深度学习下的单阶段通用目标检测算法研究综述  

Review of One-Stage Universal Object Detection Algorithms in Deep Learning

作　　者：王宁 智敏 WANG Ning;ZHI Min(College of Computer Science and Technology,Inner Mongolia Normal University,Hohhot 010022,China)

机构地区：[1]内蒙古师范大学计算机科学技术学院,呼和浩特010022

出　　处：《计算机科学与探索》2025年第5期1115-1140,共26页Journal of Frontiers of Computer Science and Technology

基　　金：呼和浩特市基础研究与应用基础研究项目(2024-规-基-33);内蒙古自然科学基金(2023MS06009);内蒙古高等学校科学研究重点项目(NJZZ21004)。

摘　　要：近年来,目标检测算法作为计算机视觉领域中的核心任务,逐渐成为热门研究方向。它使得计算机能够识别和定位图像或视频帧中的目标物体,广泛应用于自动驾驶、生物个体检测、农业检测、医疗影像分析等领域。随着深度学习的发展,通用目标检测算法从传统的目标检测方法转变为基于深度学习下的目标检测方法。其中深度学习下的通用目标检测算法主要分为单阶段目标检测与两阶段目标检测,以单阶段目标检测为切入点,根据采用经典卷积与Transformer两种不同架构,对首个单阶段目标检测算法YOLO系列(YOLOv1~YOLOv11、YOLO主要改进版本)、SSD等和以Transformer为基础架构的DETR系列的主流单阶段检测算法进行分析总结。介绍各个算法的网络结构以及其研究进展,根据各个算法的结构归纳出其特点优势以及局限性,概括目标检测领域主要通用数据集与评价指标,分析各算法以及其改进方法的性能,讨论各算法在不同领域的应用现状,展望单阶段目标检测算法在未来的研究方向。In recent years,object detection algorithms have gradually become a hot research direction as a core task in the field of computer vision.They enable computers to recognize and locate target objects in images or video frames,and are widely used in fields such as autonomous driving,biological individual detection,agricultural detection,medical image analysis,etc.With the development of deep learning,general object detection algorithms have shifted from traditional ob-ject detection methods to object detection methods based on deep learning.The general object detection algorithms under deep learning are mainly divided into one-stage object detection and two-stage object detection.This paper takes one-stage object detection as the starting point and analyzes and summarizes the mainstream one-stage detection algorithms of the first one-stage object detection algorithm YOLO series(YOLOv1 to YOLOv11,YOLO main improved version),SSD,and DETR series based on Transformer architecture,based on the use of two different architectures:classical convolution and Transformer.This paper introduces the network structure and research progress of various algorithms,summarizes their characteristics,advantages,and limitations based on their structures,summarizes the main common datasets and eval-uation indicators in the field of object detection,analyzes the performance of various algorithms and their improvement methods,discusses the application status of various algorithms in different fields,and finally looks forward to the future research directions of one-stage object detection algorithms.

关 键 词：目标检测 深度学习 计算机视觉 单阶段 YOLO DETR 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]