A Comparative Study Between the Most Usable Object Detection Methods Based on Deep Convolutional Neural Networks

Object detection is a computer vision technique that has been revolutionized by the rapid development of convolutional neural network architectures. These networks consist of powerful tools, able to learn and extract high-level features more complex. They are introduced to deal with the problems existing in traditional architectures, to find and characterize a large number of objects in an image. This technique has two types of detection: a simple detection that aims to identify a single object in an image, it is a classification problem. And multiple detections that aim not only to identify all the objects in the image but also to find the location of the objects. This article describes a simple summary of datasets and deep learning algorithms commonly used in object detection. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.