@article{Zeng2026, 
author = {Wu Zeng and Guojun Mao and Mei Li and Shuaibing Yin},
title = {Deep learning-based object detection: A comprehensive review of YOLO, RCNN, and SSD series},
year = {2026},
journal = {Electronic Research Archive},
volume = {34},
number = {4},
pages = {2674-2731},
keywords = {object detection, small object detection, unmanned aerial vehicles (UAVs), remote sensing image detection, deep learning},
url = {https://www.sciopen.com/article/10.3934/era.2026124},
doi = {10.3934/era.2026124},
abstract = {In recent years, with the development of science and technology, deep learning technology has also been continuously advancing. As an important application field of deep learning, computer vision has increasingly broad application prospects. Among them, object detection is an extremely important branch of computer vision. This technology has been widely applied in many fields such as environmental monitoring, traffic management, and agricultural evaluation. This paper focused on introducing deep learning-based computer vision object detection and small object detection technologies. In general, object detection methods can be divided into two major categories, namely one-stage and two-stage object detection algorithms. In further subdivision, we roughly classified object detection technologies into three categories: 1) object detection frameworks based on the you only look once (YOLO) series; 2) object detection frameworks based on the region-based convolutional neural network (R-CNN) series; 3) object detection frameworks based on the SSD (single shot multibox detector) series. In addition, we also introduced a series of real application scenarios of small object detection algorithms, such as small object detection based on unmanned aerial vehicles (UAVs) and remote sensing images. Finally, we summarized object detection and small object detection, and we look forward to some possible future research or improvement directions of this technology.}
}