From 0a948175c6a255f3468e66e503cb8538c0c84875 Mon Sep 17 00:00:00 2001 From: S Rohan Rao Date: Fri, 26 Jun 2020 22:07:48 +0530 Subject: [PATCH] Update README.md --- README.md | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index f1f5c2f..b3c7210 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,48 @@ # Social_Distancing_with_AI -This project aims at monitoring people violating Social Distancing over CCTV footage during these tough COVID19 times. It uses YOLOv3 for localizing the intruders. A face mask classifier model (Resnet50) is trained on augmented masked faces (using face landmarks) for finding people not wearing a face mask. +This project aims at monitoring people violating Social Distancing over video footage coming from CCTV Cameras. Uses YOLOv3 along with DBSCAN clustering for recognizing potential intruders. A Face Mask Classifier model (Resnet50) is trained and deployed for identifying people not wearing a face mask. Augmented masked faces are generated using facial landmarks for aiding the training process. + +A detailed description of this project along with the results can be found [here](#project-description-and-results). + +## Getting Started + +### Prerequisites +Running this project on your local system requires the following packages to be installed : + +* numpy +* matplotlib +* sklearn +* PIL +* cv2 +* keras +* face_detection +* face_recognition +* tqdm + +They can be installed from the Python Package Index using pip as follows : + + pip install numpy + pip install matplotlib + pip install sklearn + pip install Pillow + pip install opencv-python + pip install Keras + pip install face-detection + pip install face-recognition + pip install tqdm + +You can also use [Google Colab](https://colab.research.google.com/) in a Web Browser with most of the libraries preinstalled. + +### Usage +This project is implemented using interactive Jupyter Notebooks. You just need to open the notebook on your local system or on [Google Colab](https://colab.research.google.com/) and execute the code cells in sequential order. The function of each code cell is properly explained with the help of comments. + +Please download the following files (from the given links) and place them in the Models folder in the root directory : +1. YOLOv3 weights : https://pjreddie.com/media/files/yolov3.weights +2. Face Mask Classifier ResNet50 Keras Model : https://drive.google.com/drive/folders/1Q59338kd463UqUESwgt7aF_W46Fj5OJd?usp=sharing + +Also before starting you need to make sure that the path to various files and folders in the notebook are updated according to your working environment. If you are using [Google Colab](https://colab.research.google.com/), then : +1. Mount Google Drive using : + + from google.colab import drive + drive.mount('drive/') + +2. Update file/folder locations as `'drive/path_to_file_or_folder'`.