Archive for the ‘Computer Vision’ Category

Matlab provides a great environment to work with images and therefore a great place to develop the Structured Light Algorithm.  The beagle board was used to project the structured light images and capture the resulting scene.  These images were then loaded into matlab providing data needed to develop the algorithm.  Working with Hana Wang and […]

Rendering results with Meshlab

Posted: 26th February 2012 by hackengineer in Computer Vision
Tags: , ,

Meshlab is pretty great for 3D point clouds and its free!  Here are a few steps that help really make the point clouds look good. Open Meshlab and open the .xyz file from the 3D camera Delete any points that look like they dont belong ( if you only see a small group of points […]

The source code is posted on google code.  You can download it straight from the interwebs with beagleboard.  Download the folder, run the Makefile, run ./slGPIO.cpp, and push the button to start scanning!  Once completed if the program finds a usbdrive it will save the point cloud there.  If not it will be saved in […]

The pushbutton allows the user to start a 3D scan by the push of a button, similar to how a real portable camera works.  I wasnt able to access the beagleboards user button with software, so I used a simple SPST switch and wired one side to GND and the other to GPIO 139.  I […]

Installing your camera module and ENV.txt

Posted: 26th February 2012 by hackengineer in Computer Vision
Tags: , ,

Setting up the Leopardboard 365 VGA Camera board is pretty straight forward.  Connect it to the beagleboards camera header.  Edit the UENV.TXT file with the following line.  If it does not exist create it in /media/mmcblk0p1/UENV.TXT camera=lbcmvga We also need to build a jig to mount the lens to the camera.  Since the lens uses a magnetism to adhere a metal washer will […]

The easiest way I found to get openCV up and running on the beagleboard was to build an image from scatch using the narcissus tool.  It works and it works really well in just a few steps. Select Beagleboard Select the Packages you want OpenCV – Libraries will be readily available to include in your […]

Structured Light vs Microsoft Kinect

Posted: 26th February 2012 by hackengineer in Computer Vision
Tags: , , ,

So why use Structured light?  Turns out there is a tradeoff between depth resolution vs refresh rate.  Structured light can provide lots of depth detail (dependent on camera/project resolution) but doesn’t work well with fast moving scenes.  Kinect, on the other hand, provides decent depth maps and can handle dynamic scenes.  So if you want […]

As part of my MEE program at Rice University I decided to take a Computer vision course that was centered largely around a course project.  I told the professor that I didnt want my project to be tied up with wires at some workstation, rather a completely mobile embedded system.  It added more work for me but […]