DARK-art108 / DetectNow.ai Public

Notifications You must be signed in to change notification settings
Fork 2
Star 6

A Video Analytics Dashboard for detecting and tracking multiple objects using YoloV5 & Deepsort

6 stars 2 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
assets		assets
deep_sort_pytorch		deep_sort_pytorch
yolov5		yolov5
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
app.py		app.py
deep_list.py		deep_list.py
detect_sort.py		detect_sort.py
graphs.py		graphs.py
requirements.txt		requirements.txt
sample-input.mp4		sample-input.mp4
yolov5s_people.pt		yolov5s_people.pt

Repository files navigation

DetectNow.ai : YoloV5 and DeepSort Tracker Streamlit Dashboard

🔑 Features

Choose input source - Local, RTSP or Webcam
Input class threshold
Set FPS drop warning threshold
Option to save inference video
Input class confidence for drift detection
Option to save poor performing frames
Display objects in current frame
Display total detected objects so far
Display System stats - Ram, CPU and GPU usage
Display poor performing class
Display minimum and maximum FPS recorded during inference

💫 How to use?

Clone this repo
Install all the dependencies
Run -> streamlit run app.py

🚀 New Updates!

Fixed bug in upsampling.py [YoloV5] for cuda 11.5
Added New Requirement: TorchCUDA 11.5

❤️ Acknowledgement

Sahil Chachra

About

A Video Analytics Dashboard for detecting and tracking multiple objects using YoloV5 & Deepsort

pytorch deepsort yolov5

Report repository

Releases

No releases published

Packages

No packages published

Languages