waldo-vision / optical.flow.demo

A project that uses optical flow and machine learning to detect aimhacking in video clips.
https://www.waldo.vision
Mozilla Public License 2.0
536 stars 24 forks source link

Added a barebones GUI file selector #21

Open hilletc7 opened 2 years ago

hilletc7 commented 2 years ago

Just wanted to get the ball rolling with the GUI file selector. You mentioned that you wanted to eventually replace it in response the issue #16. I included here; it's pretty basic but it gets the job done.

I also was getting a error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor' when running "farnebackOpticalFlow.py" so I went ahead a made some tweaks to fix the error.

Hope this helps.

hilletc7 commented 2 years ago

Quick update, I saw CaptnBaguette post about the premade CNN yolov3 in the data-classification channel so I went ahead a made a simple example in a separate directory.

hilletc7 commented 2 years ago

I also removed the yolov3 code to decrease clutter.

I originally included it here since the repo was pretty bare and I didn't know where else to put it. If you want to see it, it now has a home in "video.analysis"