Biomechanical analysis and application of image processing technology based on deep learning in the indoor evaluation system of high-rise buildings
Abstract
In the context of biomechanics and the built environment, understanding the relationship between the indoor space layout of high-rise buildings and human biomechanical responses is crucial. To enhance the quality of the indoor space layout of buildings with respect to human biomechanical comfort and functionality, this paper proposes a method for extracting the characteristics of the indoor space layout of high-rise buildings based on deep-learning image processing. The indoor space layout parameters are not only related to architectural aesthetics but also have implications for human movement and biomechanical behavior. For example, the dimensions and configurations of rooms and corridors can affect gait patterns, body postures, and muscle activations during walking and other activities. According to the extracted indoor space layout parameters, their edge sequences are determined. The image processing algorithm based on deep learning is then used to control the convergence of the characteristic parameters. This process is not only for architectural feature extraction but also to analyze how these features interact with human biomechanics. For instance, the angles and lengths of corridors can influence the turning radii and step frequencies of individuals, which are key biomechanical factors. By extracting the characteristics of the indoor space layout of high-rise buildings, we can evaluate how well the space accommodates human movement and biomechanical needs. The results reveal that the proposed method can effectively extract features relevant to both architecture and biomechanics, and the accuracy in assessing biomechanically relevant features is always higher than 90%. This high accuracy indicates the potential of this method to contribute to the design of indoor spaces that are more conducive to human biomechanical well-being and efficient movement.
References
1. Peng Junshan. Method for Counting Reinforcement in Construction Sites Based on Digital Image Processing Technology [D]. Shenzhen University [2014-10-18] DOI:CNKI:CDMD:2.1017.812832.
2. Guo Peng, Chen Honglei. Application of Image Processing Technology in Solar Energy Planning and Design of Urban Buildings [J]. Theoretical Research on Urban Construction (Electronic Version), 2015 (17)/
3. Zhang Jing, Qu Juntong, Li Shuyi, et al. Application of Matlab based image processing technology in building exterior wall decorative tiles [J] two thousand and eleven
4. Yang Juntao. Research on Hierarchical Understanding Method of Indoor and Outdoor Scenes Using 3D Point Clouds [J]. Journal of Surveying and Mapping, 2023, 52 (5): 870-870. DOI: 10.11947/j.AGCS. 2023.20210586
5. Zhou Zhongchang, Liu Jicheng. Simulation Study on Optimal Energy saving Design Model for Building Space [J]. Computer Simulation, 2024, 41 (3): 528-532
6. Shen Lei, Song Jirong, Zhang Dan. Simulation study on optimal layout of indoor space in buildings based on VR technology [J]. Computer Simulation, 2023, 40 (5): 279-283
7. Zheng Haidong, Wang Kaili. Application of Computer Technology in Interior Art Design [J]. Architectural Science, 2022 (11): 179-179
8. Yang Panpan. Research on the Application of Digital Technology in Interior Design - Review of "Fundamentals of Digital Design and Manufacturing Technology Application" [J]. Chinese Journal of Science and Technology, 2022 (8)
9. Fan Lingyan. Research on Interior Design System of Digital Processing Technology and Image Processing Technology [J]. Modern Electronic Technology, 2021, 44 (9): 5. DOI: 10.16652/j.issn.1004-373x.2021.09.008
10. Metin B, Andrew T.M.P, Alessandro M,.et,al. Generative deep learning applied to biomechanics: A new augmentation technique for motion capture datasets, [J]. Journal of Biomechanics, 2022, 144: 111301.
11. Eva D , Marlies N, Christine F,.et,al. CNN-Based Estimation of Sagittal Plane Walking and Running Biomechanics From Measured and Simulated Inertial Sensor Data. Frontiers in Bioengineering and Biotechnology. 2020,8. https://doi.org/10.3389/fbioe.2020.00604
12. Walter, J.R., Günther, M., Haeufle, D.F.B. et al. A geometry- and muscle-based control architecture for synthesising biological movement. Biol Cybern 115, 7–37 (2021). https://doi.org/10.1007/s00422-020-00856-4
13. Nivethitha S, Gauthama R.M R, Krithi R, A deep learning framework for building energy consumption forecast, Renewable and Sustainable Energy Reviews, 2021,137: 110591
14. Razak O-A, Hafiz A, Ismail S, et al. Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques, Journal of Building Engineering, 2022,45: 103406.
15. Ayala C, Sesma R, Aranda C, Galar M. A Deep Learning Approach to an Enhanced Building Footprint and Road Detection in High-Resolution Satellite Imagery. Remote Sensing. 2021; 13(16):3135. https://doi.org/10.3390/rs13163135
Copyright (c) 2024 Shaoyang Li
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
