Development of a model for detecting and localizing objects in images based on the adaptation of a single-frame object detector

Бесплатный доступ

This article is devoted to the development and implementation of a new model for the detection and localization of objects in images, based on the adaptation of Single-Shot Detector (SSD). The object of this work is an approach to the detection and localization of different types of objects in images. The prerequisites for SSD are described. The development of a modified SSD method is done. The choice of the basic model of the system, configuration and description of parameters are made. The training strategy and architecture of the system are described.

Yolo, ssd

Короткий адрес: https://sciup.org/170188853

IDR: 170188853   |   DOI: 10.24412/2500-1000-2021-5-1-51-56

Статья научная