Skip to content

myominhtet/person_tracking_and_face_detection

Repository files navigation

person_tracking_and_face_detection

Detecting and tracking person using deep_sort with yolov3. Resnet50 and pretrained weights are used for feature extraction. Another feature of my implementation includes face detection with MTCNN

I have no gpu PC.So I implement this in google colab.

To run project.ipynb, dowload all the folders and upload to your google drive.

In your google colab, folder destination should be like this

drive
  • MyDrive
  • [deep_sort_pytorch-master]
  • [PyTorch-YOLOv3-master]
  • [yolov3.weights]
  • [feature_extraction.py]
  • [project.ipynb]

Here is the demo :)

ezgif-2-eebcc243a2

Code

Deep_sort_pytorch: https://github.com/ZQPei/deep_sort_pytorch YOLOv3: https://github.com/eriklindernoren/PyTorch-YOLOv3 Resnet50 from torchvision.models

Paper

Deep_sort_pytorch: https://arxiv.org/abs/1703.07402 YOLOv3: https://arxiv.org/abs/1804.02767 Resnet: https://arxiv.org/abs/1512.03385

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published