Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation

Dim and small target detection plays an important role in infrared target recognition systems. In this paper, we present a dim and small target detection algorithm based on improved bilateral filtering and Gaussian motion probability estimation, aiming to improve the detection efficiency of the dete...

Full description

Saved in:
Bibliographic Details
Main Authors: Fan Xiangsuo, Qin Wenlin, Feng Gaoshan, Huang Qingnan, Min Lei
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10636302/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849415897739952128
author Fan Xiangsuo
Qin Wenlin
Feng Gaoshan
Huang Qingnan
Min Lei
author_facet Fan Xiangsuo
Qin Wenlin
Feng Gaoshan
Huang Qingnan
Min Lei
author_sort Fan Xiangsuo
collection DOAJ
description Dim and small target detection plays an important role in infrared target recognition systems. In this paper, we present a dim and small target detection algorithm based on improved bilateral filtering and Gaussian motion probability estimation, aiming to improve the detection efficiency of the detection system. First, a bilateral filtering algorithm based on image patch analysis is proposed to complete the background modeling, compare with single pixel, image patch contains more neighborhood information. Then, we use the Gaussian process combining the target position of consecutive <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> frames to predict the target position of the <inline-formula><tex-math notation="LaTeX">$(n+1)\text{th}$</tex-math></inline-formula> frame, and the target energy is accumulated along the trajectory direction at the same time. Finally, we construct the grayscale probability model to realize the multi-frame correlation detection, which combining the grayscale features and the motion characteristics of the target. Six scenes and eleven comparison algorithms are selected for experiments, experimental results show the effectiveness and robustness of the proposed algorithm.
format Article
id doaj-art-484e2cac03cd4abf9384cd296a15ed0e
institution Kabale University
issn 1943-0655
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-484e2cac03cd4abf9384cd296a15ed0e2025-08-20T03:33:21ZengIEEEIEEE Photonics Journal1943-06552024-01-0116512010.1109/JPHOT.2024.344323910636302Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability EstimationFan Xiangsuo0https://orcid.org/0000-0002-1685-4989Qin Wenlin1https://orcid.org/0000-0003-0410-4184Feng Gaoshan2Huang Qingnan3https://orcid.org/0000-0002-0458-6630Min Lei4https://orcid.org/0000-0002-3459-6063School of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaDongfeng Liuzhou Motor Company, Ltd., Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaInstitute of Optics and Electronics Chinese Academy of Sciences, Chengdu, ChinaDim and small target detection plays an important role in infrared target recognition systems. In this paper, we present a dim and small target detection algorithm based on improved bilateral filtering and Gaussian motion probability estimation, aiming to improve the detection efficiency of the detection system. First, a bilateral filtering algorithm based on image patch analysis is proposed to complete the background modeling, compare with single pixel, image patch contains more neighborhood information. Then, we use the Gaussian process combining the target position of consecutive <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> frames to predict the target position of the <inline-formula><tex-math notation="LaTeX">$(n+1)\text{th}$</tex-math></inline-formula> frame, and the target energy is accumulated along the trajectory direction at the same time. Finally, we construct the grayscale probability model to realize the multi-frame correlation detection, which combining the grayscale features and the motion characteristics of the target. Six scenes and eleven comparison algorithms are selected for experiments, experimental results show the effectiveness and robustness of the proposed algorithm.https://ieeexplore.ieee.org/document/10636302/Bilateral filteringdim and small targetgaussian processmotion estimation
spellingShingle Fan Xiangsuo
Qin Wenlin
Feng Gaoshan
Huang Qingnan
Min Lei
Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
IEEE Photonics Journal
Bilateral filtering
dim and small target
gaussian process
motion estimation
title Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
title_full Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
title_fullStr Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
title_full_unstemmed Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
title_short Dim and Small Target Detection Based on Improved Bilateral Filtering and Gaussian Motion Probability Estimation
title_sort dim and small target detection based on improved bilateral filtering and gaussian motion probability estimation
topic Bilateral filtering
dim and small target
gaussian process
motion estimation
url https://ieeexplore.ieee.org/document/10636302/
work_keys_str_mv AT fanxiangsuo dimandsmalltargetdetectionbasedonimprovedbilateralfilteringandgaussianmotionprobabilityestimation
AT qinwenlin dimandsmalltargetdetectionbasedonimprovedbilateralfilteringandgaussianmotionprobabilityestimation
AT fenggaoshan dimandsmalltargetdetectionbasedonimprovedbilateralfilteringandgaussianmotionprobabilityestimation
AT huangqingnan dimandsmalltargetdetectionbasedonimprovedbilateralfilteringandgaussianmotionprobabilityestimation
AT minlei dimandsmalltargetdetectionbasedonimprovedbilateralfilteringandgaussianmotionprobabilityestimation