的速度。In this thesis, a hardware and software co-design approach is proposed to develop a fuzzy moving direction identification system using the Altera DE2-70 board and fuzzy logic theory. Under the system architecture of System on the Program Chip (SOPC), we take advantages of the framework of hardware and software co-design, where hardware circuits by Field Programming Gate Array (FPGA) are designed to accelerate the system performance of the historical trajectories of the target image, while direction counts are calculated by the Nios II CPU. A hardware circuit is also design to identify the moving direction of the target object. Experimental results show that the proposed method is able to identify the movement direction of the target direction, providing an interactive man-machine interface to control the operation of the machine. The contents of this thesis can be divided into: (1) proposed algorithm and its implementation by software (2) hardware and software co-design of the proposed algorithm on the Altera DE2-70 development board to accelerate the execution of the proposed algorithm.