Skip to main content

Study on the identification and dynamics of green vision rate in Jing’an district, Shanghai based on deeplab V3 + model

Abstract

Street greening is an important part of urban landscape, and Green view index (GVI) has an important influence on the comfort of street space environment. In this paper, we analyze the GVI of street space based on big data of street view photos and neural network algorithm. By collecting about 25,000 street view photos from Tencent map, we synthesize the panoramic projection photos of equal area. The image segmentation is achieved by training models through DeeplabV3 + network framework, and then the GVI after image recognition is calculated by OpenCV. The spatial distribution of GVI on the street space is analyzed by means of GIS and other means. In this paper, four spatial regression models are applied to analyze the influencing factors of GVI in the context of urbanization development from three perspectives: historical planning, economic and social. A negative correlation between road class and GVI distribution was obtained. When analyzing the influence of different POI distributions on GVI, it was found that the distribution of hospitals and subway stations was significantly correlated with GVI, and the presence of hospitals in neighborhoods would increase the GVI of surrounding streets. The presence of subway stations, on the other hand, decreases the green visibility of the surrounding streets. This study contributes to the development of human-centered planning and design and provides scientific guidance for the construction and renovation of green space in streets by targeting and optimizing the distribution of specific social facilities in the area.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

References

  1. Chen J, Yang ST, Li HW et al (2013) Research on Geographical Environment Unit Division Based on the Method of Natural Breaks (Jenks). Int Arch Photogramm Remote Sens Spatial Inf Sci XL-4/W3:47–50. https://doi.org/10.5194/isprsarchives-XL-4-W3-47-2013

    Article  Google Scholar 

  2. Chen L, Papandreou G, Kokkinos I et al (2018) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans Pattern Anal Machine Intell 40:834–848. https://doi.org/10.1109/TPAMI.2017.2699184

    Article  Google Scholar 

  3. Chen J, Zhou C, Li F (2020) Quantifying the green view indicator for assessing urban greening quality: An analysis based on Internet-crawling street view data. Ecol Ind 113:106192. https://doi.org/10.1016/j.ecolind.2020.106192

    Article  Google Scholar 

  4. Chen X, Wang Y, Dai Z, Ma X (2020) Research on demand identication for customized bus based on multi-source mobility data. Big Data Res 6:105–118

    Google Scholar 

  5. Chen Z, Huang G (2020) Research progress on supply and demand of urban green space: differences and connections. Chin J Appl Ecol 1–11

  6. Cordts M, Omran M, Ramos S, et al (2016) The Cityscapes Dataset for Semantic Urban Scene Understanding

  7. Cui Z, He M, Lu M (2018) An Analysis of Green View Index in Cold Region City: A Case Study of Harbin. J Chin Urban Forestry 16:34–38

    Google Scholar 

  8. Gao C, Feng Y, Tong X et al (2020) Modeling urban growth using spatially heterogeneous cellular automata models: Comparison of spatial lag, spatial error and GWR. Comput Environ Urban Syst 81:101459. https://doi.org/10.1016/j.compenvurbsys.2020.101459

    Article  Google Scholar 

  9. Guo F, Lyu X, Yu W et al (2020) Performance evaluation and driving mechanism of green development in Shandong Province based on panel data of 17 cities. Sci Geogr Sinica 40:200–210

    Google Scholar 

  10. Han Y, Qi X, Yang Y (2020) Analysis of the spillover effect of energy intensity among provinces in China based on space-time lag model. Environ Sci Pollut Res 27:16950–16962. https://doi.org/10.1007/s11356-020-08169-6

    Article  Google Scholar 

  11. Helbich M, Yao Y, Liu Y et al (2019) Using deep learning to examine street view green and blue spaces and their associations with geriatric depression in Beijing, China. Environ Int 126:107–117. https://doi.org/10.1016/j.envint.2019.02.013

    Article  Google Scholar 

  12. Ju H, Wei L, Susan T, et al (2020) CrackU‐net: A novel deep convolutional neural network for pixelwise pavement crack detection. Struct Control Health Monitor 27

  13. Li F, Shi H, Sa L et al (2017) 3D green volume measurement of single tree using 3D laser point cloud data and differential method. J xi’an Univ Architect Technol 49:530–535

    Google Scholar 

  14. Li F, Xie S, Li X (2019) Evolutionary driving mechanism of greenspace in central Beijing City based on the PLSR model. J Beijing Forestry Univ 41:116–126

