Mobile QR Code QR CODE
Title Dynamic Memory Access Control for Accelerating FPGA-based Image Processing
Authors (Kenta Nishiguchi) ; (Toshiyuki Inoue) ; (Rei Yamazaki) ; (Kazunori Ogohara) ; (Akira Tsuchiya) ; (Keiji Kishine)
Page pp.29-38
ISSN 1598-1657
Keywords FPGA; image processing; memory; IoT; machine learning
Abstract In an FPGA-based image processing system, memory access plays an important role in increasing the speed of image processing. With the conventional method, the memory access interval for image processing was fixed, which limited the processing speed. In this work, we developed a novel memory access method that dynamically controls the intervals between memory access requests for image processing by monitoring the memory status. We implemented an image processing system with the proposed method and examined its characteristics. The maximum processing speed with the proposed method reached 30.7 fps, which was 1.65 times faster than that of the conventional method.