距离信息与排序模型融合的显著性目标检测方法

陈睿琦; 南心蒙; 常皓

doi:10.15892/j.cnki.djzdxb.2023.03.005

弹箭与制导学报 >

2023 , Vol. 43 >Issue 3: 33 - 38

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2023.03.005

距离信息与排序模型融合的显著性目标检测方法

陈睿琦 ¹ ,
南心蒙 ¹ ,
常皓 ²

展开

¹ 西安现代控制技术研究所,陕西西安 710065
² 32382部队,北京 100072

陈睿琦(1993—),女,工程师,硕士,研究方向:软件工程。

收稿日期: 2022-10-20

网络出版日期: 2025-02-07

收起

A Salient Object Detection Method Fused with Distance Information and Manifold Ranking

CHEN Ruiqi ¹ ,
NAN Xinmeng ¹ ,
CHANG Hao ²

Expand

¹ Xi'an Mordern Control Technology Research Institute, Xi'an 710065, Shaanxi, China
² No.32382 Unit, Beijing 100072, China

Received date: 2022-10-20

Online published: 2025-02-07

Fold

摘要

针对图像探测系统对地面场景中目标探测及识别问题,提出基于距离轮廓信息与排序模型相融合的显著性目标检测方法,利用二维简易距离轮廓信息对可见光及红外图像实施分割,采用流形排序模型对图像进行处理,进而提高目标的检测性能。实验结果表明,白天条件下对显著性目标检测的准确率可达到87.7%,召回率达到91.6%;夜间条件下的检测准确率达到81.2%,召回率达到86.3%,证明了该方法在保证图像处理速度的前提下,能够显著提高目标检测的正确性。

关键词： 图像处理; 显著性目标检测; 目标识别; 流形排序; 距离信息

本文引用格式

陈睿琦 , 南心蒙 , 常皓 . 距离信息与排序模型融合的显著性目标检测方法[J]. 弹箭与制导学报, 2023 , 43(3) : 33 -38 . DOI: 10.15892/j.cnki.djzdxb.2023.03.005

Abstract

Aiming at the problem of detecting and recognizing targets from complex backgrounds, a salient object detecting method based on the combination of distance information and manifold ranking is proposed. In order to improve the detection performance in complex backgrounds, two-dimensional distance information is used to segment visible light images and infrared images, and manifold ranking is used to process the images. Experimental results show that under daylight condition the precision and recall of this method are 87.7% and 91.6% respectively; while under nighttime condition the precision and recall are above 81.2% and 86.3%. Results show the proposed method can significantly improve the accuracy of target detection from complex backgrounds while ensuring the speed of image processing.

Key words： image processing; saliency detection; target recognition; manifold ranking; distance information

[an error occurred while processing this directive]

参考文献

原文顺序 | 文献年度倒序 | 文中引用次数倒序

[1]	朱大炜. 基于深度学习的红外图像飞机目标检测方法[D]. 西安: 西安电子科技大学, 2018. ZHU D W. Aircraft target detection method based on deep learning in infrared images[D]. Xi'an: Xi'an University of Electronic Science and Technology, 2018.

[2]	管学伟. 机载IRST小目标检测技术研究[D]. 成都: 电子科技大学, 2021. GUAN X W. Research on airborne IRST small target detection technology[D]. Chendu: University of Electronic Science and Technology of China, 2021.

[3]

徐芳. 可见光遥感图像海面目标自动检测关键技术研究[D]. 长春: 中国科学院大学(长春光学精密机械与物理研究所), 2018.

. Research on key technologies for automatic detection of sea surface targets in visible light remote sensing images[D]. Changchun: University of Chinese Academy of Sciences(Changchun Institute of Optics, Precision Mechanics and Physics), 2018.

[4]	刘波. 机器视觉水中图像特征提取与对象辨识研究[D]. 大连: 大连理工大学, 2013. LIU B. Research on feature extraction and target identification in machine vision underwater and surface image[D]. Dalian: Dalian University of Technology, 2013.

[5]	WU H, LI G, LUO X. Weighted attentional blocks for probabilistic object tracking[J]. Visual Computer, 2014, 30 (2): 229-243.

[6]	WANG F, ZHEN Y, ZHONG B, et al. Robust infrared target tracking based on particle filter with embedded saliency detection[J]. Information Sciences, 2015, 301: 215-226.

[7]	GAO D, HAN S, VASCONCELOS N. Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31 (6): 989-1005. DOI PMID

[8]	毕威, 黄伟国, 张永萍, 等. 基于图像显著轮廓的目标检测[J]. 电子学报, 2017, 45(8): 1902-1910. DOI BI W, HUANG G W, ZHANG Y P, et al. Object detection based on image salient contours[J]. Chinese Journal of Electronics, 2017, 45(8): 1902-1910.

[9]	姚琳. 基于多级深度特征融合的RGB-T图像显著性目标检测[D]. 西安: 西安电子科技大学, 2020. YAO L. RGB-T salient object detection via fusing multi-level CNN features[D]. Xi'an: Xi'an University of Electronic Science and Technology, 2020.

[10]	ABDULMUNEM A, LAIY K, SUN X. Saliency guided local and global descriptors for effective action recognition[J]. Computational Visual Media, 2016, 2(1): 97-106.

[11]	GUO C L, ZHANG L M. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression[J]. IEEE Transactions on Image Processing, 2010, 19 (1): 185-198. DOI PMID

[12]	SHEN L, LIU Z, ZHANG Z. A novel H. 264 rate control algorithm with consideration of visual attention[J]. Multimedia Tools & Applications, 2013, 63(3): 709-727.

[13]	王桂召. 基于协同流形排序的多模态视觉显著性检测方法研究[D]. 合肥: 安徽大学, 2018. WANG G Z. Research on multimodal visual saliency detection method based on collaborative manifold sorting[D]. Hefei: Anhui University, 2018.

[14]	白玉, 侯志强, 刘晓义. 基于可见光图像和红外图像决策级融合的目标检测算法[J]. 空军工程大学学报(自然科学版), 2020, 21(6): 53-59. BAI Y, HOU Z Q, LIU X Y, et al. Target detection algorithm based on decision level fusion of visible and infrared images[J]. Journal of Air Force Engineering University (Natural Science Edition), 2020, 21(6): 53-59.

[15]	YANG C, ZHANG L, LU H, et al. Saliency Detection via Graph-Based Manifold Ranking[C]// IEEE. Proceedings of the 2013 IEEE Conference on Computer Vision & Pattern Recognition. New York: IEEE, 2013: 1382-1394.

Options

文章导航