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.
Read full abstract