结合对象单元和Transformer网络的城市功能区分类方法

鲁伟鹏; 贺清康; 李佳铃; 李诗逸; 陶超

doi:10.11834/jrs.20233036

浏览量 : 0 下载量: 82 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

结合对象单元和Transformer网络的城市功能区分类方法
Object Units and Transformer Networks Combined Urban Functional Zone Classification Method
2023年页码：1-13
网络出版日期： 2023-10-23 ，
DOI： 10.11834/jrs.20233036

扫描看全文

鲁伟鹏，贺清康，李佳铃，李诗逸，陶超.XXXX.结合对象单元和Transformer网络的城市功能区分类方法.遥感学报，XX（XX）： 1-13

LU Weipeng，He Qingkang，LI Jialing，LI Shiyi，TAO Chao. XXXX. Object Units and Transformer Networks Combined Urban Functional Zone Classification Method. National Remote Sensing Bulletin， XX（XX）：1-13
鲁伟鹏，贺清康，李佳铃，李诗逸，陶超.XXXX.结合对象单元和Transformer网络的城市功能区分类方法.遥感学报，XX（XX）： 1-13 DOI： 10.11834/jrs.20233036.

LU Weipeng，He Qingkang，LI Jialing，LI Shiyi，TAO Chao. XXXX. Object Units and Transformer Networks Combined Urban Functional Zone Classification Method. National Remote Sensing Bulletin， XX（XX）：1-13 DOI： 10.11834/jrs.20233036.

摘要

准确识别各类城市功能区并全面掌握其分布情况，对合理规划和科学管理城市至关重要。针对该问题，本文提出一种结合对象单元和Transformer网络的城市功能区分类方法。该方法首先以多尺度分割所获得的过分割对象作为最小分析单元，以避免出现同一分析单元包含多种城市功能区的情况。在此基础上，针对现有方法着重于对分析单元内部特征提取而忽略了分析单元之间的空间关系问题，提出利用Transformer框架和对象地理属性作为位置编码对不同分析单元之间的空间关系进行建模，从而实现兼顾分析单元内部特征和不同分析单元之间空间关系的城市功能区分类。实验结果表明，使用过分割对象作为最小分析单元能够更加准确地获取城市功能区地边界，从而避免基于规则格网单元所导致的锯齿状边缘及基于路网单元所导致地无法区分路网内不同功能区的问题。同时与仅考虑分析单元内部特征的传统方法相比，通过对不同分析单元之间的分析单元进行建模可有效提升城市功能区分类精度。

Abstract

Accurate extraction of urban functional zones (UFZs) and a comprehensive understanding of their spatial distribution play an important role in urban planning and management. This paper proposes a UFZ classification method combining object unit and Vision Transformer to address the problem. Firstly

this method utilizes the over-segmented object generated from the multi-scale segmentation method as analysis units to avoid that there are multiple kinds of UFZs in an object. Then

considering that current methods always focus on the inherent analysis of objects and ignore spatial relationships among them

Transformer is employed for spatial relationship modeling between objects

in which the geographic attributes of objects act as position embedding. In this way

the inherent features of a single analysis unit and inter-spatial features among objects are both taken into account for UFZ classification. The experimental results show that

compared with the results of the existing methods

the over-segmented objects can improve the boundary accuracy

avoiding the jagged boundaries resulting from grid units and the multi-UFZs in a single unit resulting from road-block units. Besides

the accuracy of UFZ classification increases by 13.9% to the method employing objects as analysis units and ignoring their spatial relationships.

关键词

城市功能区遥感深度学习空间关系建模Transformer

Keywords

urban functional zoneremote sensingdeep learningspatial relationship modelingTransformer

references

Baatz, Martin. 2000. "Multiresolution segmentation: an optimization approach for high quality multi-scale image segmentation." Angewandte geographische informationsverarbeitung:12-23.

Biljecki, Filip, and Koichi Ito. 2021. "Street view imagery in urban analytics and GIS: A review." Landscape and Urban Planning 215:104217 [DOI: 10.1016/j.landurbplan.2021.104217].

Chao, TAO, YIN Ziwei, ZHU Qing, and LI Haifeng. 2021. "Remote sensing image intelligent interpretation: from supervised learning to self-supervised learning." Acta Geodaetica et Cartographica Sinica 50 (8):1122 [DOI: 10.11947/j.AGCS.2021.20210089].

Chen, Zhanlong, Lulin Zhou, Wenhao Yu, Liang Wu, and Zhong Xie. 2020. "Identification of the urban functional regions considering the potential context of interest points." Acta Geodaetica et Cartographica Sinica 49:907-20

陈占龙, 周路林, 禹文豪, 吴亮, 谢忠. 2020. 顾及兴趣点潜在上下文关系的城市功能区识别. 测绘学报 49(07):907-20. [DOI: 10.11947/j.AGCS.2020.20190315].

Dosovitskiy, Alexey, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, and Sylvain Gelly. 2020. "An image is worth 16x16 words: Transformers for image recognition at scale." arXiv preprint arXiv:2010.11929 [DOI: 10.48550/arXiv.2010.11929].

