Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning

WANG Yan; LIU Wanjun; TAN Yali; LI Yu

doi:10.13203/j.whugis20210377

Volume 48 Issue 6

Jun. 2023

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2023 > 48(6): 950-959. > DOI: 10.13203/j.whugis20210377

WANG Yan, LIU Wanjun, TAN Yali, LI Yu. Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning[J]. Geomatics and Information Science of Wuhan University, 2023, 48(6): 950-959. DOI: 10.13203/j.whugis20210377

Citation:

PDF (25506 KB)

Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning

WANG Yan^1,,
LIU Wanjun²,
TAN Yali¹,
LI Yu^1, ,

1.
School of Geomatics, Liaoning Technical University, Fuxin 123000, China
2.
School of Software, Liaoning Technical University, Huludao 125000, China

More Information

Received Date: February 26, 2022
Available Online: June 11, 2023
Published Date: June 04, 2023

Graphical Abstract

Abstract

Abstract

Objectives Although remote sensing image is one of the main data sources for the classification of urban functional areas, it is rare to use remote sensing images to classify urban functional areas and extract their attribute information. At present, the classification methods of urban functional areas based on remote sensing images usually need manual interpretation, point of interest data assistance, information questionnaire survey and so on. This kind of method not only needs a lot of manual operation, but also needs other external information sources except remote sensing images.
Methods In order to solve the above problems, a sliding window-reasoning method for urban functional area classification is proposed by using convolutional neural network (CNN) to identify sliding window, extract image semantic tags, and combine semantic reasoning mechanism, which can quickly realize urban functional area classification only by remote sensing images. First, a two-level classification table of urban functional areas is established, and the training samples are marked with the second-level urban functional areas, and the training CNN is used as the recognizer. Second, using the designed overlapping sliding window recognition pattern, the trained re-cognizer is used to identify the types of features in the sliding window area, and to determine the type of urban functional area. Finally, a weighted scoring mechanism is designed as the implementation of semantic reasoning, and the semantic reasoning objects are all the recognition results. And, the type of urban functional areas of each region is determined, and the urban functional areas of large-scale remote sensing images are classified.
Results Using simulated images and high-resolution remote sensing image experiments, the total classification accuracy of simulated image experiments based on confusion matrix can reach 94.50%, and the total classification accuracy of real remote sensing image experiments based on confusion matrix can reach 92.04%.
Conclusions The purpose of the sliding window-reasoning method is to deal with the multi-semantic label results produced by the sliding window recognition through the semantic reasoning method, and to determine the real urban functional area results of the identified objects through multiple semantic tags. The results show that the method of CNN sliding window recognition combined with semantic reasoning is feasible and effective to classify urban functional areas directly using large-scale remote sensing images without the assistance of other information.
- urban functional area,
- image classification,
- convolutional neural network,
- sliding window recognition,
- semantic reasoning,
- voting mechanism

FullText(HTML)

References (24)

