YOLO

In this era of technology computer vision has paid a lot of contribution in the concept of object detection which helps the machine to learn from the environment and respond or give output based on that information.

            Computer Vision is the concept of Artificial Intelligence which uses the videos, images for learning. It requires a powerful algorithm to interpret and gave the output. Since then many researchers are studying on the concept of object detection and gave many algorithms for the study such as YOLO, CNN, ResNet and many more.

One such algorithm is YOLO “You Only Look Once” is the concept of CNN i.e. Convolutional Neural Network which is used for object detection from an image. YOLO was studied to gave better accuracy rate in object detection compared to other algorithms from the researchers perspective.

YOLO algorithm divides the image into small boxes and classes. Each box have such properties like center of the box (dx, dy), width (dw), height(dh),class( c), real number (r n).With the help of these parameters probability of the box is calculated and the box with the highest probability is selected for further calculations. After calculating probability, suppression operation is performed to ignore unnecessary information’s from the image.

The same process goes for the rest of the boxes of the image. Then all the outputs or results are further converted to Vector Values for further calculations and learning process. After making the machine to learn from the image, we give the machine some images to test. This is how YOLO algorithm works.

YOLO is generally used for object detection like a specific car from the bunch of vehicles, to identify number plate from the vehicle standing at traffic signal, identify face from a group of people or to detect whether the person is wearing the mask or not.

I hope I have made the topic clear in a very short description of YOLO Algorithm.