{"id":17358653,"url":"https://github.com/prouast/video-sensor-processing","last_synced_at":"2025-08-17T12:41:49.516Z","repository":{"id":50191035,"uuid":"237142574","full_name":"prouast/video-sensor-processing","owner":"prouast","description":"Import and processing of video sensor data for intake gesture recognition. Support for OREBA dataset.","archived":false,"fork":false,"pushed_at":"2020-10-01T23:37:13.000Z","size":54,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-08T15:49:29.675Z","etag":null,"topics":["intake-gesture-detection","opencv","oreba-dataset","tensorflow","tfrecord","video"],"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/prouast.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":"2020-01-30T05:02:01.000Z","updated_at":"2022-02-20T21:28:13.000Z","dependencies_parsed_at":"2022-09-05T15:20:34.889Z","dependency_job_id":null,"html_url":"https://github.com/prouast/video-sensor-processing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/prouast/video-sensor-processing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prouast%2Fvideo-sensor-processing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prouast%2Fvideo-sensor-processing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prouast%2Fvideo-sensor-processing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prouast%2Fvideo-sensor-processing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/prouast","download_url":"https://codeload.github.com/prouast/video-sensor-processing/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prouast%2Fvideo-sensor-processing/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268348611,"owners_count":24236297,"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","status":"online","status_checked_at":"2025-08-02T02:00:12.353Z","response_time":74,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["intake-gesture-detection","opencv","oreba-dataset","tensorflow","tfrecord","video"],"created_at":"2024-10-15T19:06:21.081Z","updated_at":"2025-08-02T07:31:22.047Z","avatar_url":"https://github.com/prouast.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# video-sensor-processing\n\nProcessing of video sensor data from the [OREBA dataset](http://www.newcastle.edu.au/oreba) for intake gesture detection.\nConvert video files and labels to `tfrecord` format.\n\n## Prepare data for TensorFlow\n\nWe use `.tfrecord` files to feed data into TensorFlow.\nThis includes [TV-L\u003csup\u003e1\u003c/sup\u003e optical flow](https://pequan.lip6.fr/~bereziat/cours/master/vision/papers/zach07.pdf), which is stored in the file alongside with raw frames and labels.\nA dependency due to optical flow calculation is [opencv](https://opencv.org).\n\n## Usage\n\nMake sure that all requirements are fulfilled\n\n```\n$ brew install opencv\n$ pip install -r requirements.txt\n```\n\nThen call `main.py`, pointing to the recordings directory for OREBA-DIS or OREBA-SHA.\n\n```\n$ python main.py --src_dir=OREBA_Dataset_Public_1_0/oreba_dis/recordings\n```\n\nThe following flags can be set:\n\n| Argument | Description | Default |\n| --- | --- | --- |\n| --src_dir | Recordings directory | OREBA_Dataset_Public_1_0/oreba_dis/recordings |\n| --exp_dir | Directory for data export | Export |\n| --dataset | Which dataset is used {OREBA-DIS or OREBA-SHA} | OREBA-DIS |\n| --label_spec | Filename of label specification | label_spec/OREBA_only_intake.xml |\n| --label_spec_inherit | Inherit label specification for sublabels (if label not included, always keep sublabels as Idle) | True |\n| --resolution | Resolution of the video {140p or 250p} | 140p |\n| --exp_fps | Store video frames using this framerate (In fps; Should be able to divide original framerate by this) | 8 |\n| --exp_optical_flow | Calculate optical flow | False |\n| --organise_data | If True, organise data in train, valid, test subfolders | False |\n| --organise_dir | Directory to copy train, val and test sets using data organiser | Organised |\n| --organise_subfolders | Create sub folder per each file in validation and test set | False |\n\n## Label specfication\n\nControl what labels are included by selecting or editing the appropriate `label_spec` file.\nTemplates are available in the `label_spec` directory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprouast%2Fvideo-sensor-processing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprouast%2Fvideo-sensor-processing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprouast%2Fvideo-sensor-processing/lists"}