{"id":17116960,"url":"https://github.com/taufeeque9/humanfalldetection","last_synced_at":"2025-04-03T09:08:28.453Z","repository":{"id":45552808,"uuid":"255925792","full_name":"taufeeque9/HumanFallDetection","owner":"taufeeque9","description":"Real-time, Multi-person \u0026 Multi-camera Fall Detector in Python","archived":false,"fork":false,"pushed_at":"2024-09-29T18:01:51.000Z","size":537015,"stargazers_count":272,"open_issues_count":10,"forks_count":64,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-03-27T07:11:14.145Z","etag":null,"topics":["deep-learning","fall-detection","human-pose-estimation","long-short-term-memory","lstm","multiple-cameras","neural-networks","python3-fall-detector","video-processing"],"latest_commit_sha":null,"homepage":"","language":"Python","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/taufeeque9.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":"2020-04-15T13:30:40.000Z","updated_at":"2025-03-21T08:37:58.000Z","dependencies_parsed_at":"2024-10-30T03:33:42.480Z","dependency_job_id":null,"html_url":"https://github.com/taufeeque9/HumanFallDetection","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/taufeeque9%2FHumanFallDetection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taufeeque9%2FHumanFallDetection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taufeeque9%2FHumanFallDetection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taufeeque9%2FHumanFallDetection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/taufeeque9","download_url":"https://codeload.github.com/taufeeque9/HumanFallDetection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246970318,"owners_count":20862509,"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":["deep-learning","fall-detection","human-pose-estimation","long-short-term-memory","lstm","multiple-cameras","neural-networks","python3-fall-detector","video-processing"],"created_at":"2024-10-14T17:50:02.692Z","updated_at":"2025-04-03T09:08:28.413Z","avatar_url":"https://github.com/taufeeque9.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HumanFallDetection\nWe augment human pose estimation\n(openpifpaf library) by support for multi-camera and multi-person tracking and a long short-term memory (LSTM)\nneural network to predict two classes: “Fall” or “No Fall”. From the poses, we extract five temporal and spatial\nfeatures which are processed by an LSTM classifier.\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"examples/fall.gif\" width=\"420\" /\u003e\n\u003c/p\u003e\n\n## Setup\n\n```shell script\npip install -r requirements.txt\n```\n\n## Usage\n```shell script\npython3 fall_detector.py\n```\n\u003cTABLE\u003e\n\u003cTR\u003e\u003cTH style=\"width:120px\"\u003eArgument\u003c/TH\u003e\u003cTH style=\"width:300px\"\u003eDescription\u003c/TH\u003e\u003cTH\u003eDefault\u003c/TH\u003e\u003c/TR\u003e\n\u003cTR\u003e\u003cTD\u003enum_cams\u003c/TD\u003e \u003cTD\u003eNumber of Cameras/Videos to process\u003c/TD\u003e\u003cTD\u003e1\u003c/TD\u003e\u003c/TR\u003e\n\u003cTR\u003e\u003cTD\u003evideo\u003c/TD\u003e\u003cTD\u003ePath to the video file (None to capture live video from camera(s)) \u003cbr\u003eFor single video fall\n                        detection(--num_cams=1), save your videos as abc.xyz\n                        and set --video=abc.xyz\u003cbr\u003e For 2 video fall\n                        detection(--num_cams=2), save your videos as abc1.xyz\n                        \u0026 abc2.xyz \u0026 set --video=abc.xyz\u003c/TD\u003e\u003cTD\u003eNone\u003c/TD\u003e\u003c/TR\u003e\n\u003cTR\u003e\u003cTD\u003esave_output\u003c/TD\u003e \u003cTD\u003eSave the result in a video file. Output videos are\n                        saved in the same directory as input videos with \"out\"\n                        appended at the start of the title\u003c/TD\u003e\u003cTD\u003eFalse\u003c/TD\u003e\u003c/TR\u003e\n\u003cTR\u003e\u003cTD\u003edisable_cuda\u003c/TD\u003e \u003cTD\u003eTo process frames on CPU by disabling CUDA support on GPU\u003c/TD\u003e\u003cTD\u003eFalse\u003c/TD\u003e\u003c/TR\u003e\n\u003c/TABLE\u003e\n\n## Dataset\nWe used the [UP-Fall Detection](https://sites.google.com/up.edu.mx/har-up/) to train the LSTM model. You can use [this](https://colab.research.google.com/drive/1PbzVZnwBzFK_CcMf5G3dFrjwKZgfK3Vy?usp=sharing) Colab notebook to download the download the dataset and compile the files into videos.\n\n\n## Citation\nPlease cite the following paper in your publications if our work has helped your research: \u003cbr\u003e [Multi-camera, multi-person, and real-time fall detection using long short term memory](https://doi.org/10.1117/12.2580700)\n\n                  \n    @inproceedings{Taufeeque2021MulticameraMA,\n                    author = {Mohammad Taufeeque and Samad Koita and Nicolai Spicher and Thomas M. Deserno},\n                    title = {{Multi-camera, multi-person, and real-time fall detection using long short term memory}},\n                    volume = {11601},\n                    booktitle = {Medical Imaging 2021: Imaging Informatics for Healthcare, Research, and Applications},\n                    organization = {International Society for Optics and Photonics},\n                    publisher = {SPIE},\n                    pages = {35 -- 42},\n                    year = {2021},\n                    doi = {10.1117/12.2580700},\n                    URL = {https://doi.org/10.1117/12.2580700}\n                  }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaufeeque9%2Fhumanfalldetection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftaufeeque9%2Fhumanfalldetection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaufeeque9%2Fhumanfalldetection/lists"}