Précédent|Prochain

Méthode de détection sémantique faible supervision des changements d’images de rue et étude de cartographie dynamique de la rénovation urbaine

  • role： First author第一作者
  • Affiliation：

    Beidou Research Institute, South China Normal University, Foshan 528225, China

    College of Geography Science, South China Normal University, Guangzhou 510631, China

  • Email：2023025220@m.scnu.edu.cn
  • Introduction：彭奕霖，研究方向为街景变化检测。E-mail： 2023025220@m.scnu.edu.cn
PENG Yilin12,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Geography Science, South China Normal University, Guangzhou 510631, China

  • Email：fuyc@m.scnu.edu.cn
  • Introduction：付迎春，主要研究方向为定量遥感与城市遥感。E-mail： fuyc@m.scnu.edu.cn
FU Yingchun2*,  
  • Affiliation：

    Beidou Research Institute, South China Normal University, Foshan 528225, China

XING Hanfa1,  
  • Affiliation：

    College of Geography Science, South China Normal University, Guangzhou 510631, China

CHEN Shuqi2,  
  • Affiliation：

    College of Geography Science, South China Normal University, Guangzhou 510631, China

LI Zhenhao2,  
  • Affiliation：

    College of Geography Science, South China Normal University, Guangzhou 510631, China

ZHANG Si2

résumé

Les images de rue constituent une nouvelle forme de données géographiques massives pour percevoir l’environnement matériel urbain. La détection des changements de façade à partir des images de rue et la reconnaissance des catégories sémantiques des changements sont des moyens importants pour percevoir la rénovation urbaine. Les méthodes traditionnelles de détection de changement ne peuvent pas distinguer directement l’appartenance temporelle des objets de changement dans les images de rue (partition temporelle), rendant difficile la reconnaissance efficace des catégories sémantiques des zones de changement entre deux périodes. Cet article propose le modèle Cross-C2PO (Cross-Combine 2 POssible change types) qui unifie les tâches de détection des changements et de partition temporelle, facilitant l’introduction des modèles actuels de segmentation sémantique d’images pour la détection des changements sémantiques dans les images de rue. Sur cette base, une méthode d’analyse perceptuelle des indicateurs dynamiques de rénovation urbaine est construite, visant la surveillance des changements de 2013 à 2019 dans le centre-ville de Guangzhou, réalisant une perception complète des changements dans les quatre angles de vue avant, arrière, gauche et droite pour cartographier la dynamique de la rénovation urbaine, montrant visuellement la répartition des rénovations urbaines et l’intensité des changements de l’environnement physique, fournissant une méthode innovante et une étude de cas pour l’application intelligente combinant images de rue et vision par ordinateur.

mots-clés

rénovation urbaine;images de rue;détection de changement sémantique;détection de changement de scène;faible supervision;dynamique

