重庆邮电大学学报（自然科学版）2025，Vol.37Issue(1)：57-66,10.DOI:10.3979/j.issn.1673-825X.202312260433
联合边缘检测强化空间细节的语义分割方法
Semantic segmentation methods with enhanced spatial details by joint edge detection
摘要
Abstract
To address the issues of blurred edges and low accuracy in image semantic segmentation,this paper proposes an image semantic segmentation method based on edge-aware reinforcement of spatial details.An edge detection module is in-troduced into the semantic segmentation network to capture finer spatial details.The model adopts an encoder-decoder archi-tecture and uses the atrous spatial pyramid pooling(ASPP)module to extract semantic information.A bi-directional multi-level aggregation(BMLA)module is proposed to generate edge features and reinforce spatial details.A novel attention-based feature fusion module(AFFM)is designed to integrate the enhanced spatial features with the semantic features.Ex-periments on the Cityscapes and ADE20K datasets show that,compared with other mainstream semantic segmentation algo-rithms,the proposed method demonstrates strong competitiveness in segmentation performance.关键词
语义分割/边缘检测/编码器-解码器/注意力机制Key words
semantic segmentation/edge detection/encoder-decoder/attention mechanism分类
信息技术与安全科学引用本文复制引用
刘伯红,蒋佳跞..联合边缘检测强化空间细节的语义分割方法[J].重庆邮电大学学报（自然科学版）,2025,37(1):57-66,10.基金项目
国家自然科学基金项目(62272075)National Natural Science Foundation of China(62272075) （62272075）