References

[1]	吴海平, 黄世存. 基于深度学习的新增建设用地信息提取试验研究: 全国土地利用遥感监测工程创新探索[J]. 国土资源遥感, 2019, 31(4): 159-166. https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201904025.htm Wu Haiping, Huang Shicun. Research on New Construction Land Information Extraction Based on Deep Learning: Innovation Exploration of the National Project of Land Use Monitoring via Remote Sensing[J]. Remote Sensing for Land & Resources, 2019, 31(4): 159-166. https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201904025.htm
[2]	陈逸敏, 黎夏. 机器学习在城市空间演化模拟中的应用与新趋势[J]. 武汉大学学报(信息科学版), 2020, 45(12): 1884-1889. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202012007.htm Chen Yimin, Li Xia. Applications and New Trends of Machine Learning in Urban Simulation Research[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1884-1889. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202012007.htm
[3]	郝文璇, 仝德, 刘青, 等. 改造功能区划定与分类规划管理: 来自深圳城市更新的经验和探讨[J]. 城市发展研究, 2015, 22(10): 42-48. doi: 10.3969/j.issn.1006-3862.2015.10.006 Hao Wenxuan, Tong De, Liu Qing, et al. The Delimitation and Classified Planning and Management of Transformation Function Region: The Experience and Exploration of Urban Renewal in Shenzhen[J]. Urban Development Studies, 2015, 22(10): 42-48. doi: 10.3969/j.issn.1006-3862.2015.10.006
[4]	李志学, 莫文波, 周松林, 等. 空间主成分分析的城市生活便利度指数研究: 以长沙市为例[J]. 测绘地理信息, 2021, 46(2): 110-115. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202102026.htm Li Zhixue, Mo Wenbo, Zhou Songlin, et al. Urban Life Convenience Index Based on Spatial Principal Component Analysis: A Case Study of Changsha City[J]. Journal of Geomatics, 2021, 46(2): 110-115. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202102026.htm
[5]	张慧芳, 张鹏林, 晁剑. 使用多尺度模糊融合的高分影像变化检测[J]. 武汉大学学报(信息科学版), 2022, 47(2): 296-303. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202202013.htm Zhang Huifang, Zhang Penglin, Chao Jian. Change Detection by Multi-scale Fuzzy Fusion on High Resolution Images[J]. Geomatics and Information Science of Wuhan University, 2022, 47(2): 296-303. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202202013.htm
[6]	徐敬海, 杜东升, 李枝军, 等. 一种应用传感器网和实景三维模型的复杂建筑物实时动态监测方法[J]. 武汉大学学报(信息科学版), 2021, 46(5): 630-639. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202105004.htm Xu Jinghai, Du Dongsheng, Li Zhijun, et al. A Real-time Dynamic Monitoring Method for Complex Building Applying Sensor Network and Reality 3D Model[J]. Geomatics and Information Science of Wuhan University, 2021, 46(5): 630-639. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202105004.htm
[7]	祖立辉, 杨静, 苗世源. 基于遥感影像的临湘市土地利用/覆盖时空变化研究[J]. 测绘地理信息, 2021, 46(2): 30-35. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202102007.htm Zu Lihu, Yang Jing, Miao Shiyuan. Spatial-temporal Change of Land Use/Cover in Linxiang City Based on Remote Sensing Images[J]. Journal of Geomatics, 2021, 46(2): 30-35. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202102007.htm
[8]	曲畅, 任玉环, 刘亚岚, 等. POI辅助下的高分辨率遥感影像城市建筑物功能分类研究[J]. 地球信息科学学报, 2017, 19(6): 831-837. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201706013.htm Qu Chang, Ren Yuhuan, Liu Yalan, et al. Functional Classification of Urban Buildings in High Resolution Remote Sensing Images Through POI-Assisted Analysis[J]. Journal of Geo⁃Information Science, 2017, 19(6): 831-837. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201706013.htm
[9]	郑力夫, 沈凌云, 刘慧平, 等. 基于在线地图数据的城市混合功能二三维划分方法研究[J]. 测绘地理信息, 2022, 47(S1): 188-193. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG2022S1041.htm Zheng Lifu, Shen Lingyun, Liu Huiping, et al. Quantitative Identification of Urban Mixed Functions Based on Multidimensional Data Obtained from Online Map[J]. Journal of Geomatics, 2022, 47(S1): 188-193. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG2022S1041.htm
[10]	谷岩岩, 焦利民, 董婷, 等. 基于多源数据的城市功能区识别及相互作用分析[J]. 武汉大学学报(信息科学版), 2018, 43(7): 1113-1121. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201807021.htm Gu Yanyan, Jiao Limin, Dong Ting, et al. Spatial Distribution and Interaction Analysis of Urban Functional Areas Based on Multi-source Data[J]. Geomatics and Information Science of Wuhan University, 2018, 43(7): 1113-1121. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201807021.htm
[11]	黄怡敏, 邵世维, 雷英哲, 等. 运用网络核密度估计与克里格插值识别城市功能区[J]. 测绘地理信息, 2019, 44(4): 14-18. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201904003.htm Huang Yimin, Shao Shiwei, Lei Yingzhe, et al. Identification of Urban Functional Zones Using Network Kernel Density Estimation and Kriging Interpolation[J]. Journal of Geomatics, 2019, 44(4): 14-18. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201904003.htm
[12]	彭正洪, 孙志豪, 程青, 等. 利用时序手机通话数据识别城市用地功能[J]. 武汉大学学报(信息科学版), 2018, 43(9): 1399-1407. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201809017.htm Peng Zhenghong, Sun Zhihao, Cheng Qing, et al. Urban Land Use Function Recognition Method Using Sequential Mobile Phone Data[J]. Geomatics and Information Science of Wuhan University, 2018, 43(9): 1399-1407. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201809017.htm
[13]	姚尧, 张亚涛, 关庆锋, 等. 使用时序出租车轨迹识别多层次城市功能结构[J]. 武汉大学学报(信息科学版), 2019, 44(6): 875-884. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201906013.htm Yao Yao, Zhang Yatao, Guan Qingfeng, et al. Sensing Multi-level Urban Functional Structures by Using Time Series Taxi Trajectory Data[J]. Geomatics and Information Science of Wuhan University, 2019, 44(6): 875-884. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201906013.htm
[14]	Zhou W, Ming D P, Lü X W, et al. SO-CNN Based Urban Functional Zone Fine Division with VHR Remote Sensing Image[J]. Remote Sensing of Environment, 2020, 236: 111458.
[15]	Yu J, Zeng P, Yu Y Y, et al. A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data[J]. Remote Sensing, 2022, 14(5): 1128.
[16]	Lecun Y, Bottou L, Bengio Y, et al. Gradient-based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[17]	Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks[J]. Communications of the ACM, 2016, 60(6): 84-90.
[18]	Kim J, Lee J K, Lee K M. Accurate Image Super-resolution Using very Deep Convolutional Networks[C]// IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
[19]	Szegedy C, Liu W, Jia Y Q, et al. Going Deeper with Convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015.
[20]	Tian T, Chu Z, Hu Q, et al. Class-Wise Fully Convolutional Network for Semantic Segmentation of Remote Sensing Images[J]. Remote Sensing, 2021, 13(10): 3211.
[21]	胡敏, 张柯柯, 王晓华, 等. 结合滑动窗口动态时间规整和CNN的视频人脸表情识别[J]. 中国图象图形学报, 2018, 23(8): 1144-1153. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201808004.htm Hu Min, Zhang Keke, Wang Xiaohua, et al. Video Facial Expression Recognition Combined with Sli-ding Window Dynamic Time Warping and CNN[J]. Journal of Image and Graphics, 2018, 23(8): 1144-1153. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201808004.htm
[22]	Gimpel K, Smith N A. Softmax-margin CRFS: Training Log-linear Models with Cost Functions[C]// Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Los Angeles, USA, 2010.
[23]	Eckle K, Schmidt-Hieber J. A Comparison of Deep Networks with ReLU Activation Function and Linear Spline-type Methods[J]. Neural Networks: the Official Journal of the International Neural Network Society, 2019, 110: 232-242.
[24]	Xia G S, Hu J W, Hu F, et al. AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(7): 3965-3981.

