Peter Abeles is a researcher in computer vision and mobile robotics. He is currently an independent consultant and entrepreneur working to bring the latest technologies out of R&D and into commercial products. A strong supporter of open source development, he maintains and develops several projects of his own. Over the past 12 years, he worked on and led numerous projects while at Intelligent Automation Inc, Lockheed Martin, and Carnegie Mellon University . His most recent work has included various SBIR and DARPA BAA projects with a focus on localization and mapping technologies using a variety of different modalities, e.g. visual, LADAR, IR, GPS, and satellite tracking.
In addition to his professional work, he is an avid kayaker and spends many of his weekends on the water. Other active hobbies include snow boarding, drawing, hiking, cooking, traveling and swing dancing. Recently became certified as a wilderness first responder and taken swift water rescue classes.
Hi Peter,
My name is Robert and I have come across your “video mosaic” page created through BoofCV and I am interested to learn more.
I am new to CV as my background is geology. I have an idea that I would like to implement video mosaicing to what I do in the mines. I have developed my own 360 camera and use it for investigations and site surveys. I find that this is lacking what I want and I would like to somehow create linear panorama’s or video mosaics of mining environments. Would this be of interest to you in helping me?
I look forward to your response.
Kindest regards
Robert
Hi Robert,
I appreciate your engagement and efforts in boofCV very much. I would like to use boofCV in a little project and came up with this question: I have 4 points in a 2D (source-)image that build up an arbitrary convex(!) shape. I would like to warp the image, such that the 4 points constitute a perfect rectangle with known width/height centered in the middle of the (destination-)image. My idea is to take the 8 known points and to compute a homography matrix H, such that p1 = H*p2. Can this be done using the computeFundamental methods of boofCV? If yes, how does the homography matrix relate to the fundamental matrix? (Also found this one on my googling journey, which I find very useful: http://www.youtube.com/watch?feature=endscreen&v=fVJeJMWZcq8&NR=1).
It would be very nice if you could take some of your precious time to answer this silly question of mine.
Thanks in advance
Hendrik
(Sorry for the bad english)
Hi Hendrik,
BoofCV does come with a function for computing the homography directly, see FactoryMultiView.computeHomography(). Technically you could use a fundamental matrix instead, but it would require more work and be less reliable. There are a few more steps left..
For BoofCV releated questions could you post to the discussion board instead of posting here?
https://groups.google.com/forum/?fromgroups#!forum/boofcv
Tried your Boof Demo app. Calibration doesn’t work.
Can I email you a Screenshot and describe the problem?