改进DeepLabV3+网络的露天矿挡墙分割方法  

Semantic segmentation method of safety retaining wall in open pit mine with improved DeepLabV3+network

作　　者：马旭 杨立东[1] 郭勇[1] 赵艳锋[1] Ma Xu;Yang Lidong;Guo Yong;Zhao Yanfeng(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014000,China)

机构地区：[1]内蒙古科技大学信息工程学院,包头014000

出　　处：《电子测量技术》2023年第10期92-97,共6页Electronic Measurement Technology

基　　金：国家自然科学基金(62161040);内蒙古自然科学基金(2021MS06030);内蒙古科技计划项目(2021GG0023);内蒙古自治区高等学校青年科技英才支持计划(NJYT22056)项目资助。

摘　　要：为抑制露天矿场复杂环境下的背景干扰,对安全挡墙进行精确的语义分割,提出了一种基于改进DeepLabV3+网络的露天矿安全挡墙分割方法。首先,主干网络采用轻量级的MobileNetV2网络,通过深度可分离卷积和倒残差结构有效降低了网络参数量和计算量。然后,加入混合注意力模块进行通道及空间上的特征强化,可避免边缘信息丢失。最后,利用数据增强和迁移学习解决目标数据集较少的问题,提高模型的泛化能力。实验结果证明,该方法有较好的分割效果,MIOU和MPA分别为85.06%、92.94%,均优于原网络和其他经典网络模型。该方法能够精确地分割露天矿安全挡墙,有较好的实际应用价值。In order to suppress the background interference in the complex environment of the open-pit mine and perform accurate semantic segmentation of the safety retaining wall,a segmentation method of the safety retaining wall of the open-pit mine based on the improved DeepLabV3+network is proposed.First,the backbone network adopts the lightweight MobileNetV2 network,which effectively reduces the amount of network parameters and computation through the depthwise separable convolution and inverted residual structure.Then,a hybrid attention module is added for channel and spatial feature enhancement,which can avoid the loss of edge information.Finally,data augmentation and transfer learning are used to solve problems with fewer target datasets and improve the generalization ability of the model.The experimental results show that the method has a good segmentation effect,with MIOU and MPA of 85.06%and 92.94%,respectively,which are better than the original network and other classic network models.

关 键 词：语义分割 MobileNetV2 混合注意力 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]