Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach

In remote sensing, object classification often suffers from severe degradation caused by atmospheric turbulence and low-signal conditions. Traditional image reconstruction approaches are computationally expensive and fragile under such conditions. In this work, we propose a novel image-free classifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin Cheng, Yusen Liao, Jun Ke
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/4137
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115712321847296
author Yin Cheng
Yusen Liao
Jun Ke
author_facet Yin Cheng
Yusen Liao
Jun Ke
author_sort Yin Cheng
collection DOAJ
description In remote sensing, object classification often suffers from severe degradation caused by atmospheric turbulence and low-signal conditions. Traditional image reconstruction approaches are computationally expensive and fragile under such conditions. In this work, we propose a novel image-free classification framework using single-pixel imaging (SPI), which directly classifies targets from 1D measurements without reconstructing the image. A learnable sampling matrix is introduced for structured light modulation, and a hybrid CNN-Transformer network (Hybrid-CTNet) is employed for robust feature extraction. To enhance resilience against turbulence and enable efficient deployment, we design a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi>N</mi><mo>+</mo><mn>1</mn><mo>)</mo><mo>×</mo><mi>L</mi></mrow></semantics></math></inline-formula> hybrid strategy that integrates convolutional and Transformer blocks in every stage. Extensive simulations and optical experiments validate the effectiveness of our approach under various turbulence intensities and sampling rates as low as 1%. Compared with existing image-based and image-free methods, our model achieves superior performance in classification accuracy, computational efficiency, and robustness, which is important for potential low-resource real-time remote sensing applications.
format Article
id doaj-art-fb12d34aa2994d30bf914735b1f83be6
institution OA Journals
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-fb12d34aa2994d30bf914735b1f83be62025-08-20T02:36:30ZengMDPI AGSensors1424-82202025-07-012513413710.3390/s25134137Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free ApproachYin Cheng0Yusen Liao1Jun Ke2School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaIn remote sensing, object classification often suffers from severe degradation caused by atmospheric turbulence and low-signal conditions. Traditional image reconstruction approaches are computationally expensive and fragile under such conditions. In this work, we propose a novel image-free classification framework using single-pixel imaging (SPI), which directly classifies targets from 1D measurements without reconstructing the image. A learnable sampling matrix is introduced for structured light modulation, and a hybrid CNN-Transformer network (Hybrid-CTNet) is employed for robust feature extraction. To enhance resilience against turbulence and enable efficient deployment, we design a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi>N</mi><mo>+</mo><mn>1</mn><mo>)</mo><mo>×</mo><mi>L</mi></mrow></semantics></math></inline-formula> hybrid strategy that integrates convolutional and Transformer blocks in every stage. Extensive simulations and optical experiments validate the effectiveness of our approach under various turbulence intensities and sampling rates as low as 1%. Compared with existing image-based and image-free methods, our model achieves superior performance in classification accuracy, computational efficiency, and robustness, which is important for potential low-resource real-time remote sensing applications.https://www.mdpi.com/1424-8220/25/13/4137object classificationimage processingsingle pixel imagingatmospheric turbulence
spellingShingle Yin Cheng
Yusen Liao
Jun Ke
Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
Sensors
object classification
image processing
single pixel imaging
atmospheric turbulence
title Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
title_full Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
title_fullStr Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
title_full_unstemmed Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
title_short Turbulence-Resilient Object Classification in Remote Sensing Using a Single-Pixel Image-Free Approach
title_sort turbulence resilient object classification in remote sensing using a single pixel image free approach
topic object classification
image processing
single pixel imaging
atmospheric turbulence
url https://www.mdpi.com/1424-8220/25/13/4137
work_keys_str_mv AT yincheng turbulenceresilientobjectclassificationinremotesensingusingasinglepixelimagefreeapproach
AT yusenliao turbulenceresilientobjectclassificationinremotesensingusingasinglepixelimagefreeapproach
AT junke turbulenceresilientobjectclassificationinremotesensingusingasinglepixelimagefreeapproach