[1]	ZHU Shaolin, YUE Dongjie, HE Lina, CHEN Jian, LIU Shengnan. BDS-2/BDS-3 Joint Triple-Frequency Precise Point Positioning Models and Bias Characteristic Analysis[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12): 2049-2059. DOI: 10.13203/j.whugis20210273
[2]	LIU Zhiqiang, YUE Dongjie, WANG Hu, ZHENG Dehua. An Approach for Real-Time GPS/GLONASS Satellite Clock Estimation with GLONASS Code Inter-Frequency Biases Compensation[J]. Geomatics and Information Science of Wuhan University, 2017, 42(9): 1209-1215. DOI: 10.13203/j.whugis20150542
[3]	RUAN Rengui, WU Xianbing, FENG Laiping. Comparison of Observation Models and Ionospheric Elimination Approaches for Single Frequency Precise Point Positioning[J]. Geomatics and Information Science of Wuhan University, 2013, 38(9): 1023-1028.
[4]	ZOU Xuan, JIANG Weiping, SU Lina, LIU Jingnan. A New Single-Frequency PPP Method Using Dynamic Reference Network[J]. Geomatics and Information Science of Wuhan University, 2013, 38(4): 403-407.
[5]	TU Rui, HUANG Guanwen, ZHANG Qin, WANG Li. PPP Algorithm of Single Frequency Based on Corrections of Single-base Station and Ionospheric Parameters Estimation[J]. Geomatics and Information Science of Wuhan University, 2012, 37(2): 170-173.
[6]	TU Rui, HUANG Guanwen, ZHANG Qin, WANG Li. The Research of Dual Frequency Solution Method for Single Frequency Precise Point Positioning(PPP) Based on SEID Model[J]. Geomatics and Information Science of Wuhan University, 2011, 36(10): 1187-1190.
[7]	SHI Chuang, GU Shengfeng, GENG Changjiang, SONG Weiwei. High-Precision Single-Frequency Point Positioning with Randomness of Ionosphere Delay Correction in Consideration[J]. Geomatics and Information Science of Wuhan University, 2011, 36(7): 807-810.
[8]	LIU Jihua, OU Jikun, SUN Baoqi, ZHONG Shiming. The GEO Satellite Precise Orbit Determination Based on Inter-satellite Single Difference Method[J]. Geomatics and Information Science of Wuhan University, 2011, 36(1): 24-28.
[9]	SONG Weiwei, SHI Chuang, YAO Yibin, YE Shirong. Ionosphere Delay Processing Methods and Positioning Precision of Single Frequency Precise Point Positioning[J]. Geomatics and Information Science of Wuhan University, 2009, 34(7): 778-781.
[10]	ZHANG Xiaohong, LI Xingxing, GUO Fei, ZHANG Ming. Realization and Precision Analysis of Single-Frequency Precise Point Positioning Software[J]. Geomatics and Information Science of Wuhan University, 2008, 33(8): 783-787.

