Lightweight faster R-CNN for object detection in optical remote sensing images

Abstract Various applications in remote sensing rely on object detection approaches, such as urban detection, precision farming, and disaster prediction. Faster RCNN has gained popularity for its performance but comes with significant computational and storage demands. Model compression techniques l...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrew Magdy, Marwa S. Moustafa, Hala M. Ebied, Mohamed F. Tolba
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99242-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190907537620992
author Andrew Magdy
Marwa S. Moustafa
Hala M. Ebied
Mohamed F. Tolba
author_facet Andrew Magdy
Marwa S. Moustafa
Hala M. Ebied
Mohamed F. Tolba
author_sort Andrew Magdy
collection DOAJ
description Abstract Various applications in remote sensing rely on object detection approaches, such as urban detection, precision farming, and disaster prediction. Faster RCNN has gained popularity for its performance but comes with significant computational and storage demands. Model compression techniques like pruning and quantization are frequently employed to mitigate these challenges. This paper introduces a novel bi-stage compression approach to create a lightweight Faster R-CNN for satellite images with minimal performance degradation. The proposed approach employs two distinct phases: aware training and post-training compression. First, aware training employs mixed-precision FP16 computation, which enhances training speed by a factor of 1.5 to 5.5 while preserving model accuracy and optimizing memory efficiency. Second, post-training compression applies unstructured weight pruning to eliminate redundant parameters, followed by dynamic quantization to reduce precision, thereby minimizing the model size at runtime and computational load. The proposed approach was assessed on the NWPU VHR-10 and Ship datasets. The results demonstrate an average 25.6% reduction in model size and a 56.6% reduction in parameters while maintaining the mean Average Precision (mAP).
format Article
id doaj-art-bc91c387203543f997d6c3373dccabb6
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-bc91c387203543f997d6c3373dccabb62025-08-20T02:15:07ZengNature PortfolioScientific Reports2045-23222025-05-0115111410.1038/s41598-025-99242-yLightweight faster R-CNN for object detection in optical remote sensing imagesAndrew Magdy0Marwa S. Moustafa1Hala M. Ebied2Mohamed F. Tolba3Department of Scientific Computing, Faculty of Computer and Information Sciences, Ain Shams UniversityDepartment of Image Processing and Its Application, National Authority for Remote Sensing and Space Sciences (NARSS)Department of Scientific Computing, Faculty of Computer and Information Sciences, Ain Shams UniversityDepartment of Scientific Computing, Faculty of Computer and Information Sciences, Ain Shams UniversityAbstract Various applications in remote sensing rely on object detection approaches, such as urban detection, precision farming, and disaster prediction. Faster RCNN has gained popularity for its performance but comes with significant computational and storage demands. Model compression techniques like pruning and quantization are frequently employed to mitigate these challenges. This paper introduces a novel bi-stage compression approach to create a lightweight Faster R-CNN for satellite images with minimal performance degradation. The proposed approach employs two distinct phases: aware training and post-training compression. First, aware training employs mixed-precision FP16 computation, which enhances training speed by a factor of 1.5 to 5.5 while preserving model accuracy and optimizing memory efficiency. Second, post-training compression applies unstructured weight pruning to eliminate redundant parameters, followed by dynamic quantization to reduce precision, thereby minimizing the model size at runtime and computational load. The proposed approach was assessed on the NWPU VHR-10 and Ship datasets. The results demonstrate an average 25.6% reduction in model size and a 56.6% reduction in parameters while maintaining the mean Average Precision (mAP).https://doi.org/10.1038/s41598-025-99242-yFaster R-CNNPruningQuantization
spellingShingle Andrew Magdy
Marwa S. Moustafa
Hala M. Ebied
Mohamed F. Tolba
Lightweight faster R-CNN for object detection in optical remote sensing images
Scientific Reports
Faster R-CNN
Pruning
Quantization
title Lightweight faster R-CNN for object detection in optical remote sensing images
title_full Lightweight faster R-CNN for object detection in optical remote sensing images
title_fullStr Lightweight faster R-CNN for object detection in optical remote sensing images
title_full_unstemmed Lightweight faster R-CNN for object detection in optical remote sensing images
title_short Lightweight faster R-CNN for object detection in optical remote sensing images
title_sort lightweight faster r cnn for object detection in optical remote sensing images
topic Faster R-CNN
Pruning
Quantization
url https://doi.org/10.1038/s41598-025-99242-y
work_keys_str_mv AT andrewmagdy lightweightfasterrcnnforobjectdetectioninopticalremotesensingimages
AT marwasmoustafa lightweightfasterrcnnforobjectdetectioninopticalremotesensingimages
AT halamebied lightweightfasterrcnnforobjectdetectioninopticalremotesensingimages
AT mohamedftolba lightweightfasterrcnnforobjectdetectioninopticalremotesensingimages