banner
Home > Open Journal Systems

Examining the nuances of Huizhou architecture and building decoration elements within the framework of rural development and urban aesthetics through the application of object detection and explicative analysis

Linyu Liu, Raziah Ahmad, Suriati Ahmad, Xuejie Jiang

Abstract


This scholarly investigation immerses itself in the intricate domain of Huizhou architecture and building decoration elements, which represent a distinct traditional Chinese architectural style. The study explores the evolution of Huizhou-style architecture and its ornamental techniques while delving into the visual aspects of contemporary urban architecture influenced by this unique style. Employing advanced technologies such as computer vision and explainable artificial intelligence (AI), the research aims to contribute to the preservation and documentation of China’s cultural heritage, specifically focusing on the intricate designs and distinctive building decorations inherent in Huizhou-style architecture. To methodically curate a diverse image dataset, a combination of automated annotation tools and manual labeling was utilized, establishing a robust benchmark for the exploration and comprehension of Huizhou architectural elements. The YOLOv7 model underwent retraining on this dataset, exhibiting noteworthy enhancements in precision, recall, and Mean Average Precision (mAP), surpassing the performance of the pre-trained model. In addition, the study introduces SHAPE, an explainable AI tool designed for interpretability, providing detailed insights into the decision-making process. This not only bolsters the reliability of our results but also enriches our comprehension of Huizhou-style architecture. This multidimensional approach not only propels the field of computer vision but also makes significant strides in the preservation of China’s cultural legacy. By integrating cutting-edge technologies with a meticulous exploration of architectural elements, this research fosters a deeper understanding of Huizhou architecture and its role in shaping the visual landscape of both rural and urban environments.


Keywords


Huizhou style architecture; building decoration; rural development; YOLO; explainable AI; object detection

Full Text:

PDF

References


1. Starzyńska, Małgorzata B, Roussel R, et al. Computer vision-based analysis of buildings and built environments: A systematic review of current approaches. arXiv preprint arXiv:2208.00881. 2022.

2. Wang M. Place-making for the people: Socially engaged art in rural China. China Information. 2018; 32(2): 244-269. doi: 10.1177/0920203x17749433

3. Karthikeyan P, Chang CC, Hsiung PA. Labor exploitation investigation using statistical and multiple object tracking assessment methods. Multimedia Tools and Applications. 2023; 82(29): 46085-46108. doi: 10.1007/s11042-023-16094-2

4. Shi Y. Literal translation extraction and free translation change design of Leizhou ancient residential buildings based on artificial intelligence and Internet of Things. Sustainable Energy Technologies and Assessments. 2023; 56: 103092. doi: 10.1016/j.seta.2023.103092

5. Karthikeyan P, Pratap A, Chu WCH, et al. Analysis of Fisherman Exploitation in Taiwan Distant Water Fishing. IEEE Technology and Society Magazine. 2023; 42(3): 88-97. doi: 10.1109/mts.2023.3306539

6. Pratap A, Sardana N, Utomo S, et al. Analysis of Defect Associated with Powder Bed Fusion with Deep Learning and Explainable AI. 2023 15th International Conference on Knowledge and Smart Technology (KST). Published online February 21, 2023. doi: 10.1109/kst57286.2023.10086905

7. Yang C, Liu T. Social Media Data in Urban Design and Landscape Research: A Comprehensive Literature Review. Land. 2022; 11(10): 1796. doi: 10.3390/land11101796

8. Ji SY, Jun HJ. Deep Learning Model for Form Recognition and Structural Member Classification of East Asian Traditional Buildings. Sustainability. 2020; 12(13): 5292. doi: 10.3390/su12135292

9. Jain A, Gandhi K, Ginoria DK, et al. Human Activity Recognition with Videos Using Deep Learning. 2021 International Conference on Forensics, Analytics, Big Data, Security (FABS). Published online December 21, 2021. doi: 10.1109/fabs52071.2021.9702599

10. Starzyńska-Grześ MB, Roussel R, Jacoby S, et al. Computer Vision-based Analysis of Buildings and Built Environments: A Systematic Review of Current Approaches. ACM Computing Surveys. 2023; 55(13s): 1-25. doi: 10.1145/3578552

11. Xia B, Li X, Shi H, et al. Style classification and prediction of residential buildings based on machine learning. Journal of Asian Architecture and Building Engineering. 2020; 19(6): 714-730. doi: 10.1080/13467581.2020.1779728

12. Ren X. Hybrid Building and Hybrid Practitioner: Understanding and Transforming Chinese Rural Villages through Architecture of Social Engagement [PhD thesis]. University of Sheffield; 2017.

13. Xu Y, Guo Y, Jumani AK, et al. Application of ecological ideas in indoor environmental art design based on hybrid conformal prediction algorithm framework. Environmental Impact Assessment Review. 2021; 86: 106494. doi: 10.1016/j.eiar.2020.106494

14. Mirra F. Visual arts: imagining ashanzhaicity in twenty-first century China. Visual Studies. Published online September 5, 2023: 1-13. doi: 10.1080/1472586x.2023.2243594

15. As I, Basu P, Talwar P. Artificial intelligence in urban planning and design: technologies, implementation, and impacts. Elsevier; 2022.

16. Chen P, Kong X. Tourism-led Commodification of Place and Rural Transformation Development: A Case Study of Xixinan Village, Huangshan, China. Land. 2021; 10(7): 694. doi: 10.3390/land10070694

17. Wu KC, Chen CH, Hsu CH. Three-dimensional visualization of thermal environments in urban canyons. Geocarto International. 2022; 37(27): 16261-16282. doi: 10.1080/10106049.2022.2107713

18. Xiao X, Fang C, Lin H, et al. A framework for quantitative analysis and differentiated marketing of tourism destination image based on visual content of photos. Tourism Management. 2022; 93: 104585. doi: 10.1016/j.tourman.2022.104585

19. Moustafa N, Koroniotis N, Keshk M, et al. Explainable Intrusion Detection for Cyber Defences in the Internet of Things: Opportunities and Solutions. IEEE Communications Surveys & Tutorials. 2023; 25(3): 1775-1807. doi: 10.1109/comst.2023.3280465

20. Huang ZK. Research on the Design of Chinese Rural Homestay Inn Based on the Concept of Symbiosis. 2022.

21. Maskeliūnas R, Katkevičius A, Plonis D, et al. Building Façade Style Classification from UAV Imagery Using a Pareto-Optimized Deep Learning Network. Electronics. 2022; 11(21): 3450. doi: 10.3390/electronics11213450

22. Wang CY, Liao HYM, Yeh IH. Designing network design strategies through gradient path analysis. arXiv preprint arXiv:2211.04800. 2022.

23. Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Published online June 2023. doi: 10.1109/cvpr52729.2023.00721

24. Wu D, Jiang S, Zhao E, et al. Detection of Camellia oleifera Fruit in Complex Scenes by Using YOLOv7 and Data Augmentation. Applied Sciences. 2022; 12(22): 11318. doi: 10.3390/app122211318

25. Holzinger A, Saranti A, Molnar C, et al. Explainable AI methods-a brief overview. In: International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers. Cham: Springer International Publishing; 2020. pp. 13-38.




DOI: https://doi.org/10.32629/jai.v7i5.1577

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Linyu Liu, Raziah Ahmad, Suriati Ahmad, Xuejie Jiang

License URL: https://creativecommons.org/licenses/by-nc/4.0/