README.md

YOLO (You Only Look Once) Object Detection using OpenCV in Python.

OpenCV dnn module supports running inference on pre-trained deep learning models from popular frameworks like YOLO, TensorFlow, etc.

This project implements image Object detection, video Object detection and Real Time video Object detection through webcam using YOLO (You Only Look Once) algorithm.
For this project pretrained YOLOv3 models was used. The YOLOv3 implementation is from darknet.

---

Tech stack

Important Modules Needed

1. opencv-python:

Pre-built CPU-only OpenCV packages for Python.

2. numpy:

NumPy can be used as an efficient multi-dimensional container of generic data. Arbitrary data-types can be defined

3. argparse:

The argparse module makes it easy to write user friendly command line interfaces.

---

I've used YOLO v3 for coding purpose in this repository.
YOLO (You Only Look Once) is a very powerful and a fast algorithm in object detection. A strong understanding of the algorithm is essential before we start to code.

Before getting started, Make sure you have numpy and opencv installed. If not install them using pip.

 pip install numpy
 pip install opencv-python

---

Steps to get started

1. Clone the repository

git clone https://github.com/anotherwebguy/Object-Detection-Yolo.git

2. Move to the directory

cd Object-Detection-Yolo

3. Download the pretrained weights yolov3.weights

4. Place the yolov3.weights in the yolo-coco directory

5. For Object Detection in images

python main.py --image-path 'path/to/image/'

6. For Object Detection in vidoes

python main.py --video-path 'path/to/video/'

7. For Real time Object Detection using webcam

python main.py    

---

Inference on Images

Inference on Videos

output1.mp4

output.mp4

Inferences in Real Time