Edge Detection System in Real-Time

Overview

A 2MP camera is used by this project where an image stream is continuously captured with a VGA monitor used to display the real-time edge detection performed on an FPGA.

Details

In image processing and computer vision, edge detection uses algorithms at identifying points in a digital image where the image brightness changes sharply. To divide an image into areas corresponding to different objects, edge detection is extensively used in image segmentation. The edges often represent object boundaries and occur in parts of the image with strong intensity contrast. Since edge detection is computationally less expensive and often yields better results, it is commonly performed in the spatial domain. By applying high pass frequency filter in the Fourier domain or by convolving the image with an appropriate kernel in the spatial domain, edges can be detected.

Through a 2MP CMOS image sensor, the DE2 camera module captures the image where the raw image data is converted into an RGB color space. To obtain the image intensity for edge detection, the image will be converted to grayscale. The grayscale image is stored in the SDRAM FIFO and mirrored to be displayed properly on the VGA.