FPGA的图像识别与目标跟踪系统设计

Design of Image Recognition and Target Tracking System Based on FPGA

采用FPGA构建目标跟踪系统实现对单色背景下的某一物体的识别与跟踪。此设计由图像采集模块、图像存储模块、图像处理模块、图像显示模块4大模块构成。系统选用OV5640数字摄像头对图像信息进行采集,SDRAM对图像数据进行存储,然后利用均值滤波算法来平滑图像,紧接着使用Sobel边缘检测算法对目标进行处理,并对其结果进行二值化操作,再通过包围盒技术以实现对目标的跟踪,最后将其结果在VGA显示屏上显示出来。测试结果表明,整个系统能够实时准确地对单色背景下的某一物体进行跟踪。

In the paper,FPGA is used to construct the target tracking system to realize the recognition and tracking of an object in a monochromatic background.This design is composed of four modules:image acquisition module,image storage module,image processing module and image display module.The system uses OV5640 digital camera to collect image information,SDRAM to store image data,and then uses mean filtering algorithm to smooth the image,and then uses Sobel edge detection algorithm to process the target.The results are binarized,and then the bounding box technology is used to track the target.Finally,the results are displayed on the VGA display screen.The test results show that the whole system can track an object in a monochromatic background in real time and accurately.