Repository files navigation

Simple model to"Detect/Track" and"Re-identify" individuals in different cameras/videos.

This project aims to track people in different videos accounting for different angles.

The framework used to accomplish this task relies on MOT and ReID to track and re-identify ID's of humans, respectively.The tracking can be completed using YOLO_v3 or YOLO_v4 and ReID relies on KaiyangZhou's Torchreid library.

• DownloadAnaconda if it is not installed on your machine

• Clone the repository

gitclonehttps://github.com/samihormi/Multi-Camera-Person-Tracking-and-Re-Identification

• Create a project environment

cdMulti-Camera-Person-Tracking-and-Re-Identificationcondacreate--namepy37python=3.7condaactivatepy37

• Install dependencies

pipinstall-rrequirements.txt

• Install torch and torchvision based on the cuda version of your machine

condainstallpytorchtorchvisioncudatoolkit-cpytorch

• Download the YOLO models forYOLO_v3 andYOLO_v4 and add them to /model_data/weights/

• YOLO_v3

pythonconvert_y3.pymodel_data\weights\yolov3.weightsmodel_data\models\yolov3.h5

• YOLO_v4

pythonconvert_y4.pymodel_data\weights\yolov4.weightsmodel_data\models\yolov4.h5

• Download the Keras models forYOLO_v3 andYOLO_v4 and add them to \model_data\models\

• Download either one of the following Torchreid models1,2 and add them to \model_data\models\ (you might have to change the path in reid.py)

You can try out your own videos by running demo.py.Under the directory \videos\output, the program will generate a video of the tracking, as well as a video of the tracking and ReID. (as can be seen in the example above)You should specify the path of the videos and the version of YOLO you would like to use (v3 or v4)

pythondemo.py--videosvideos\init\Double1.mp4videos\init\Single1.mp4--versionv3

This model is build on top of the incredible work done in the following projects:

• https://github.com/nwojke/cosine_metric_learning
• https://github.com/KaiyangZhou/deep-person-reid
• https://github.com/Qidian213/deep_sort_yolov3
• https://github.com/Ma-Dan/keras-yolo4
• https://github.com/lyrgwlr/Human-tracking-multicam