| 基于实例分割模型的建筑物自动提取 |
| |
| 引用本文： | 瑚敏君,冯德俊,李强.基于实例分割模型的建筑物自动提取[J].测绘通报,2020,0(4):16. |
| |
| 作者姓名： | 瑚敏君 冯德俊 李强 |
| |
| 作者单位： | 1. 西南交通大学地球科学与环境工程学院, 四川 成都 611756;2. 四川省地质工程勘察院集团有限公司, 四川 成都 610036 |
| |
| 基金项目： | 国家重点研发计划（2016YFC0803105） |
| |
| 摘 要： | 传统的遥感影像目标提取方法大多采用目视解译或基于像素信息进行处理，难以适用于高分辨率影像中的复杂场景。而现有的卷积神经网络语义分割模型，由于难以达到较高的精度会出现提取目标粘连的情况。针对该问题，本文对实例分割模型Mask R-CNN进行改进，提出了一种高效、准确的高分辨率遥感影像建筑物提取算法。首先，在Mask R-CNN原有的特征提取部分每个层级的特征图后再增加一层卷积操作，以降低上采样造成的混叠效应；然后，在原有掩膜预测结构的基础上增加一个分支，改善掩膜预测的效果；最后，将改进后的网络在建筑物数据集上进行训练。结果表明，本文方法能够准确独立预测每个建筑物顶部，没有目标粘连情况，且mAP值较Mask R-CNN有所提高，能够有效实现遥感影像建筑物精细化提取。
|
| 关 键 词： | 卷积神经网络 实例分割 Mask R-CNN 建筑物 特征提取 |
| 收稿时间： | 2019-07-05 |
| 修稿时间： | 2020-03-01 |
Automatic extraction of buildings based on instance segmentation model |
| |
| HU Minjun,FENG Dejun,LI Qiang.Automatic extraction of buildings based on instance segmentation model[J].Bulletin of Surveying and Mapping,2020,0(4):16. |
| |
| Authors: | HU Minjun FENG Dejun LI Qiang |
| |
| Institution: | 1. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China;2. Sichuan Geological Engineering Investigation Institute Group Co., Ltd., Chengdu 610036, China |
| |
| Abstract: | Traditional remote sensing image target extraction methods mostly use visual interpretation or processing of pixel information, which is difficult to apply to complex scenes of high-resolution remote sensing images. However, the existing convolutional neural network semantic segmentation model may cause the extraction of target adhesion due to difficulty in achieving high precision. Aiming at this problem, this paper improves the instance segmentation model Mask R-CNN and proposes an efficient and accurate high-resolution remote sensing image building extraction algorithm. Firstly, convolution operation is added to the original feature extraction part of the Mask R-CNN to reduce the aliasing effect caused by upsampling. Then, a branch is added to the original mask prediction structure to improve the effect of mask prediction. Finally, train the improved network on the building dataset, the results show that the proposed method can accurately predict the top of each building independently, without target adhesion, and the mAP value is improved compared with the Mask R-CNN, which can effectively realize the refined extraction of remote sensing image buildings. |
| |
| Keywords: | convolutional neural network instance segmentation Mask R-CNN building feature extraction |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
|
