The quarter is ending and so is my current work on AudioVision. I have successfully managed to convert a basic two camera view into stereophonic 3d audio, using OpenCV (C++). I hope to continue this work some time in the future, so keep an eye out here for any future developments.
I submitted “Graffiti” for the End challenge at DPChallenge. I cam in 94 out of 145 with a score of 4.74 / 10. I think I may have over done the contrast on the shot, but it still turned out to be pretty interesting.
WARNING IMAGE 3251607843 COULD NOT BE FOUND
A collection of random photos taken at the house in Terre Haute.
I submitted “Lonely Winter Night” for the Silence II challenge at DPChallenge. I came in 110 out of 177 with a score of 4.96 / 10. So far this is my best result at DPChallenge. I think that I may have over done the softening on the shot, but I still think it was a cool effect.
WARNING IMAGE 3232537411 COULD NOT BE FOUND
The first real snowfall of the year for Terre Haute. I looked out around 9:30 and it was too nice out not to take pictures.
Since deciding that I cannot use MATLAB because of the additional addons necessary to use webcams, I have been deciding between C# and Python as the next language to try. I’ve settled on Python for the time being, using VideoCapture to connect to the webcams and Numpy to process the data. It turns out that Python + VideoCapture + Numpy is actually rather similar in functionality and syntax to MATLAB with its image processing library.
I submitted “Natural 20” for the Lucky challenge at DPChallenge. I came in 66 out of 85 with a score of 4.41 / 10. In 20⁄20 hindsight, I probably should have submitted the other version of that shot. Oh well.
WARNING IMAGE 3175155980 COULD NOT BE FOUND
I submitted “Can You See?” for the Transparency III challenge at DPChallenge. I came in 116 out of 152 with a score of 4.64 / 10. I hope to do better in the next competition.
WARNING IMAGE 3145238635 COULD NOT BE FOUND
Shots of dice in black and white. There’s really not much more to say than that.
The original plan to use Make3D for the visual depth determination has mostly fallen through, partially because it has several dependencies that I cannot get to build correctly and partially because it is written in a combination of C and MATLAB. I have nothing against either of these languages; however, I do not have the addons necessary for MATLAB to connect to a webcam.
As such, I’ve decided to switch from a monocular vision algorithm to a more traditional stereo vision algorithm.