References

  1. 1.
    Alcantarilla P F, Stent S, Ros G, Arroyo R and Gherardi R. 2018. Street-view change detection with deconvolutional networks. Autonomous Robots, 42(7): 1301-1322 .
  2. 2.
    Badland H M, Opit S, Witten K, Kearns R A and Mavoa S. 2010. Can Virtual Streetscape Audits Reliably Replace Physical Streetscape Audits? Journal of Urban Health, 87(6): 1007-1016 .
  3. 3.
    Berland A and Lange D A. 2017. Google Street View shows promise for virtual street tree surveys. Urban Forestry & Urban Greening, 21: 11-15
  4. 4.
    Caye Daudt R, Le Saux B and Boulch A. 2018. Fully Convolutional Siamese Networks for Change Detection. 2018 25th IEEE International Conference on Image Processing (ICIP). 4063-4067
  5. 5.
    Chen L C, Papandreou G, Schroff F and Adam H. 2017. Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv
  6. 6.
    Chen S, Yang K and Stiefelhagen R. 2021. DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection. 2021 IEEE Intelligent Vehicles Symposium (IV). 502-509
  7. 7.
    Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S and Schiele B. 2016. The Cityscapes Dataset for Semantic Urban Scene Understanding. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society: 3213-3223
  8. 8.
    Davison G, Ferris D, Pearson A and Shach R. 2020. Investments with returns: a systematic literature review of health-focused housing interventions. Journal of Housing and the Built Environment, 35(3): 829-845 .
  9. 9.
    FU Y C, GUO B Y, WANG M and QIN X L. 2022. Spatial resilience evolution of green space from the perspective of social-ecological system adaptive governance: A case study for urban renewal in Guangzhou, China. JOURNAL OF NATURAL RESOURCES, 2022, 37(8): 2118-2136
  10. 10.
    Goel R, Garcia L M T, Goodman A, Johnson R, Aldred R, Murugesan M, Brage S, Bhalla K and Woodcock J. 2018. Estimating city-level travel patterns using street imagery: A case study of using Google Street View in Britain. PLOS ONE, 13(5): e0196521 [DOI: 10.1371/journal.pone.0196521].
  11. 11.
    Gong P, Chen B, Li X, Liu H, Wang J, Bai Y, Chen J, Chen X, Fang L, Feng S, Feng Y, Gong Y, Gu H, Huang H, Huang X, Jiao H, Kang Y, Lei G, Li A, Li Xiaoting, Li Xun, Li Y, Li Zhilin, Li Zhongde, Liu Chong, Liu Chunxia, Liu M, Liu S, Mao W, Miao C, Ni H, Pan Q, Qi S, Ren Z, Shan Z, Shen S, Shi M, Song Y, Su M, Ping Suen H, Sun B, Sun F, Sun J, Sun L, Sun W, Tian T, Tong X, Tseng Y, Tu Y, Wang H, Wang L, Wang X, Wang Z, Wu T, Xie Y, Yang Jian, Yang Jun, Yuan M, Yue W, Zeng H, Zhang K, Zhang N, Zhang T, Zhang Y, Zhao F, Zheng Y, Zhou Q, Clinton N, Zhu Z and Xu B. 2020. Mapping essential urban land use categories in China (EULUC-China): preliminary results for 2018. Science Bulletin, 65(3): 182-187
  12. 12.
    HUANG H M. 2013. The characteristics of urban morphological transformations and development mechanisms: A case study of Guangzhou since 1949. Guangzhou: South China University of Technology. (黄慧明. 2013. 1949年以来广州旧城的形态演变特征与机制研究. 广州: 华南理工大学)
  13. 13.
    He K, Gkioxari G, Dollár P and Girshick R. 2017. Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV). 2980-2988
  14. 14.
    Kingma D P and Ba J. 2017. Adam: A Method for Stochastic Optimization. arXiv
  15. 15.
    Kirillov A, He K, Girshick R, Rother C and Dollár P. 2019. Panoptic Segmentation. arXiv
  16. 16.
    Lei Y, Peng D, Zhang P, Ke Q and Li H. 2021. Hierarchical Paired Channel Fusion Network for Street Scene Change Detection. IEEE Transactions on Image Processing, 30: 55-67
  17. 17.
    Liang C, Jiang H, Yang S, Tian P, Ma X, Tang Z, Wang H and Wang W. 2024. Characterizing street trees in three metropolises of central China by using Street View data: From individual trees to landscape mapping. Ecological Informatics, 80: 102480
  18. 18.
    Lin T Y, Dollár P, Girshick R, He K, Hariharan B and Belongie S. 2017. Feature Pyramid Networks for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society: 936-944
  19. 19.
    Liu C and Song W. 2024. Mapping property redevelopment via GeoAI: Integrating computer vision and socioenvironmental patterns and processes. Cities, 144: 104644
  20. 20.
    Liu C T, Feng Q L, Liu J T, Wang Y, Shi T G, Li Y, Gong J H and Zhao H H. 2022. Urban green plastic cover extraction and spatial pattern changes in Jinan city based on DeepLabv3+ semantic segmentation model. National Remote Sensing Bulletin, 26(12): 2518-2530
