基于Vivado HLS的求取特征点图像坐标的设计

针对传统嵌入式处理器处理高清图像时功耗高、延时长以及数据存储带宽受限等问题，文中提出了对软件进行硬件加速以提高图像处理系统计算性能的方案。该设计采用Xilinx高层次综合工具Vivado HLS，通过软硬件协同设计将OpenCV及C++编写的算法程序转化为RTL硬件。设计成果显示，该方案有效的提高了系统的计算性能，并且缩短了硬件开发周期。

Design of Calculating Image Coordinates of Feature Point Based on Vivado HLS

Aiming at the problems of traditional embedded processors such as high power consumption, the hardware acceleration of the software was proposed to improve the computing performance of the image processing system program. In this paper, With the usage of Vivado HLS, a high-level synthesis tool, OpenCV and C++ algorithms were translated into RTL hardware through hardware-software co-design. The design results showed that the scheme effectively improved the computing performance of the system and shorten the hardware development cycle.