{"id":23533171,"url":"https://github.com/sphamba/trainguide","last_synced_at":"2025-05-14T16:34:51.613Z","repository":{"id":264396413,"uuid":"316928004","full_name":"sphamba/TrainGuide","owner":"sphamba","description":"Mobile ML model to detect door buttons on Swiss trains","archived":false,"fork":false,"pushed_at":"2020-11-29T12:11:09.000Z","size":40841,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-17T05:11:21.404Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sphamba.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-11-29T10:40:34.000Z","updated_at":"2023-11-24T14:00:00.000Z","dependencies_parsed_at":"2024-11-24T00:36:06.303Z","dependency_job_id":null,"html_url":"https://github.com/sphamba/TrainGuide","commit_stats":null,"previous_names":["sphamba/trainguide"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sphamba%2FTrainGuide","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sphamba%2FTrainGuide/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sphamba%2FTrainGuide/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sphamba%2FTrainGuide/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sphamba","download_url":"https://codeload.github.com/sphamba/TrainGuide/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254183485,"owners_count":22028502,"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":[],"created_at":"2024-12-25T23:14:27.401Z","updated_at":"2025-05-14T16:34:51.593Z","avatar_url":"https://github.com/sphamba.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TrainGuide\r\n\r\nAn object detector model is used to find the handle/button of a train door and guidance for blind people is provided by sound cues.\r\n\r\n## Model training\r\n\r\nWe opted for a MobileNet V2 of 320x320 for its relatively high speed, in order to reach real-time performances on mobile devices. The directory `model` contains Notebooks to train a model in Tensorflow from a pre-trained model found on the _TensorFlow 2 Detection Model Zoo_. A script is then used to convert the exported model for use with Tensorflow JS in a web browser.\r\n\r\n## WebApp\r\n\r\nThe trained model is used on a real time video captured from the device camera to find the positions of doors (closed or opened), buttons and handles.\r\n[...]\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsphamba%2Ftrainguide","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsphamba%2Ftrainguide","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsphamba%2Ftrainguide/lists"}