YOLO Realtime Human Detection

YOLO Real Time Human Detection Detection (YOLO) with OpenCV and Python.

This project implements a real time human detection via video or webcam detection using yolov3-tiny algorithm. YOLO is a object detection algorithm which stand for You Only Look Once. I've implemented the algorithm from scratch in Python using pre-trained weights. YOLOv3 was published in research paper: YOLOv3: An Incremental Improvement: Joseph Redmon, Ali Farhadi It's originally implemented in YOLOv3.

COCO dataset is used for training.

Real-Time Human Detection and Distance Estimation GUI

YOLO Real-time Young Women Detection
YOLO Real-time Kid Detection
YOLO Real-time Fashion Women Detection

YOLOv3

You only look once (YOLO) is an object detection system targeted for real-time processing. We will introduce YOLO, YOLOv2 and YOLO9000 in this article. For those only interested in YOLOv3, please forward to the bottom of the article. Here is the accuracy and speed comparison provided by the YOLO web site.

Requirement

• OpenCV 4.2.0
• Python 3.6

Quick start

• Download official yolov3-tiny.weights and place it under a folder called weight.
• Download yolov3-tiny.cfg and place it under a folder called cfg.

Dependencies

• opencv
• numpy

Install dependencies

pip install numpy opencv-python

How to use?

1. Clone the repository

git clone https://github.com/muhammadshiraz/YOLO-Realtime-Human-Detection.git

2. Move to the directory

cd YOLO-Realtime-Human-Detection

3. To view the YOLO Real-time Young Women Detection

python yolo_realtime_young_detection.py

4. To view the YOLO Real-time Kid Detection

python yolo_realtime_kid_detection.py

5. To use in YOLO Real-time Fashion Women Detection

python yolo_realtime_woman_detection.py.py

Run by PyCharm IDE:

Object Detection Distance Estimation