It will detect the common objects which we specified. Detecting and naming the objects can help people who do not know what they will be called.
YOLO(“You Only Look Once”) uses neural networks to provide real-time object detection. The algorithm is well-liked due to its speed and accuracy. It has been used in different applications to detect traffic signals, people, parking meters, animals, and much more. The algorithm was trained to find a variety of classes of objects. 20 conditional class probabilities will be outputted for any grid cell and one for each class. There is a choice between two bounding boxes gives by the grid cell, we have only one class probability vector.
The OpenCV dnn supports running inference on pre-trained deep learning models from well-known frameworks like Caffe, Torch and TensorFlow.
In object detection the popular frameworks are
YOLO
SSD
Faster R-CNN
In OpenCV dnn module recently the support added for running YOLO/DarkNet.
Dependencies
OpenCV
numpy
pip install numpy opencv-python
Note: Compatability with Python 3.x only tested for this.
Submitted by VARUN SIMHA REDDY (VARUNREDDY099)
Download packets of source code on Coders Packet
Comments