fivepoint-pynq 1.0

This project provides overlay and notebooks to run a websocket-based 5-point relative pose application. It requires PYNQ version 2.5.1 and above to work.

The purpose of this application is to identify the possible relative camera motions given five matching points from two calibrated views.

This is a porting of the project by the NECSTLab at Politecnico di Milano that won the Xilinx European Open Hardware Design Contest in 2018, for the AWS EC2 F1 Category.

More info on the project can be found at the following links:

• Project website
• PDF report
• YouTube presentation
• Open Hardware 2018 winners & finalists

Refer to the README in the overlay folder for more information regarding the used overlay and how it is created.

Please notice that the distributed overlay might not be available for all target devices. Supported devices are listed in the overlays README. There you may also find instructions on how to synthesize and use overlays for a different device.

Quick Start

Install the fivepoint-pynq package using pip:

pip install fivepoint-pynq

After the package is installed, to get your own copy of all the notebooks available run:

pynq get-notebooks 5point

You can try things out by running:

cd pynq-notebooks
jupyter notebook

There are a number of additional options for the pynq get-notebooks command, you can list them by typing

pynq get-notebooks --help

You can also refer to the official PYNQ documentation for more information regarding the PYNQ Command Line Interface and in particular the get-notebooks command.

Licenses

5point-PYNQ: Apache License 2.0

Xilinx Open Hardware 2018 - 5 Points to Rule Them All: MIT License (3d-party component)