# Down-Recognition **Repository Path**: liuhunck/down-recognition ## Basic Information - **Project Name**: Down-Recognition - **Description**: one project of HNU SIT, the body is forked from a github repository. What I add to the project is the camera api from YingShi. - **Primary Language**: Python - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2024-03-12 - **Last Updated**: 2024-03-30 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README

Human Falling Detection and Tracking

Using Tiny-YOLO oneclass to detect each person in the frame and use [AlphaPose](https://github.com/MVIG-SJTU/AlphaPose) to get skeleton-pose and then use [ST-GCN](https://github.com/yysijie/st-gcn) model to predict action from every 30 frames of each person tracks. Which now support 7 actions: Standing, Walking, Sitting, Lying Down, Stand up, Sit down, Fall Down. ## Prerequisites - Python > 3.6 - Pytorch > 1.3.1 Original test run on: NVIDIA Orin NX Developer Kit, CUDA 11.4 ## Data This project has trained a new Tiny-YOLO oneclass model to detect only person objects and to reducing model size. Train with rotation augmented [COCO](http://cocodataset.org/#home) person keypoints dataset for more robust person detection in a variant of angle pose. For actions recognition used data from [Le2i](http://le2i.cnrs.fr/Fall-detection-Dataset?lang=fr) Fall detection Dataset (Coffee room, Home) extract skeleton-pose by AlphaPose and labeled each action frames by hand for training ST-GCN model. ## Pre-Trained Models - Tiny-YOLO oneclass - [.pth](https://drive.google.com/file/d/1obEbWBSm9bXeg10FriJ7R2cGLRsg-AfP/view?usp=sharing), [.cfg](https://drive.google.com/file/d/19sPzBZjAjuJQ3emRteHybm2SG25w9Wn5/view?usp=sharing) - SPPE FastPose (AlphaPose) - [resnet101](https://drive.google.com/file/d/1N2MgE1Esq6CKYA6FyZVKpPwHRyOCrzA0/view?usp=sharing), [resnet50](https://drive.google.com/file/d/1IPfCDRwCmQDnQy94nT1V-_NVtTEi4VmU/view?usp=sharing) - ST-GCN action recognition - [tsstg](https://drive.google.com/file/d/1mQQ4JHe58ylKbBqTjuKzpwN2nwKOWJ9u/view?usp=sharing) ## Basic Use 1. Download all pre-trained models into ./Models folder. 2. Run main.py ``` python main.py ${video file or camera source or ./config/video.yaml} ``` ## Reference - AlphaPose : https://github.com/Amanbhandula/AlphaPose - ST-GCN : https://github.com/yysijie/st-gcn