A CPU based video summarization and classification tool. Extracts every movement out of a given video, aggregates the extracted changes into movement layers, which can be exported or further analysed and classified..

Go to file

Askill 90c07016fe continued contoured extraction TODO: fix rendering		2020-11-28 11:03:24 +01:00
.vscode	contours are getting extracted	2020-09-22 20:25:06 +02:00
Application	continued contoured extraction	2020-11-28 11:03:24 +01:00
generate test footage	fixed layer.add()	2020-11-08 16:28:47 +01:00
.gitignore	merging layers	2020-11-12 18:59:57 +01:00
README.md	Update README.md	2020-11-18 16:28:16 +01:00
main.py	continued contoured extraction	2020-11-28 11:03:24 +01:00
ueberblick.drawio.png	started contoured diff instaed of rect	2020-11-27 01:06:25 +01:00
ueberblick.png	added doc and kap.py	2020-11-05 23:17:05 +01:00

README.md

wip

notes:

Time consumed reading video: 369.0188868045807s 3.06GB 26min 1080p downscaled 500p 30fps Time consumed reading video: 240.s 3.06GB 26min 1080p downscaled 500p 30fps when multithreaded contour extraction: 10.5 Sec. when only 2 Threads 8 secs when also mapping getContours()

install tensorflow==1.15.0 and tensorflow-gpu==1.15.0, cuda 10.2 and 10.0, copy missing files from 10.0 to 10.2, restart computer, set maximum vram