Cited By

Cited by

Periodical cited type(11)

1.	段博文，白征东，郭锦萍. 北斗二号卫星伪距偏差分析与建模. 测绘工程. 2024(02): 18-27 .
2.	高扬，沙海，楚恒林，王梦丽. 北斗B1C、B2a信号非理想性分析及接收约束建议. 武汉大学学报(信息科学版). 2023(04): 587-592 .
3.	耿涛，李钟兴，谢新，马壮，赵齐乐. GNSS接收机伪距偏差确定方法及其对定位的影响. 武汉大学学报(信息科学版). 2023(07): 1134-1145 .
4.	周中华，万祥，程艳，刘志忠，汪文君，张雪丽. 一种地基GNSS接收机差分码偏差估算方法. 空间科学学报. 2022(01): 170-178 .
5.	许海林，周恩泽，童梦想，鄂盛龙，田翔，罗颖婷. GPS/BDS/Galileo单点定位精度分析. 测绘地理信息. 2022(04): 19-24 .
6.	李浩东，赵齐乐，陶钧，龙宇浩. 北斗三号卫星FCB估计及其模糊度固定. 武汉大学学报(信息科学版). 2022(09): 1439-1446 .
7.	慕仁海，党亚民，许长辉. BDS-3新频点单点定位研究. 测绘通报. 2021(03): 12-17 .
8.	毛飞宇，龚晓鹏，辜声峰，王琛琛，楼益栋. 北斗三号卫星导航信号接收机端伪距偏差建模与验证. 测绘学报. 2021(04): 457-465 .
9.	徐宗秋，丁新展，徐彦田，唐龙江，李磊，胡艳阳. BDS静态精密单点定位模糊度固定解精度分析. 测绘科学. 2019(07): 30-34 .
10.	李森，周命端，陈积旭. 北斗数据工程控制网应用实验及精度分析. 测绘科学. 2019(09): 1-6 .
11.	唐卫明，刘前，高柯夫，邓辰龙，崔健慧，沈明星. 北斗伪距码偏差对基线解算的影响分析. 武汉大学学报(信息科学版). 2018(08): 1199-1206 .

Other cited types(13)

Get Citation

PDF

XML

Article views (454) PDF downloads (121) Cited by(24)

Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning

Abstract

References

Related Articles

Cited by

Periodical cited type(11)

Other cited types(13)

Catalog

Related

Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning

Abstract

References

Related Articles

Cited by

Periodical cited type(11)

Other cited types(13)

Catalog

Related

Export File

Citation

Format

Content