Du, Shouhang, Shihong Du, Bo Liu, and Xiuyuan Zhang. 2021. "Mapping large-scale and fine-grained urban functional zones from VHR images using a multi-scale semantic segmentation network and object based approach." Remote Sensing of Environment 261:112480 [DOI: 10.1016/j.rse.2021.112480].

Du, Shouji, Shihong Du, Bo Liu, and Xiuyuan Zhang. 2019. "Context-enabled extraction of large-scale urban functional zones from very-high-resolution images: A multiscale segmentation approach." Remote Sensing 11 (16):1902 [DOI: 10.3390/rs11161902].

Du, Shouji, Shihong Du, Bo Liu, Xiuyuan Zhang, and Zhijia Zheng. 2020. "Large-scale urban functional zone mapping by integrating remote sensing images and open social data." GIScience & Remote Sensing 57 (3):411-30 [DOI: 10.1080/15481603.2020.1724707http://dx.doi.org/10.1080/15481603.2020.1724707].

Gao, Lianru, Zhu Han, Danfeng Hong, Bing Zhang, and Jocelyn Chanussot. 2021. "CyCU-Net: Cycle-consistency unmixing network by learning cascaded autoencoders." IEEE Transactions on Geoscience and Remote Sensing 60:1-14 [DOI: 10.1109/TGRS.2021.3064958http://dx.doi.org/10.1109/TGRS.2021.3064958].

Gong, Jianya, Mi Zhang, Xiangyun Hu, Zhan Zhang, Yansheng Li, and Liangcun Jiang. 2022. “The design of deep learning framework and model for intelligent remote sensing.” Acta Geodaetica et Cartographica Sinica 51(4):475-481

龚健雅,张觅,胡翔云,张展,李彦胜, 姜良存. 2022 .智能遥感深度学习框架与模型设计. 测绘学报(04), 475-487. [DOI:10.11947/j.AGCS.2022.20220027http://dx.doi.org/10.11947/j.AGCS.2022.20220027]

Gu, Yanyan, Limin Jiao, Ting Dong, Yandong Wang, and Gang Xu. 2018. "Spatial Distribution and Interaction Analysis of Urban Functional Areas Based on Multi-source Data." Geomatics and Information Science of Wuhan University 43:1113-21

谷岩岩, 焦利民, 董婷, 王艳东, 许刚. 2018. 基于多源数据的城市功能区识别及相互作用分析. 武汉大学学报(信息科学版) 43(07):1113-21. [DOI: 10.13203/j.whugis20160192].

He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

Li, Deren, Liangpei Zhang, and Guisong Xia. 2014. "Automatic Analysis and Mining of Remote Sensing Big Data." Acta Geodaetica et Cartographica Sinica 43:1211

李德仁, 张良培, 夏桂松. 2014. 遥感大数据自动分析与数据挖掘. 测绘学报 43(12):1211. [DOI: 10.13485/j.cnki.11-2089.2014.0187.].

Li, Yanyu, Geng Yuan, Yang Wen, Ju Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, and Jian Ren. 2022. EfficientFormer: Vision Transformers at MobileNet. Paper presented at Speed at Advances in Neural Information Processing Systems 35 NeurIPS 2022.

Liu, Baihua, Yingbin Deng, Miao Li, Ji Yang, and Tao Liu. 2021. "Classification schemes and identification methods for urban functional zone: A Review of Recent Papers." Applied Sciences 11 (21):9968 [DOI: 10.3390/app11219968].

Liu, Jing, Xiaoqing Zuo, Limin Wu, Liang Huang, and Zhaoyi Lu. 2013. "Water extraction of satellite images considering space and feature relationship." Acta Geodaetica et Cartographica Sinica 38:163-5

刘静, 左小清, 吴俐民, 黄亮, 卢昭羿. 2013. 顾及地物空间关系的卫星影像水系信息提取. 测绘科学 38(3):163-5. [DOI: 10.16251/j.cnki.1009-2307.2013.03.050.].

Lu, Weipeng, Chao Tao, Haifeng Li, Ji Qi, and Yansheng Li. 2022. "A unified deep learning framework for urban functional zone extraction based on multi-source heterogeneous data." Remote Sensing of Environment 270:112830 [DOI: 10.1016/j.rse.2021.112830].

Luo, Jiancheng, Xiaodong Hu, Tianjun Wu, Liu Wei, Liegang Xia, Haiping Yang, Yingwei Sun, et al. 2021. "Research on intelligent calculation model and method of precision land use/cover change information driven by high-resolution remote sensing." National Remote Sensing Bulletin 25:1351-73

骆剑承, 胡晓东, 吴田军, 刘巍, 夏列钢, 杨海平, 孙营伟, 徐楠, 张新, 沈占锋. 2021. 高分遥感驱动的精准土地利用与土地覆盖变化信息智能计算模型与方法研究. 遥感学报 25(7):1351-73. [DOI: 10.11834/jrs.20219402].

Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. Paper presented at the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18.

