Darknet & YOLO object detection

Finally it’s coming, since my laptop was under service before.

This time I’ll write about Darknet and YOLO Object Detection, and some tutorial on it. I know them from humanoid robot research, which needs computer vision and machine learning to detect object.

Darknet

to install darknet: https://pjreddie.com/darknet/install/

Easily, darknet is the main program to run, and YOLO is the library used.

Yolo is a real time object detection system. It uses dataset to train what contained in an image. Not just image, you could capture the moment from webcam, like a humanoid robot did (Yeah I miss them so much).

In the website, it was said:

Source: https://pjreddie.com/darknet/yolo/

How YOLO Works?

It was said that:

Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.

We use a totally different approach. We apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.

Our model has several advantages over classifier-based systems. It looks at the whole image at test time so its predictions are informed by global context in the image. It also makes predictions with a single network evaluation unlike systems like R-CNN which require thousands for a single image. This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than Fast R-CNN. See our paper for more details on the full system. [1]

The technical step showed here: https://pjreddie.com/darknet/yolo/

This is my trained image!

 

Sources:

  1. https://pjreddie.com/darknet/yolo/

Leave a Reply

Your email address will not be published. Required fields are marked *