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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |