多尺度目标检测的深度学习研究综述
作者:
作者单位:

作者简介:

陈科圻(1997-),男,硕士生,主要研究领域为计算机视觉.
朱志亮(1988-),男,博士,讲师,主要研究领域为图像智能感知与增强,人机交互.
邓小明(1980-),男,博士,副研究员,CCF高级会员,主要研究领域为计算机视觉,人机交互.
马翠霞(1975-),女,博士,研究员,博士生导师,CCF高级会员,主要研究领域为人机交互,媒体大数据可视分析.
王宏安(1963-),男,博士,研究员,博士生导师,CCF高级会员,主要研究领域为自然人机交互,实时智能计算.

通讯作者:

马翠霞,E-mail:cuixia@iscas.ac.cn

基金项目:

国家重点研发计划(2016YFB1001200);国家自然科学基金(61872346)


Deep Learning for Multi-scale Object Detection: A Survey
Author:
Affiliation:

Fund Project:

National Key Research and Development Program of China (2016YFB1001200); National Natural Science Foundation of China (61872346)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    目标检测一直以来都是计算机视觉领域的研究热点之一,其任务是返回给定图像中的单个或多个特定目标的类别与矩形包围框坐标.随着神经网络研究的飞速进展,R-CNN检测器的诞生标志着目标检测正式进入深度学习时代,速度和精度相较于传统算法均有了极大的提升.但是,目标检测的尺度问题对于深度学习算法而言也始终是一个难题,即检测器对于尺度极大或极小目标的检测精度会显著下降,因此,近年来有不少学者在研究如何才能更好地实现多尺度目标检测.虽然已有一系列的综述文章从算法流程、网络结构、训练方式和数据集等方面对基于深度学习的目标检测算法进行了总结与分析,但对多尺度目标检测的归纳和整理却鲜有人涉足.因此,首先对基于深度学习的目标检测的两个主要算法流派的奠基过程进行了回顾,包括以R-CNN系列为代表的两阶段算法和以YOLO、SSD为代表的一阶段算法;然后,以多尺度目标检测的实现为核心,重点诠释了图像金字塔、构建网络内的特征金字塔等典型策略;最后,对多尺度目标检测的现状进行总结,并针对未来的研究方向进行展望.

    Abstract:

    Object detection is a classic computer vision task which aims to detect multiple objects of certain classes within a given image by bounding-box-level localization. With the rapid development of neural network technology and the birth of R-CNN detector as a milestone, a series of deep-learning-based object detectors have been developed in recent years, showing the overwhelming speed and accuracy advantage against traditional algorithms. However, how to precisely detect objects in large scale variance, also known as the scale problem, still remains a great challenge even for the deep learning methods, while many scholars have made several contributions to it over the last few years. Although there are already dozens of surveys focusing on the summarization of deep-learning-based object detectors in several aspects including algorithm procedure, network structure, training and datasets, very few of them concentrate on the methods of multi-scale object detection. Therefore, this paper firstly review the foundation of the deep-learning-based detectors in two main streams, including the two-stage detectors like R-CNN and one-stage detectors like YOLO and SSD. Then, the effective approaches are discussed to address the scale problems including most commonly used image pyramids, in-network feature pyramids, etc. At last, the current situations of the multi-scale object detection are concluded and the future research directions are looked ahead.

    参考文献
    相似文献
    引证文献
引用本文

陈科圻,朱志亮,邓小明,马翠霞,王宏安.多尺度目标检测的深度学习研究综述.软件学报,2021,32(4):1201-1227

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-08-10
  • 最后修改日期:2020-09-20
  • 录用日期:
  • 在线发布日期: 2020-12-02
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号