Please enable JavaScript.
Coggle requires JavaScript to display documents.
YOLO - Coggle Diagram
YOLO
The bounding box consist in:
Centre of the bounding box
Width
Height
Class of object
Probability that there is an object in the bounding box
Darknet
Open Source Neural Network Framerwork
Written in C language and CUDA technology
Algorithm based on regression
Singles Step Process
Images is screened, objects are located and bounding boxes are drawn in the same run
Time, speed and accuracy are prime concerns
Real time object detection algorithm
Classifies images into different categories, after the image clasification. A further process involves location, that is Object Localization. The last function is Object Detection which is drawing a box around the located objects.
"You Only Look Once: Unified Real Time Object Detection"
Author: Joseoph Redmon et al.
2015
Variants: YOLOv3, PP-YOLO, YOLO9000.
Uses Artificial Intelligence and Deep Learning
It involves the splitting of the image into multiple cells.
YOLO model evolved on the basis of the Pascal VOC detection dataset.