Omnivision Module V3: Difference between revisions
No edit summary |
|||
| (2 intermediate revisions by the same user not shown) | |||
| Line 4: | Line 4: | ||
* compatible with Pi-puck and interfaced with the Raspberry Pi Zero W | * compatible with Pi-puck and interfaced with the Raspberry Pi Zero W | ||
* parabolic mirror for uniform pixel distribution | * parabolic mirror for uniform pixel distribution | ||
* suitable for basic image processing such as blobs, colors and light detection. | |||
=Image grabbing= | =Image grabbing= | ||
| Line 11: | Line 12: | ||
=Image unwrapping= | =Image unwrapping= | ||
<span class="plainlinks">[ | <span class="plainlinks">[https://projects.gctronic.com/epuck2/wiki_images/omni3-img-unwrap.jpg <img width=800 src="https://projects.gctronic.com/epuck2/wiki_images/omni3-img-unwrap-small.jpg">]</span><br/> | ||
=OpenCV= | =OpenCV= | ||
Latest revision as of 07:52, 29 September 2021
Overview
Features:
- 5Mpixel color camera looking 360° all around the robot
- compatible with Pi-puck and interfaced with the Raspberry Pi Zero W
- parabolic mirror for uniform pixel distribution
- suitable for basic image processing such as blobs, colors and light detection.
Image grabbing
You can use raspistill to grab an image with the command: raspistill -t 0 -k -o image.jpg.
This command open a live preview of the camera. When you press ENTER, an image is grabbed. To terminate press x+ENTER.
You can find detailed documentation about raspistill in the following link https://www.raspberrypi.org/documentation/raspbian/applications/camera.md.
Image unwrapping
OpenCV
Blob tracking
A simple demo was developed to track an orange blob. It is thought to be run with the omnivision extension. The robot rotate in place towards the target when it finds one.
The code can be downloaded from the following repo: git clone https://github.com/e-puck2/e-puck2_pi_blob-tracking.git
Refer to the github page for information about building and running this demo.
This example is available in the system in the directory /home/pi/e-puck2_pi_blob-tracking.
This directory includes a simple launch script for the demo that can be run with the command ./omni_detect_blob.sh; the color parameters given are supposed to follow a pink object.
Beware that this directory isn't garanted to be synced with the last repository version, thus to get the last version use git pull and then rebuild.