    Google Scholar 

  15. Li Z, He Z, Zhang Y et al (2020) Impact of greenspace exposure on residents’ mental health:A case study of Nanjing City. Progress Geogr 39:779–791. https://doi.org/10.18306/dlkxjz.2020.05.007

    Article  Google Scholar 

  16. Liu Z, Han C, Wang J, Hong G (2020) Influence of socioeconomic factors on the green rate of built districts in China from the perspective of spatial spillover effect. J Suzhou Univ Sci Technol (Engineering and Technology) 33:39-44+80

    Google Scholar 

  17. Long Y, Liu L (2017) How green are the streets? An analysis for central areas of Chinese cities using Tencent Street View. PLoS ONE 12:e0171110. https://doi.org/10.1371/journal.pone.0171110

    Article  Google Scholar 

  18. Luo X (2020) GIS-Based Research on Evaluation and Construction of Ecological Greenland System in Industrial Cities – Taking the Built-up Area of Zibo City, Shandong Province as an Example. PhD Thesis, Shandong Jianzhu University

  19. Matsumoto T (2008) Issues and Future Prospects for Regulatory and Guidance Methods to Create a Good Landscape. J Japan Real Estate Soc 22:104–113. https://doi.org/10/gjt97t

  20. Meng Q, Wang X, Sun Y et al (2020) Construction of green view index model based on street view data and research on its influence factors. Ecol Sci 39:146–155

    Google Scholar 

  21. Ru X, Jiang T (2015) Analysis on Evolution Driving Factors and Landscape Pattern of Urban Green Space -Taking Built-up Area of Ji’nan City as an Example. Res Soil Water Conserv 22:197–203

    Google Scholar 

  22. Shen S, Liu X, Sun X, Ding L (2020) Regional Coupling Differences of Green Coverage Rate and Green Space Rate of the Cities with Districts in China——A Perspective Based on Dry and Wet Climate Zoning. J Northwest Forestry Univ 35:236–241

    Google Scholar 

  23. Wang K, Yan B, Wang F, Gao X (2014) Countermeasures of Urban Planning to Manage“Urban Disease”: The Experiences from Foreign Countries. World Regional Studies 23:65–72

    Google Scholar 

  24. Wang R, Helbich M, Yao Y et al (2019) Urban greenery and mental wellbeing in adults: Cross-sectional mediation analyses on multiple pathways across different greenery measures. Environ Res 176:108535. https://doi.org/10.1016/j.envres.2019.108535

    Article  Google Scholar 

  25. Wang H, Hu Y, Tang L, Zhuo Q (2020a) Distribution of Urban Blue and Green Space in Beijing and Its Influence Factors. Sustainability 12:2252. https://doi.org/10.3390/su12062252

    Article  Google Scholar 

  26. Wang J, Liu Z, Liu L, Hong G (2020b) Study on the Influencing Mechanism of Spatial Differentiation of Green Rate of Built District of Typical Transects in China Based on Geodetector. Ecol Econ 36:104–111

    Google Scholar 

  27. Wei Y (2016a) Research on Visible Green Index Evaluation of High Density Urban Area on Macau Peninsula. PhD Thesis, South China Agricultural University

  28. Wei Y (2016b) Research on Visible Green Index Evaluation of High Density Urban Area on Macau Peninsula. Master’s thesis, South China Agricultural University

  29. Xiao X, Wei Y, Li M (2018) The Method of Measurement and Applications of Visible Green Index in Japan. Urban Plann Int 33:98–103

    Article  Google Scholar 

  30. Xu L, Jiang W, Chen Z (2018) Study on Perceived Safety in Public Spaces: Take Perception of Stree View in Shanghai as an Example. Landsc Architect 25:23–29

    Google Scholar 

  31. Yang W, Li X, Ye C (2019) Evaluation Index System for Urban Green System Planning. Planners 35:71–76

    Google Scholar 

  32. Zhang W, Zhou Y et al (2019) Research on automatic identification and measurement of panoramic visible green index. Landscape Architecture 26:89–94

  33. Zhao H, Wang S, Meng F et al (2020) Green space pattern changes and its driving mechanism:a case study of Nanjing metropolitan area. Acta Ecol Sin 40:7861–7872

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Jiangbo Wang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Communicated by H. Babaie

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Gou, A., Zhang, C. & Wang, J. Study on the identification and dynamics of green vision rate in Jing’an district, Shanghai based on deeplab V3 + model. Earth Sci Inform (2021). https://doi.org/10.1007/s12145-021-00691-6

Download citation

Keywords

  • Spatial model
  • Green view index
  • Neural network
  • Jing’an District