Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
N
NINA Thesis
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Leonardo de Lima Gaspar
NINA Thesis
Repository graph
Repository graph
You can move around the graph by using the arrow keys.
main
Select Git revision
Branches
7
HoG_implementation
OpenCV_CMake_test
ViBe
addCuttingVideo
csv-timeformat-changer
main
default
protected
test
7 results
Begin with the selected commit
Created with Raphaël 2.2.0
15
Mar
14
1
28
Feb
24
23
21
20
18
17
16
15
10
8
7
4
3
16
Jan
14
11
Structured files that were merged, and corrected ground truth formats.
main
main
merging addCuttingVideo
HoG_implementat…
HoG_implementation
Added functionality to dataset generator; now works with multiple videos, and extracts a given percentage per video.
addCuttingVideo
addCuttingVideo
Replacing old files in new HoG branch.
Restructured for python utilities package, and made standalone utility to generate labelled dataset that can easily be fed into keras later.
added ground truth folder and files
Fixed .csv reading, now correctly finds ground truth in input folder if it exists. Changed notation to 'groundTruth_[file]'
added code and example files for converting from hr.min.sec to only sec
csv-timeformat-…
csv-timeformat-changer
added .venv to gitignore
Removed cout's
Fixed writing to csv; issue was caused by out of bounds array in dilation logic.
Testing OR instead of XOR for change detection.
Fully functional Jaccard index/similary score complete. Will now look for ground truth file at end of computation, with name groundTruth[videoFile].csv, and calculate score. Note that the trimming functionality is commented out for faster testing of model.
wat
Cleaned up some code and csv reading logic. Should work as standalone.
added a groundTruth file
added .venv to gitignore
Adding CMakeLitst.txt to gititnore
added CMakeLists.txt to gitignore
Casted output to csv to int.
Removed comment, reworded error.
Cleaned up main a little.
Connected the Python parts that retrieve the generated .csv and trim the video based on the timestamps. Haven't been able to test, but it should work as a complete MVP. Have yet to add the optional success rate calculation functionality if there is a ground truth to compare to.
CSV file get's named after video input file
Merge branch 'addCuttingVideo' of https://git.gvk.idi.ntnu.no/LeoDLG/nina-thesis into addCuttingVideo
added csv writer
Python module that calls video processing executable via shell. Works fine, might need to add config files for more flexible/dynamic path, as it now looks in a static directory with no condition guarding.
Merged cpp and python modules, finished dynamic binary of timestamp generator; can be called with video file as argument. Need to stitch together with other parts for functioning MVP.
Update README.md
Merge branch 'OpenCV_CMake_test'
Merge branch 'ViBe'
added gitignore
Folder restructure
OpenCV_CMake_test
OpenCV_CMake_test
Restructure of folders
ViBe
ViBe
Added gitignore
Implemented frame change detection, and timestamp generation based on that output. Current parameters seem to work decently well, but still significant gaps from ground truth comparison.
Trying again
Clean up debug build from git.
Got opencv::bgsegm to work and build to binary; Added bg segmentation functionality. Also added thresholding to determine motion, and saving simulated timestamps. Still need to convert to real time, add interval logic, and finally export to CSV.
Got opencv::bgsegm to work and build to binary; Added bg segmentation functionality. Also added thresholding to determine motion, and saving simulated timestamps. Still need to convert to real time, add interval logic, and finally export to CSV.
Loading