Open
Conversation
Wsl connect, also added self-calibration for hough circle params
added Z's stackImg function to better organize the imgages, used the …
… main, then pull main on the jetson
minor adjustments, switching branch
added a script to test camera recording on the jetson, gonna merge to…
… record video. The resulting recording could not be read by mpv, mplayer, or opencv (these video players have been tested on another video). As a hotfix, the file saves each individual frame as a seperate png, this is horribly inefficient because it sums up to 1 mb per png. this will make data aquisition harder, should fix later
…s, which can iether be jpg or png are compiled into an mp4 which has a unique name based on the dateTime (so it wont replace any other videos when saving), after the video has compiled, the frames, which are no longer needed, are deleted. For 200 frames. With frmDiv=2, it skips every other frame to reduce filesize, as a result, it would record at ~16-20 fps, a resulting 10s video compiled from pngs would be ~400kb. for a 1-minute vid, it would be frmLim=1200, and its size would be 2.4mb. (keep in mind this is tested on my webcam, and not on the actual submarine camera)
…the smaller file size. A ~4 minute video is ~13.5mb for png and ~17.5mb for jpgs. Also considering implementing the use of command line arguments to change vidlength on the fly. Still getting the weird glitch where the first recorded frame is momentarily displayed at a given interval
Richard/cam integration
…ith camera plugged into theo otgg sockett, camNum=2, still need to test using the orbitty and using the usb hub
…ch to v4ls recording for usb camera using gstreamer
… recording is possible using gstreamer pipeline 1 after installing canberra, and using the MFPG format for the videowriter, a 10s vid is ~6.5mb.VIdeos are recording at 30fs, but frame division might still be viable for stretching them out. Still need to implement command line arguments for ease of use
…diffMat was formed such that the outline of the baloon is left intact after the inside part is gone; used the np.where() function, it seems that redmax does not work on clear video, only murky water in which there is a clear blue or green shade, tested with mountain dew bottle. Added RedMax V2 in which works with HSV instead of BGR; v2 creates a percentile mask based on the Hue matrix of the frame, the results seem to be very noisy and unclear compared to the original RedMax, but it is still an early version
…ith redmax but results were lackluster
…ent it into the DragonVision prototype, tensorflow is installed in the base env
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.