Multiscale and Multidimensional Weighted Network for Salient Object Detection in Optical Remote Sensing Images
- 20 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Abstract
Recent advancements have significantly benefited in salient object detection for optical remote sensing images (ORSI-SOD). Given the varying spatial resolutions and complex scenes characteristic of optical remote sensing images (ORSI), leveraging and integrating features across scales is vital. However, excessive feature integration can introduce significant noise and result in inaccurate saliency mapping. To address this issue, we propose the Multi-scale and Multi-dimensional Weighted Network for ORSI-SOD (WeightNet). The network adopts a two-stage design where the first stage generates multi-scale weighted information, and the second stage conducts indirect multi-scale feature weighted fusion. This design skillfully avoids the lack of scale adaptation and noise interference that may arise from direct multi-scale feature fusion. Furthermore, to enhance feature fusion and target localization precision, we introduce the Multi-Scale Weighted Feature Aggregation Module (MWFAM) and the Multi-Dimensional Feature Guidance Module (MDFGM). MWFAM facilitates multi-scale feature fusion while minimizing noise from cross-layer interactions. MDFGM specializes in precise target localization and enhancement of detail and edge information. Additionally, the introduction of a Multi-Scale Parallel Decoder (MPD) significantly boosts the decoder’s capability in identifying targets across various scales. Extensive qualitative and quantitative evaluations on three public ORSI datasets demonstrate the effectiveness and superiority of WeightNet over contemporary state-of-the-art models.Keywords
Funding Information
- Key Research and Development Projects of Shaanxi Province (2022GY-075)
- National Key Projects of China (2021XJTU0040)
This publication has 69 references indexed in Scilit:
- MEANet: An effective and lightweight solution for salient object detection in optical remote sensing imagesExpert Systems with Applications, 2023
- Aggregating transformers and CNNs for salient object detection in optical remote sensing imagesNeurocomputing, 2023
- Transformer guidance dual-stream network for salient object detection in optical remote sensing imagesNeural Computing and Applications, 2023
- Global–local–global context-aware network for salient object detection in optical remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Review of pixel-level remote sensing image fusion based on deep learningInformation Fusion, 2022
- Densely nested top-down flows for salient object detectionScience China Information Sciences, 2022
- CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advancesInformation Sciences, 2021
- Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency mapsPattern Recognition, 2020
- Saliency detection via multi-level integration and multi-scale fusion neural networksNeurocomputing, 2019
- Salient object detection: A surveyComputational Visual Media, 2019