并行路径与强注意力机制遥感图像建筑物分割  

Parallel path and strong attention mechanism for building segmentation in remote sensing images

作　　者：杨坚华 张浩[1,2,3,4] 花海洋[1,2,3] YANG Jianhua;ZHANG Hao;HUA Haiyang(Key Laboratory of Opto-Electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院光电信息处理重点实验室,辽宁沈阳110016 [2]中国科学院沈阳自动化研究所,辽宁沈阳110016 [3]中国科学院机器人与智能制造创新研究院,辽宁沈阳110169 [4]中国科学院大学,北京100049

出　　处：《光学精密工程》2023年第2期234-245,共12页Optics and Precision Engineering

基　　金：中科院创新基金资助项目(No.E01Z040101)。

摘　　要：遥感图像建筑物分割广泛应用于城市规划及军事领域,是当前遥感领域的研究热点。针对遥感图像中建筑物之间尺度变化较大、建筑物遮挡、建筑物阴影与建筑物边缘相似所导致建筑物分割精度较低的问题,提出一种并行路径和强注意力机制的卷积神经网络模型。该模型基于ResNet网络残差连接的思想,以ResNet为基础网络提高网络深度,并采用卷积下采样得到并行路径,提取建筑物的多尺度特征,以减少建筑物之间尺度变化的影响。然后加入强注意力机制,增强多尺度信息的融合效果,增加不同特征之间的区分度,抑制建筑物遮挡及建筑物阴影的影响。最后,在多尺度融合特征后加入金字塔空间池化模块,抑制分割结果中建筑物内部孔洞的出现,提高分割精度。在WHU以及Massachusetts Buildings公开数据集进行实验,分别从MIoU,Recall,Precision,F1-score 4个指标对分割结果进行量化比较,在Massachusetts Buildings数据集中MIoU达到72.84%,相较于ResUNet-a提升1.46%,能够有效提高遥感影像中建筑的分割精度。Building segmentation in remote sensing images is widely used in urban planning and military fields, and is a current focus of research in the remote sensing field. To solve the problems of large-scale changes between buildings, building occlusion, and similar building shadows and edges in remote sensing images, which result in low building segmentation accuracy, a convolutional neural network with parallel paths and strong attention mechanism was developed. The model was based on the idea of residual connections of a ResNet network, and used ResNet as the basic network to improve the network depth and convolution downsampling to obtain parallel paths to extract multi-scale features of buildings to reduce the influence of scale changes between buildings. A strong attention mechanism was then added to enhance the fusion effect of the multi-scale information and discrimination of different features, and suppress the influence of building occlusion and shadows. Finally, a pyramid space pooling module was added after the multiscale fusion features to suppress the appearance of holes inside the building in the segmentation result and improve the segmentation accuracy. Experiments were conducted on the WHU and Massachusetts Buildings public datasets, and the segmentation results were quantitatively compared using four indicators, namely MIoU, recall, precision, and F1-score. In the Massachusetts Buildings dataset, MIoU reaches 72.84%, which is 1.46% higher than the MIoU obtained with ResUNet-a. Thus, the model effectively improved the segmentation accuracy of buildings in remote sensing images.

关 键 词：遥感图像 建筑物分割 并行路径 强注意力机制 金字塔空间池化 

分 类 号：P236[天文地球—摄影测量与遥感]