This is a standalone, all in one Edge Detector that is mainly running on GPU using the CUDA technology. Each algorithm also has an OpenCV counterpart which is the closest one in terms of speed.
This project is partly based on the Sobel Filter sample available as part of the CUDA SDK.
This project also partly uses the OpenCV library to load different types of image.
This program includes: Prewitt filter, Roberts Cross, Canny edge detector and finally Sobel filter with the ability to modify some variables such as sigma in Canny and see the result in real-time.
To access and download the code, please review the code section. (The code section is currently close until our article gets published)
Commiting publicly to the project is currently closed but feel free to email us.
The source code is dependant on CUDA 5.0 Samples now available as part of the CUDA Toolkit.
"This software contains source code provided by NVIDIA Corporation."
- All-in-one edge detector
- Implemented on GPU using CUDA to be fast
- Live output of each filter with the ability to change between filters
- Change all the variables like threshold and sigma in Canny and brightness and immediately see the result
- Load any input image
Be the first to post a review of GPU Edge Detector!