YOLOv4

Object detection is a computer technology related computer vision and image processing that deals with
detection instances of semantic objects of a certain instances of semantic objects of a certain class(such
as humans, buildings, or cars) in digital images and videos.

Machine learning approaches

Viola-jones object detection framework based on Haar features

Scale-invariant feature transform(SIFT)

Histogram of oriented gradients(HOG) features

Deep Learning approaches

Region prosposals (R-CNN, Fast R-CNN, Faster R-CNN,cascade R-CNN)

Single Shot Multibox Detector (SSD)

YOLO

Single Shot Refinement Neural Network for Object detection(RefineDet)

Retina-Net

Distinct features of yolov4

 More parameters – for greater capacity of a model to detect multiple objects of different sizes in a single
image
 Higher input network size (resolution) – for detecting multiple small-sized objects