Dear all,
is it possible to obtain sources of UAV use-case? We would like to analyze it to evaluate TULIPP board for another european project that just started. It is called FITOPTIVIS.
Giacomo
Sources of UAV use-case
- Flemming_Christensen
- Posts: 278
- Joined: Thu Jun 09, 2016 11:50 am
- Location: Chesham
- Contact:
Re: Sources of UAV use-case
Hi,
We have two 'demos' for UAV application.
A simple one that was developed for fun = https://www.youtube.com/watch?v=pMDMTUCVwKc [I shall ask if we can provide sources]
The REAL one by Fraunhofer = https://www.youtube.com/watch?v=ZnfNLrXWkIM [Some of the IP is protected, but shall get FHG to confirm what they can share]
Thanks for interest.
Flemming
We have two 'demos' for UAV application.
A simple one that was developed for fun = https://www.youtube.com/watch?v=pMDMTUCVwKc [I shall ask if we can provide sources]
The REAL one by Fraunhofer = https://www.youtube.com/watch?v=ZnfNLrXWkIM [Some of the IP is protected, but shall get FHG to confirm what they can share]
Thanks for interest.
Flemming
-
- Posts: 61
- Joined: Thu Jun 09, 2016 4:28 pm
Re: Sources of UAV use-case
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
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
Return to “FAQ about Tulipp Development Platform”
Who is online
Users browsing this forum: No registered users and 0 guests