Sabater A., Montesano L., and Murillo A. C. 2022. Event Transformer. A sparse-aware solution for efficient event data processing. Paper presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Shu, Mi, and Shihong Du. 2022. "Forty Years' Progress and Challenges of Remote Sensing in National Land Survey." Journal of Geo-Information Science 24:597-616

舒弥, 杜世宏. 2022. 国土调查遥感40年进展与挑战. 地球信息科学学报 24(4):597-616. [DOI: 10.12082/dqxxkx.2022.210512].

Tao, Chao, Weipeng Lu, Ji Qi, and Hao Wang. 2020. "Spatial information considered network for scene classification." IEEE Geoscience and Remote Sensing Letters 18 (6):984-8 [DOI: 10.1109/LGRS.2020.2992929http://dx.doi.org/10.1109/LGRS.2020.2992929].

Troya-Galvis, Andrés, Pierre Gançarski, Nicolas Passat, and Laure Berti-Equille. 2015. "Unsupervised quantification of under-and over-segmentation for object-based remote sensing image analysis." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8 (5):1936-45 [DOI: 10.1109/JSTARS.2015.2424457http://dx.doi.org/10.1109/JSTARS.2015.2424457].

Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. "Attention is all you need." Advances in neural information processing systems 30 [DOI: 10.48550/arXiv.1706.03762].

Wu, Hao, Anqi Lin, Xudong Xing, Danxia Song, and Yan Li. 2021. “Identifying core driving factors of urban land use change from global land cover products and POI data using the random forest method”. International Journal of Applied Earth Observation and Geoinformation103:102475.[10.1016/j.jag.2021.102475http://dx.doi.org/10.1016/j.jag.2021.102475]

Wu, Hao, Wenting Luo, Anqi Lin, Fanghua Hao, Ana-Maria Olteanu-Raimond, Lanfa Liu, Yan Li. 2023. “SALT: A multifeature ensemble learning framework for mapping urban functional zones from VGI data and VHR images.” Computers, Environment and Urban Systems 100:101921.[DOI:10.1016/j.compenvurbsys.2022.101921http://dx.doi.org/10.1016/j.compenvurbsys.2022.101921]

Zhang, Xiuyuan, Shihong Du, and Qiao Wang. 2017. "Hierarchical semantic cognition for urban functional zones with VHR satellite images and POI data." ISPRS Journal of Photogrammetry and Remote Sensing 132:170-84 [DOI: 10.1016/j.isprsjprs.2017.09.007http://dx.doi.org/10.1016/j.isprsjprs.2017.09.007].

———. 2018. "Integrating bottom-up classification and top-down feedback for improving urban land-cover and functional-zone mapping." Remote Sensing of Environment 212:231-48 [DOI: 10.1016/j.rse.2018.05.006http://dx.doi.org/10.1016/j.rse.2018.05.006].

Zhao, Kun, Yongkun Liu, Siyuan Hao, Shaoxing Lu, Hongbin Liu, and Lijian Zhou. 2021. "Bounding boxes are all we need: street view image classification via context encoding of detected buildings." IEEE Transactions on Geoscience and Remote Sensing 60:1-17 [DOI: 10.1109/TGRS.2021.3064316http://dx.doi.org/10.1109/TGRS.2021.3064316].

Zhao, Wudi, Shanshan Li, An Li, Bing Zhang, and Jun Chen. 2021. "Deep fusion of hyperspectral images and multi-source remote sensing data for classification with convolutional neural network:." National Remote Sensing Bulletin 25:1489-502

赵伍迪, 李山山, 李安, 张兵, 陈俊. 2021. 结合深度学习的高光谱与多源遥感数据融合分类. 遥感学报 25(7):1489-502. [DOI:10.11834/jrs.20219117].

Zhao, Zhiyao, and Hongchao Fan. 2022. "Towards Exploring Patterns of Editing Behavior on OpenStreetMap." Journal of Geodesy and Geoinformation Science 5 (2):85 [DOI: 10.11947/j.JGGS.2022.0209].

Zhong, Yanfei, Yu Su, Siqi Wu, Zhendong Zheng, Ji Zhao, Ailong Ma, Qiqi Zhu, Richen Ye, Xiaoman Li, Petri Pellikka, Liangpei Zhang. 2020. “Open-source data-driven urban land-use mapping integrating point-line-polygon semantic objects: A case study of Chinese cities.” Remote Sensing of Environment 247:111838. [10.1016/j.rse.2020.111838http://dx.doi.org/10.1016/j.rse.2020.111838]

Zhou, Wen, Dongping Ming, Xianwei Lv, Keqi Zhou, Hanqing Bao, and Zhaoli Hong. 2020. "SO–CNN based urban functional zone fine division with VHR remote sensing image." Remote Sensing of Environment 236:111458 [DOI: 10.1016/j.rse.2019.111458].

文章被引用时，请邮件提醒。

提交

光学信号Token引导的异源遥感变化检测网络

高光谱遥感影像异常目标检测研究进展

基于多方向自适应感知网络的高光谱遥感图像分类

弱监督尺度自适应增强的高分辨率遥感影像场景分类

结合RGB-DSM图像和深度学习的城市樟树树冠检测