[1]金海燕,肖照林,蔡 磊,等.显著性目标检测理论与应用研究综述[J].计算机技术与发展,2022,32(09):1-7.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 001]
　JIN Hai-yan,XIAO Zhao-lin,CAI Lei,et al.Review on Theory and Application of Saliency Target Detection[J].,2022,32(09):1-7.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 001]
点击复制

显著性目标检测理论与应用研究综述()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年09期
页码:
1-7
栏目:
综述
出版日期:
2022-09-10

文章信息/Info

Title:
Review on Theory and Application of Saliency Target Detection
文章编号:
1673-629X(2022)09-0001-07
作者:
金海燕1; 2 ; 肖照林1; 2 ; 蔡 磊1; 2 ; 王 彬1; 2
1. 西安理工大学 计算机科学与工程学院,陕西 西安 710048
2. 陕西省网络计算与安全技术重点实验室,陕西 西安 710048
Author(s):
JIN Hai-yan1; 2 ; XIAO Zhao-lin1; 2 ; CAI Lei1; 2 ; WANG Bin1; 2
1. School of Computer Science and Engineering,Xi’an University of Technology,Xi’an 710048,China
2. Shaanxi Key Laboratory for Network Computing and Security Technology,Xi’an 710048,China
关键词:
显著性检测; 视觉显著性; 多模态; 特征提取; 图像融合; 深度学习
Keywords:
saliency detection; visual saliency; multi-modal; feature extraction; image fusion; deep learning
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 09. 001
摘要:
显著性目标检测旨在从输入图像中根据显著性特征,快速有效地提取场景中有用区域,即目标区域,其本质是一种分割任务。 高质量的显著性目标检测技术可提升基于视觉感知的人工智能系统对场景的判断与理解能力。 在计算机视觉领域,显著性检测目标检测是十分重要的一个分支,逐渐成为研究热点,在目标识别、图像检测、图像检索等相关行业中具有十分广阔的应用前景。 传统的显著性检测方法主要针对简单场景下的单一模态数据,由于其场景信息完备性较低,进而导致对显著性目标特征的分析、提取、表达、计算等诸多环节的理论拓展性较弱,适用范围受限。 该文围绕显著性目标检测理论研究,分析了国内外关于显著性目标检测理论研究的主要方向和发展现状,总结了显著性目标检测的主要应用,讨论了目前显著性目标检测理论研究的热点领域以及将来需要重点研究的问题和面临的挑战。
Abstract:
The salient object detection aims to extract the useful area ( target area) in the scene according to the salient features from thein put image quickly and effectively, which is essentially a segmentation task. High - quality salient target detection technology can improve the ability of artificial intelligence systems based on visual perception to judge and understand scenes. In the field of computervision,saliency detection target detection is a very important branch,and has gradually become a research hotspot,which has very broad application prospects in related industries such as target recognition,image detection,and image retrieval. Traditional saliency detection methods are mainly aimed? ? ?at single - modal data in simple scenes. Due to the low completeness of scene information, the the oreticalexpansion of many links such as analysis, extraction, expression, and calculation of saliency target features is weak, and the scope ofapplication is limited. Focused on the theory of saliency target detection,the main research directions and development status for saliencytarget detection theory at home and abroad is introduced,and the main application of saliency target detection is analyzed,at the same time the current theoretical research hot area on saliency target detection is discussed. Finally,the important issues and challenges that need to be studied in the future are explored.

相似文献/References:

[1]陈凡[],童莹[],曹雪虹[]. 复杂环境下基于视觉显著性的人脸目标检测[J].计算机技术与发展,2017,27(01):48.
　CHEN Fan[],TONG Ying[],CAO Xue-hong[]. Face Target Detection of Visual Saliency in Complex Environment[J].,2017,27(09):48.
[2]鲍小如,陈瑞,曹雪虹,等.基于视觉显著性与肤色分割的人脸检测[J].计算机技术与发展,2018,28(04):104.[doi:10.3969/ j. issn.1673-629X.2018.04.022]
　BAO Xiao-ru,CHEN Rui,CAO Xue-hong,et al.Face Detection Based on Visual Salient and Skin Color[J].,2018,28(09):104.[doi:10.3969/ j. issn.1673-629X.2018.04.022]
[3]刘华春,侯向宁.采用视觉显著性和卷积网络的车牌定位算法[J].计算机技术与发展,2019,29(06):74.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 016]
　LIU Hua-chun,HOU Xiang-ning.A License Plate Location Algorithm Using Visual Saliency and Convolutional Network[J].,2019,29(09):74.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 016]
[4]李江龙,鲍义东,陈 果.基于视觉显著性的农作物图像评价方法研究[J].计算机技术与发展,2020,30(04):211.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 040]
　LI Jiang-long,BAO Yi-dong,CHEN Guo.Study on Crop Image Evaluation Methods Based on Visual Saliency[J].,2020,30(09):211.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 040]
[5]王 楠 *,伍阳停,朱琦赫,等.面向检索应用的商标显著性检测方法[J].计算机技术与发展,2023,33(11):162.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 024]
　WANG Nan *,WU Yang-ting,ZHU Qi-he,et al.Trademark Saliency Detection Method for Image Retrieval[J].,2023,33(09):162.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 024]

更新日期/Last Update: 2022-09-10