Speaker
Description
The combination of the two natural features of riverside coasts and mountain ranges is a relatively common geographic environment in urban settlements (Kim, Kim&Joo, 2024), and riverfront mountain landscapes have become one of the most important spatial vectors for highlighting the city's distinctive style and image due to their unique geographic location advantages and morphological features. However, for cities with limited space, it is not feasible to increase the number of mountain green spaces to improve the spatial quality only by increasing the number of green spaces in the mountains, when the development of urban densification has become a common trend (Chen,Qiu&Gao,2019). An in-depth understanding of landscape perceptual preferences is essential for maintaining attractive mountain landscapes and promoting sustainable urban public space development, further providing a theoretical basis for decision-making on improving green space quality (Jim and Chen, 2006). Meanwhile, with the rapid development of big data, user-generated image data provides a new research perspective for exploring landscape preferences due to its large sample size, high degree of public participation, and sufficient authenticity. However, most of the existing studies only reveal the degree of importance of landscape elements (Tieskens et al., 2018), confusing the two independent perceptual attributes of visual attention and aesthetic preference (Qiu et al., 2023), which makes it difficult to effectively identify the landscape content that truly attracts the public through social media, Crowdsourcing geo-information landscape content that really attracts the public. Therefore, this study takes Chongqing, the largest mountainous city in western China, as an example and constructs a set of mountain visual perception preference analysis system based on user-generated image data. The article combines the spatial aggregation distribution of user-generated pictures appearing in the elements of the riverside mountain landscape with the content analysis of the photographs, assesses the perceived preference of the riverside mountain landscape by analysing the geospatial distribution of the photographs and the comparison of the mountain visibility, and then combines the content analysis of the photographs with deep learning in order to determine the content in the mountain landscape that attracts people. The results of the study show that iconic point-scape structures rich in humanistic heritage, transport facilities such as bridges ropeways and rails with mountain characteristics, and the hierarchy of mountains and buildings are important factors influencing tourists‘ and residents’ visual preferences for the riverside mountain landscape. The method successfully links visual concerns and aesthetic preferences, which is important for shaping urban landscape design decisions that appeal to the public.
References
Chen, H., Qiu, L. & Gao, T., 2019. Application of the eight perceived sensory dimensions as a tool for urban green space assessment and planning in China. Urban Forestry & Urban Greening, 39, pp. 63-72.
Jim, C.Y. & Chen, W.Y., 2006. Perception and attitude of residents toward urban green spaces in Guangzhou (China). Environmental Management, 37(3), pp. 323-334.
Kim, B.-C., Kim, S.-N. & Joo, Y., 2024. Visual impact control of urban waterfront development on the background mountain view: Examining its justifiability through two types of immersive virtual reality experiments. Environmental Impact Assessment Review, 98, p. 106983.
Qiu, Y., Luo, T., Wang, Y., Fan, X. & Zhao, C., 2023. Research on the perceived characteristics of urban landscape elements based on visual attention and aesthetic preferences. Chinese Landscape Architecture, 39(6), pp. 82-87.
Tieskens, K.F., van Zanten, B.T., Schulp, C.J.E. & Verburg, P.H., 2018. Aesthetic appreciation of the cultural landscape through social media: An analysis of revealed preference in the Dutch river landscape. Landscape and Urban Planning, 180, pp. 83-92.
| Keywords | visual perception;User-generated data;Mountain Cities |
|---|---|
| Best Congress Paper Award | Yes |
