To read this content please select one of the options below:

MFLD: lightweight object detection with multi-receptive field and long-range dependency in remote sensing images

Weixing Wang (School of Artificial Intelligence, The Open University of Guangdong, Guangzhou, China)
Yixia Chen (College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China)
Mingwei Lin (College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China)

International Journal of Intelligent Computing and Cybernetics

ISSN: 1756-378X

Article publication date: 9 September 2024

Issue publication date: 11 November 2024

29

Abstract

Purpose

Based on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.

Design/methodology/approach

To alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.

Findings

To concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.

Originality/value

This paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

Keywords

Acknowledgements

This research work was supported by the Guangzhou Science and Technology Plan Project under Grant No. 202102080382.

Citation

Wang, W., Chen, Y. and Lin, M. (2024), "MFLD: lightweight object detection with multi-receptive field and long-range dependency in remote sensing images", International Journal of Intelligent Computing and Cybernetics, Vol. 17 No. 4, pp. 805-823. https://doi.org/10.1108/IJICC-01-2024-0020

Publisher

:

Emerald Publishing Limited

Copyright © 2024, Emerald Publishing Limited

Related articles