{"id":13613581,"url":"https://github.com/Eyevinn/autovmaf-preprocessing","last_synced_at":"2025-04-13T15:33:17.429Z","repository":{"id":45685317,"uuid":"513837907","full_name":"Eyevinn/autovmaf-preprocessing","owner":"Eyevinn","description":" Tool that analyses a video via a combination of motion and sharpness to determine the most suitable parts to be used for VMAF analysis. https://github.com/Eyevinn/autovmaf","archived":false,"fork":false,"pushed_at":"2022-09-02T19:05:22.000Z","size":485,"stargazers_count":7,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T14:04:04.656Z","etag":null,"topics":["opencv","tools","video-processing","vmaf"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Eyevinn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-07-14T09:27:03.000Z","updated_at":"2023-05-17T08:45:12.000Z","dependencies_parsed_at":"2023-01-17T19:45:13.223Z","dependency_job_id":null,"html_url":"https://github.com/Eyevinn/autovmaf-preprocessing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eyevinn%2Fautovmaf-preprocessing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eyevinn%2Fautovmaf-preprocessing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eyevinn%2Fautovmaf-preprocessing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eyevinn%2Fautovmaf-preprocessing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Eyevinn","download_url":"https://codeload.github.com/Eyevinn/autovmaf-preprocessing/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248736235,"owners_count":21153556,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["opencv","tools","video-processing","vmaf"],"created_at":"2024-08-01T20:00:50.984Z","updated_at":"2025-04-13T15:33:16.720Z","avatar_url":"https://github.com/Eyevinn.png","language":"Python","funding_links":[],"categories":["HarmonyOS"],"sub_categories":["Windows Manager"],"readme":"# AutoVMAF Preprocessing\n\nPython script that analyzes a video (local file or hls-stream) via a combination of motion and sharpness to determine the most suitable section to be used for VMAF analysis.\n\nThe output is a time-code of the frame that contains the most motion and finer details. This can for example be confetti, particles, tree leaves, etc.\n\nExample of a processed frame:\nThe tool converts motion pixels to white and everything else to black pixels.\nThe percentage of white pixels in the frame and the overall sharpness of the original frame (how much that is in focus) is then calculated per frame and then compared to the next frame and so on.\n\n## Installation\n\nThe tool has a dependency on openCV for python, which should be installed using `pip` (or possibly `pip3` or similar): \n\n`pip3 install opencv-python`\n\n\n## Usage\n\nExample:\n\n```python\nfrom .src.analyze import video_analyzer\n\nthreshold = 4 # Motion threshold (higher = more motion required) (default: 25 max: 255)\ntimecode = video_analyzer(file_path=\"video.mp4\", threshold=threshold)\n\nprint(timecode) # HH:MM:SS:FF\n\n# To run the script with the debug option to show the processed frames:\ntimecode = video_analyzer(file_path=\"video.mp4\", threshold=threshold, debug_video=True)\n\nprint(timecode) # HH:MM:SS:FF\n```\n\nAn example CLI have also been provided that prints the timecode to the console.\n\n```text\nusage: cli.py [-h] [-f FILE] [-d] [-t THRESHOLD]\n\nrequired arguments:\n  -f FILE, --file FILE  path to the video file\n\noptional arguments:\n  -d, --debug           show the current processed frame\n  -t THRESHOLD, --threshold THRESHOLD\n                        threshold for motion detection, default: 25 max: 255\n```\n\nExample:\n\n```bash\npython cli.py -f video.mp4 -t 4\n\n# To run the script with the debug option to show the processed frames:\npython cli.py -f video.mp4 -t 4 -d\n```\n\n## About Eyevinn Technology\n\nEyevinn Technology is an independent consultant firm specialized in video and streaming. Independent in a way that we are not commercially tied to any platform or technology vendor.\n\nAt Eyevinn, every software developer consultant has a dedicated budget reserved for open source development and contribution to the open source community. This give us room for innovation, team building and personal competence development. And also gives us as a company a way to contribute back to the open source community.\n\nWant to know more about Eyevinn and how it is to work here. Contact us at work@eyevinn.se!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEyevinn%2Fautovmaf-preprocessing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEyevinn%2Fautovmaf-preprocessing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEyevinn%2Fautovmaf-preprocessing/lists"}