Object detection using deep learning with OpenCV and Python

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

When it comes to object detection, popular detection frameworks are

• YOLO
• SSD
• Faster R-CNN

Support for running YOLO/DarkNet has been added to OpenCV dnn module recently.

Install

1. Clone repository: $ [email protected]:cmower/object-detection-opencv.git
2. Change directory: $ cd object-detection-opencv
3. Install: $ pip install .

Usage

Either you can use the command line interface yolo_opencv (see examples below) or import the package using

import yolo_opencv

YOLO (You Only Look Once)

Download the pre-trained YOLO v3 weights file from this link and place it in the current directory or you can directly download to the current directory in terminal using

$ wget https://pjreddie.com/media/files/yolov3.weights

Provided all the files are in the current directory, below command will apply object detection on the input image dog.jpg.

$ yolo_opencv --image dog.jpg --config yolov3.cfg --weights yolov3.weights --classes yolov3.txt

Command format

$ yolo_opencv --image /path/to/input/image --config /path/to/config/file --weights /path/to/weights/file --classes /path/to/classes/file_

Checkout the blog post to learn more.

sample output :

Checkout the object detection implementation available in cvlib which enables detecting common objects in the context through a single function call detect_common_objects().

(SSD and Faster R-CNN examples will be added soon)