askill
/
Video-Summary
mirror of https://github.com/Askill/Video-Summary.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Patrice Matz 2022-10-06 10:30:25 +02:00 committed by GitHub
parent 31731f2dc3
commit ee535ccb4c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@ -28,20 +28,21 @@ On my configuration 1 minutes of of the original Video can be processed in about
./Application/Config.py ./Application/Config.py
"min_area": 100, min area in pixels "min_area": 100, min area in pixels, of a single contour, smaller is ignored
"max_area": 9000000, max area in pixels "max_area": 9000000, max area in pixels, of a single contour, larger is ignored
"threashold": 6, luminance difference threashold "threashold": 6, luminance difference threashold, sensitivity of movement detection
"resizeWidth": 1000, video is scaled down internally "resizeWidth": 600, video is scaled down internally
"inputPath": None, overwritten in main.py "inputPath": None, overwritten in main.py
"outputPath": None, overwritten in main.py "outputPath": None, overwritten in main.py
"maxLayerLength": 5000, max langth of Layer "maxLayerLength": 5000, max length of Layer in frames
"minLayerLength": 10, min langth of Layer "minLayerLength": 10, min length of Layer in frames
"tolerance": 100, max distance between contours to be aggragated into layer "tolerance": 100, max distance (in pixels) between contours to be aggragated into layer
"maxLength": None, "maxLength": None,
"ttolerance": 60, number of frames movement can be apart until a new layer is created "ttolerance": 60, number of frames movement can be apart until a new layer is created
"videoBufferLength": 100, Buffer Length of Video Reader Componenent "videoBufferLength": 100, Buffer Length of Video Reader Componenent
"LayersPerContour": 220, number of layers a single contour can belong to "LayersPerContour": 2, number of layers a single contour can belong to
"avgNum": 10, number of images that should be averaged before calculating the difference "avgNum": 10, number of images that should be averaged before calculating the difference
(computationally expensive, needed in outdoor scenarios due to clouds, leaves moving in the wind ...)
### notes: ### notes: