Mindboards

I came across this Raspberry Pi Camera. The board itself is tiny, at around 36mm x 36mm. The highlight of our module is that the Lens is replaceable compared to official one, making it perfect for mobile or other applications where size and image quality are important. The camera is supported in the latest version of Raspbian, Raspberry Pi’s preferred operating system.



It connects to Raspberry Pi by way of a short ribbon cable. The camera is connected to the BCM2835 processor on the Pi via the CSI bus, a higher bandwidth link which carries pixel data from the camera back to the processor. This bus travels along the ribbon cable that attaches the camera board to the Pi.



The sensor itself has a native resolution of 5 megapixel, and has a fixed focus lens onboard. In terms of still images, the camera is capable of 2592 x 1944 pixel static images, and also supports 1080p30, 720p60 and 640x480p60/90 video.



I have ordered one myself and am looking forward to wrapping my little pinkies around it....

Full details available here: Raspberry Pi Camera Board with CS Mount Lens

is there any image processing like BLOB color detection, shape detection, movement detection ?
(e.g., like POBeye or like formerly Lego Mindstorms Vision Command ?)

The camera board itself doesn't support image processing, but you can use the RPi to process the information. For movement detection, there's a program called "motion" (I think it's specifically for the RPi) that you could look into using. You could probably find more specific helpful information by searching Google.

I actually assumed I could get more specific information in this specific RPI-related forum

Hi doc-helmut,

I have ordered one of these camera to use with my Pi's. Initially I will be relying on a lot of 'Google-ing' I image. That said, listed below is some data from the raspberrypi.org website which may be of interest.

As mattallen37 states, all the 'Robotics Related Image' processing is software driven from the Raspberry Pi. You will need to code your own specific Visual System to suite your requirements. There are a number of OpenSource Image processing engines to choose from on the Linux platform that will run on the Pi.

1. What is the Camera Board?

The Camera Board is a small PCB that connects to the CSI-2 camera port on the Raspberry Pi using a short ribbon cable. It provides connectivity for a camera capable of capturing still images or video recordings. The camera connects to the Image System Pipeline (ISP) in the Raspberry Pi’s SoC, where the incoming camera data is processed and eventually converted to an image or video on the SD card (or other storage).

2. What model camera does the camera board use?

The camera module is an Omnivision 5647. It comparable to cameras used in mobile phones.

3. What resolutions are supported?

The camera module is capable of up taking photos up to 5 MegaPixels (5MP) (2592×1944 pixels) and can record video at resolutions up to 1080p30 (1920x1080x30fps).

4. What picture formats are supported?

The camera module supports raw capturing (Bayer data direct from the sensor) or encoding as JPEG, PNG, GIF and BMP, uncompressed YUV, or uncompressed RGB photos. It can record video as H.264, baseline, main or high-profile formats.

5. How do I use the camera?

There are three command line applications provided for stills, video, and stills output uncompressed. These applications provide the typical features you might find on a compact cameras, e.g. Set image size, compression quality, exposure mode, ISO. See the documentation located on the Technical Documents Page for more details.

6. Can I extend the ribbon cable?

Yes, people have used cables up to 4 meters and still received acceptable images, though your mileage may vary.

7. Can I have a camera with more MP’s?

No, this is the only camera module that is compatible with the Raspberry Pi. There are currently no plans to release a higher-resolution sensor in the future either.

8. How much power does the camera module use?

The camera board requires 250mA to operate. Make sure you ensure your power supply can provide enough power for the camera module as well as the Raspberry Pi, and any peripherials directly attached to the Raspberry Pi.

I trust that this maybe of assistance.

You will need to code your own specific Visual System to suite your requirements.

ok, thanks, but if there isn't anything already available out of the box like "recognize a X-shape" or "recognize a red O-shape" or "recognize all 16 color patterns on a 4x4 Rubik's cube face" then it's not what I'm looking for.
For the shape patterns it must be able to simply take a picture of a specimen pattern and then say "search for any matching pattern in different sizes at different distances" (the way it's been demonstated for the POB-eye cam)
and for the 16 blobs one would simply need to specify the 16 regions referring to their location on a cube face (somehow it once worked by Vision Command or like David Gilday did it for his cubesolvers by a smartphone cam).

Hi doc-helmut,

It's early days for the Pi Camera.

I suggest that by visiting the themagpi.com and downloading the later copies of 'The MagPi' magazine, where you will find articles on using the Pi Camera.

Issue 17 has a nice article on the BrickPi. Also there is a CameraPi articles as well.

The book, 'The Definitive Guide to Building Robots with JAVA Brains', has several chapters on Robot Vision, which would be a good starting point for you. I found an eBook version, prior to getting my hard copy, Although it appear the book is a good investment as I think I only paid $5 for my copy new.

thanks, but Java is no option for me, just C with a simple, logical, and convenient API.
A cam for my purposes must have all image processing and object-detecting routines on-board.

hi,
now there is such a cam availbale, for Arduinos and probably also for Rasperry Pi:

https://www.kickstarter.com/projects/25 ... nav_search

http://www.adafruit.com/product/1906

http://www.cmucam.org/projects/cmucam5/ ... _an_object