## What is YOLO Algorithm?

YOLO means “You Only Look Once.” YOLO is a real-time object detection algorithm that uses neural networks. YOLO is popular because of its excellent accuracy and fastest speed in real-time. Nowadays, it is used in many fields like autonomous cars, people, animals, and other objects’ detection in real-time. You only look once to provide the probabilities of the class of the detected image, and this task is done as a regression problem.

As we can understand from the name of the algorithm that it only needs one single forward propagation through the neural network to get the results.

YOLO has many variants like **YOLO-v1, YOLO-v2, YOLOR**(You Only Look Once Representation), etc.

## Why YOLO algorithm is important?

YOLO is an important algorithm because of the following reasons:

**Speed:** This Algorithm is very fast than other algorithms. This algorithm can detect objects in the image in real-time.

**Accuracy:** The accuracy of this algorithm is very good. The chances of errors in this algorithm are very rare.

**Learning Capability: **YOLO has amazing learning capabilities it can learn from data and create the model for prediction then detect the object in the picture in real-time.

## How YOLO algorithm work?

YOLO algorithm works using the following techniques:

- Residual Blocks
- Bounding Box Regression
- Intersection Over Union

### Residual Blocks:

In **YOLO algorithms object detection** the first step is to divide the image into grids. Each grid’s dimension will be SxS. The grid which contains the center of the object will be responsible for the detection of the object.

### Bounding Box Regression:

The bounding box is the box around the detected object which highlight the object in the image.

Every Bounding box in the image consists of the following components: Width, Height, Class, and Bounding Box Center.

YOLO uses the single bounding box regression to predict the width, height, and center of the bounding box, along with the class of the detected object.

### Intersection over union:

Intersection over union is the phenomenon in real-time object detection that explains how the **boxes **overlap. YOLO uses intersection over union to provide an output box that perfectly surrounds the detected object.

If the original bounding box is equal to the predicted bounding box, then the intersection over the union will be equal to 1. The other bounding boxes that are not equal to the real box will be eliminated.

### Conclusion:

So we have discussed, what is YOLO? Importance of YOLO and the Working of the YOLO algorithm. If you have any confusion or question please don’t hesitate to ask in the comment section. Thank You