文献类型：期刊文献

英文题名：DSC-Net: Enhancing Blind Road Semantic Segmentation with Visual Sensor Using a Dual-Branch Swin-CNN Architecture

作者：Yuan, Ying[1];Du, Yu[1];Ma, Yan[1];Lv, Hejun[1]

第一作者：Yuan, Ying

通讯作者：Du, Y[1]

机构：[1]Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室|北京联合大学机器人学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2024

卷号：24

期号：18

外文期刊名：SENSORS

收录：;EI(收录号：20244017141592);Scopus(收录号：2-s2.0-85205310636);WOS:【SCI-EXPANDED(收录号:WOS:001323671900001)】；

基金：This work was primarily supported by the Vehicle Road Cooperative Autonomous Driving Fusion Control Project. Funding has also been provided by the Academic Research Projects of Beijing Union University (Nos. ZK80202003, ZK90202105). In addition, the project received sponsorship from the Science and Technology Program of the Beijing Municipal Education Commission (Nos. KM202111417007, KM202211417006). These combined resources have significantly contributed to the research and development efforts.

语种：英文

外文关键词：semantic segmentation; transformer; blind roads segmentation; edge information; visual sensors

摘要：In modern urban environments, visual sensors are crucial for enhancing the functionality of navigation systems, particularly for devices designed for visually impaired individuals. The high-resolution images captured by these sensors form the basis for understanding the surrounding environment and identifying key landmarks. However, the core challenge in the semantic segmentation of blind roads lies in the effective extraction of global context and edge features. Most existing methods rely on Convolutional Neural Networks (CNNs), whose inherent inductive biases limit their ability to capture global context and accurately detect discontinuous features such as gaps and obstructions in blind roads. To overcome these limitations, we introduce Dual-Branch Swin-CNN Net(DSC-Net), a new method that integrates the global modeling capabilities of the Swin-Transformer with the CNN-based U-Net architecture. This combination allows for the hierarchical extraction of both fine and coarse features. First, the Spatial Blending Module (SBM) mitigates blurring of target information caused by object occlusion to enhance accuracy. The hybrid attention module (HAM), embedded within the Inverted Residual Module (IRM), sharpens the detection of blind road boundaries, while the IRM improves the speed of network processing. In tests on a specialized dataset designed for blind road semantic segmentation in real-world scenarios, our method achieved an impressive mIoU of 97.72%. Additionally, it demonstrated exceptional performance on other public datasets.