基于边缘特征和注意力机制的图像语义分割  

Image Semantic Segmentation Based on Edge Features and Attention Mechanism

作　　者：王军[1,2] 张霁云 程勇 WANG Jun;ZHANG Ji-Yun;CHENG Yong(School of Computer Science,Nanjing University of Information Science and Technology,Nanjing 210044,China;Science and Technology Industry Division,Nanjing University of Information Science and Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学计算机学院,南京210044 [2]南京信息工程大学科技产业处,南京210044

出　　处：《计算机系统应用》2024年第7期63-73,共11页Computer Systems & Applications

基　　金：国家自然科学基金(41975183)。

摘　　要：在语义分割任务中,编码器的下采样过程会导致分辨率降低,造成图像空间信息细节的丢失,因此在物体边缘会出现分割不连续或者错误分割的现象,进而对整体分割性能产生负面影响.针对上述问题,提出基于边缘特征和注意力机制的图像语义分割模型EASSNet.首先,使用边缘检测算子计算原始图像的边缘图,通过池化下采样和卷积运算提取边缘特征.接着,将边缘特征融合到经过编码器提取的深层语义特征当中,恢复经过下采样的特征图像的空间细节信息,并且通过注意力机制来强化有意义的信息,从而提高物体边缘分割的准确性,进而提升语义分割的整体性能.最后,EASSNet在PASCAL VOC 2012和Cityscapes数据集上的平均交并比分别达到85.9%和76.7%,与当前流行的语义分割网络相比,整体分割性能和物体边缘的分割效果都具有明显优势.In semantic segmentation tasks,the downsampling process of the encoder can lead to a decrease in resolution,resulting in the loss of spatial information details in the image.As a result,segmentation discontinuity or incorrect segmentation may occur at object edges,which can damage overall segmentation performance.To address the above issues,an image semantic segmentation model EASSNet based on edge features and attention mechanisms is proposed.Firstly,the edge detection operator is used to calculate the edge map of the original image,and edge features are extracted through pooling downsampling and convolution operations.Next,edge features are fused into deep semantic features extracted by the encoder,restoring the spatial detail information of downsampled feature images,and strengthening meaningful information through attention mechanisms to improve the accuracy of object edge segmentation and overall semantic segmentation performance.Finally,EASSNet achieves the average intersection over the union of 85.9%and 76.7%on the PASCAL VOC 2012 and Cityscapes datasets,respectively.Compared with current popular semantic segmentation networks,EASSNet has significant advantages in overall segmentation performance and object edge segmentation.

关 键 词：语义分割 空间细节信息 边缘特征 特征融合 注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]