Extracting urban spatial perception attributes and scene elements by integrating VGG-16 and CBAM

Abstract

As urbanization continues to accelerate, there is a growing need for the analysis of urban spatial perception attributes and scene elements. In response, the research proposed a multi-scale perception network-based model for extracting urban scene elements and an attention-enhanced segmentation network-based model for analyzing urban spatial scene structures. The urban scene feature extraction model incorporated Siamese convolutional neural networks and convolutional block attention to achieve multi-scale perception extraction. The urban spatial scene structure analysis model combined a dynamic attention module with an encoder-decoder architecture to enhance the accuracy of scene element segmentation. During testing of the urban scene feature extraction model at a resolution of 768, its classification accuracy and cross entropy were 95.4% and 0.065, respectively. The model's average ranking accuracy for beauty, comfort, and cleanliness was 92.5%, 91.8%, and 93.2%. In testing the urban spatial scene structure analysis model, the boundary intersection to union ratio and boundary F1 score were 81.2% and 82.1%, respectively, with a boundary complexity of 0.6. The results demonstrated that the proposed method excelled in tasks such as perceptual attribute classification and scene element parsing, effectively addressing complex and diverse urban spatial features.

Keywords

VGG-16 / CBAM / City / Spatial scene / Perceived attributes / Element extraction / Information and Computing Sciences / Artificial Intelligence and Image Processing

References

[1] CarballalA, Fernandez-LozanoC, HerasJ, RomeroJ. Transfer learning features for predicting aesthetics through a novel hybrid machine learning method. Neural Computing and Applications., 2020, 32: 5889-5900.

[2] ChenXH, XuXQ, LiuYJ, WangY, ZhangMX, MaLY. Liu S Patterns and Driving Forces of the Temporal-Spatial Evolution of Urban Vulnerability in Harbin-Changchun Urban Agglomeration based on the production-living-ecological Spatial Quality. Acta Ecologica Sinica, 2022, 42126395-6405

[3] DeepaV, Sathish KumarC, CherianT. Automated grading of diabetic retinopathy using CNN with hierarchical clustering of image patches by siamese network. Physical and Engineering Sciences in Medicine, 2022, 452623-635.

[4] GanW, WangY, LiX. Practical study on the application of embedded machine learning method in generative design at block level. Journal of Human Settlements in West China, 2024, 3932-8

[5] Gümüşİ, ErdönmezE. Impact of spatial configuration to spatial quality: Venice and Istanbul. Journal of Architecture and Urbanism, 2021, 452205-216.

[6] Gümüşİ, EtikeBA, KöseİSP. The comparative analysis of SPACE SYNTAX and PPS approaches in measuring quality of urban space: The case of Beyazit district Istanbul. Garon, 2022, 173437-448

[7] HouZ, ChengM, MaS, QuM, YangX. Real-time urban street view semantic segmentation based on cross-layer aggregation network. Optics and Precision Engineering, 2024, 3281212-1226.

[8] JiachuanS, GuolinHU, YuzhiLI. Emotional Rendering of 3D Indoor Scene with Chinese Elements. Journal of Frontiers of Computer Science & Technology, 2024, 182465-476

[9] LiuZ, LyuJ, YaoY, ZhangJ, KouS, GuanQ. Research method of interpretable urban perception model based on street view imagery. J. Geo-Inf. Sci, 2022, 24102045-2057

[10] NaseerA, ZafarK. Meta-feature based few-shot Siamese learning for Urdu optical character recognition. Computational Intelligence, 2022, 3851707-1727.

[11] NiyomubyeyiO, VeysipanahM, SarwatS, PilesjöP, MansourianA. An improved non-dominated sorting biogeography-based optimization algorithm for multi-objective land-use allocation: A case study in Kigali-Rwanda. Geo-Spatial Information Science, 2024, 274968-982.

[12] PrSD. A two-phase approach for expression invariant 3D face recognition using fine-tuned VGG-16 and 3D-SIFT descriptors. Multimedia Tools and Applications, 2023, 821523873-23890.

[13] RavikumarM, RachanaPG, ShivaprasadBJ. Segmentation of tumour from mammogram images using U-SegNet: A hybrid approach. Comput Methods Biomech Biomed Eng Imaging Vis., 2023, 113387-398.

[14] ReddySK, KathirveluK. Prostate cancer detection using Henry firefly gas solubility optimization-based deep residual network. Multimedia Tools and Applications, 2024, 831029331-29352.

[15] SahakAS, KarsliF. A new approach for the assessment of urban eco-environmental quality based on remote sensing: A case study of Herat City. Afghanistan. Journal of Spatial Science, 2024, 693937-962.

[16] VankyA, LeR. Urban-semantic computer vision: A framework for contextual understanding of people in urban spaces. AI & SOCIETY, 2023, 3831193-1207.

[17] WangX, LiX, ZhangS. Has the polycentric spatial structure promoted high-quality urban development. China Population, Resources and Environment, 2022, 32557-67

[18] XuanW, PengK, ZangC. The Correlation Between Street Space and Behaviours in the New Data Environment. South Architecture, 2023, 2449-60

[19] YangN, DengZ, HuF, ChaoY, WanL, GuanQ, WeiZ. Urban perception by using eye movement data on street view images. Transactions in GIS, 2024, 2851021-1042.

[20] ZhangX, LiP. Transfer learning in the transformer model for thermal comfort prediction: A case of limited data. Energies, 2023, 16207137.

[21] ZhaoZ, ZhengX, FanH, SunM. Urban spatial structure analysis: Quantitative identification of urban social functions using building footprints. Frontiers of Earth Science, 2021, 153507-525.

RIGHTS & PERMISSIONS

The Author(s)