Enhancing DeepLabv3+ With Multiscale Sparse-Aware Dilated Convolution and Boundary-Interactive ASPP for River Ice Segmentation
- 23 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Abstract
Accurate segmentation of river ice in remote sensing imagery remains challenging due to heterogeneous ice textures, fragmented floes, and ambiguous ice–water boundaries. While DeepLabv3+ effectively captures multi-scale context, its standard atrous convolution suffers from uniform sampling and gridding effects, which limit boundary discrimination in complex river ice scenes. To address these issues, we propose a lightweight enhancement to DeepLabv3+ that integrates regionally weighted dilated convolution, a coordinated dilation configuration strategy, and a boundary-aware refinement branch. The proposed design improves central feature aggregation while preserving global context, without introducing additional computational overhead. Experiments on the NWPU_YRCC2 dataset demonstrate a 1.95% mIoU improvement over the baseline DeepLabv3+, validating the effectiveness of the proposed framework for precise and efficient river ice segmentation.Keywords
Funding Information
- Inner Mongolia Key Research and Development and Achievement Transformation Project (2023YFSH0043)
This publication has 17 references indexed in Scilit:
- ECASeg: Enhancing Semantic Segmentation with Edge Context and Attention StrategyProcedia Computer Science, 2025
- Frequency-Adaptive Dilated Convolution for Semantic Segmentation2024
- Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation2024
- DynIceData: a gridded ice–water classification dataset at short-time intervals based on observations from multiple satellites over the marginal ice zoneBig Earth Data, 2023
- FastICENet: A real-time and accurate semantic segmentation model for aerial remote sensing river ice imageSignal Processing, 2023
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic SegmentationInternational Journal of Computer Vision, 2021
- Rethinking BiSeNet For Real-time Semantic Segmentation2021
- Detection and Semantic Segmentation of Disaster Damage in UAV FootageJournal of Computing in Civil Engineering, 2021
- Pyramid Scene Parsing Network2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015