Innovative Lightweight Detection for Airborne Remote Sensing: Integrating G-Shuffle and Dynamic Multiscale Pyramid Networks
Lists
Only you see this
Abstract
To address the challenges of significant scale variations and difficulty in extracting discriminative features for small targets in airborne remote sensing object detection, while considering the constraints and efficiency requirements of onboard systems, this article proposes a lightweight detection algorithm. First, a structural reparameterization strategy is applied to optimize depthwise separable convolutions, simplifying complex structures during the inference stage, which improves inference speed and memory utilization. Second, the G-Shuffle module is designed to significantly enhance feature extraction efficiency and interchannel information interaction, balancing computational complexity and detection accuracy. Lastly, a dynamic multiscale pyramid network is introduced, employing pyramid convolution to effectively extract and fuse multiscale features. Additionally, a channel attention network is integrated to establish channel interconnections, expanding the receptive field and enhancing the extraction of finegrained features at different scales, thereby improving the detection capability for targets of various sizes, especially small targets. Experimental results demonstrate that the proposed method achieves a [email protected] of 0.552 and [email protected]:0.95 of 0.265 on the AI-TOD dataset, with a 2.7 ms improvement in inference speed and a 14% reduction in model parameters. These results indicate superior performance across multiple metrics compared to existing state-of-the-art methods, proving the method's potential and practicality for airborne remote sensing object detection.
BibTeX
@article{liang2025innovative,
author = {Ruofei Liang and Yigang Cen and Yigang Cen and Fugui Zhang and Yansen Huang and Fei Gan},
title = {{Innovative Lightweight Detection for Airborne Remote Sensing: Integrating G-Shuffle and Dynamic Multiscale Pyramid Networks}},
journal = {IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens.},
year = {2025},
doi = {10.1109/jstars.2024.3509691},
}Loading related content...