  21. 21.
    Long Y and Liu L. 2017. How green are the streets? An analysis for central areas of Chinese cities using Tencent Street View. PLOS ONE, 12(2): e0171110 [DOI: 10.1371/journal.pone.0171110].
  22. 22.
    Loshchilov I and Hutter F. 2017. SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv
  23. 23.
    Ma X, Ma C, Wu C, Xi Y, Yang R, Peng N, Zhang C and Ren F. 2021. Measuring human perceptions of streetscapes to better inform urban renewal: A perspective of scene semantic parsing. Cities, 110: 103086
  24. 24.
    Miao C, Yu S, Hu Y, Zhang H, He X and Chen W. 2020. Review of methods used to estimate the sky view factor in urban street canyons. Building and Environment, 168: 106497
  25. 25.
    Orhan S. 2022. Semantic Segmentation of Panoramic Images and Panoramic Image Based Outdoor Visual Localization. Izmir Institute of Technology (Turkey)
  26. 26.
    Radke R J, Andra S, Al-Kofahi O and Roysam B. 2005. Image change detection algorithms: a systematic survey. IEEE Transactions on Image Processing, 14(3): 294-307
  27. 27.
    Ravi N, Gabeur V, Hu Y T, Hu R, Ryali C, Ma T, Khedr H, Rädle R, Rolland C, Gustafson L, Mintun E, Pan J, Alwala K V, Carion N, Wu C Y, Girshick R, Dollár P and Feichtenhofer C. 2024. SAM 2: Segment Anything in Images and Videos. arXiv
  28. 28.
    Ronneberger O, Fischer P and Brox T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv
  29. 29.
    Sakurada K, Shibuya M and Wang W. 2020. Weakly Supervised Silhouette-based Semantic Scene Change Detection. 2020 IEEE International Conference on Robotics and Automation (ICRA). 6861-6867
  30. 30.
    Sakurada K, Wang W, Kawaguchi N and Nakamura R. 2017. Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints. arXiv
  31. 31.
    Sampson R J. 2017. Urban sustainability in an age of enduring inequalities: Advancing theory and ecometrics for the 21st-century city. Proceedings of the National Academy of Sciences, 114(34): 8957-8962
  32. 32.
    Shelhamer E, Long J and Darrell T. 2017. Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651
  33. 33.
    Simonyan K and Zisserman A. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv
  34. 34.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V and Rabinovich A. 2014. Going Deeper with Convolutions. arXiv
  35. 35.
    Varghese A, Gubbi J, Ramaswamy A and Balamuralidhar P. 2019. ChangeNet: A Deep Learning Architecture for Visual Change Detection. Computer Vision – ECCV 2018 Workshops. Cham: Springer International Publishing: 129-145
  36. 36.
    Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L and Polosukhin I. 2023. Attention Is All You Need. arXiv
  37. 37.
    Wang G H, Gao B B and Wang C. 2023. How to Reduce Change Detection to Semantic Segmentation. Pattern Recognition, 138: 109384
  38. 38.
    Wang X L and Bao Y H. STUDY ON THE METHODS OF LAND USE DYNAMIC CHANGE RESEARCH. PROGRESS IN GEOGRAPHY, 1999, 18(1): 81-87
  39. 39.
    Xie E, Wang W, Yu Z, Anandkumar A, Alvarez J M and Luo P. 2021. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv
  40. 40.
    Yao Z H and Tian L. 2017. Transition of Pattern and Modes of Governance for Urban Renewal in Guangzhou since the 21st Century. Shanghai Urban Planning Review, (5): 29-34
  41. 41.
    Yin L and Wang Z. 2016. Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imagery. Applied Geography, 76: 147-153
  42. 42.
    Yue Z, Lo C Y, Wu R, Ma L and Sham C W. 2024. Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes. Urban Science, 8(2): 23 [DOI: 10.3390/urbansci8020023].
  43. 43.
    Zhang F, Wu L, Zhu D and Liu Y. 2019. Social sensing from street-level imagery: A case study in learning spatio-temporal urban mobility patterns. ISPRS Journal of Photogrammetry and Remote Sensing, 153: 48-58
  44. 44.
    Zhang F and Liu Y. 2021. Street view imagery: Methods and applications based on artificial intelligence. National Remote Sensing Bulletin, 25(5): 1043-1054
  45. 45.
    Zhao T, Zhang S C, He X N, Xue B W and Zha F K. 2024. Improved DeepLabV3+ model for landslide identification in high-resolution remote sensing images after earthquakes. National Remote Sensing Bulletin, 28(9): 2293-2305

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website