Hi Giacomo,
what part of the UAV use-case would you like to have.
1. We have developed a simple avoidance algorithm, which takes a disparity map as input and computes an evasion maneuvre for the UAV (
https://www.youtube.com/watch?v=pMDMTUCVwKc). This was developed in C/C++ and runs on the CPU.
2. The main part of the use case, however, was the development of a disparity estimation algorithm based on the SGM algorithm. It is optimized and synthesized to run on the FPGA of the Zynq Ultrascale+. We have two version of the algorithm which are essentially equal. They only differ in the input data. One reads images from the SD Card and processes them to compute a disparity map (
https://www.youtube.com/watch?v=gzIFqUmqM7g&t=3s). The second one uses a stereo camera system as input, which is connected via CameraLink (
https://www.youtube.com/watch?v=ZnfNLrXWkIM). The IP, which is responsible for capturing images from the camera might be protected. I would need to confirm with our partner if you are interested.
However, the disparity estimation algorithm is the same for both versions.
Best Regards,
Boitumelo