Researchers at Osaka University can use AI technology and street view images to visualize the structural and seasonal characteristics of urban vegetation, allowing urban planners to enhance the annual benefits of urban green spaces
The benefits of urban green spaces have been known for decades in terms of ecological sustainability, climate change and human well-being. Recently, additional economic and recovery payoffs from diverse and colorful plantings have been recognized. Currently, Japanese researchers have developed a new method for identifying changes in vegetation colour, structure and seasonal changes in urban environments.
In a study published in Landscape Ecology, researchers at Osaka University reveal an innovative approach to capturing the seasonal changes in urban plant species. This method combines artificial intelligence (AI) technology with street view images to help planners improve the visual appeal of urban green spaces throughout the year.
“Diversity in both plant colour and species appears to reinforce the “pleasant” factors of urban green spaces for urban residents and visitors,” says Ankiff, the lead author of the study. “Our aim was to develop a way to visualize urban vegetation composition and seasonality in much more detail than before.”
This method integrates AI with street view images in the form of deep learning and 3D reconstruction techniques, greatly improving the accuracy and consistency of urban vegetation analysis. The effectiveness of the technology was tested on the streets of Susa city, Osaka prefecture and applied to the design of a virtual park.
The index of seasonal species-specific plant views can distinguish between 51 urban plant species with an average accuracy of 82.17%. You can pick plants with very seasonal visual effects, such as spring cherry blossoms and autumn maple leaves. This level of detailed modeling and identification is almost impossible with traditional greenview analysis.
“Our approach removes coverage distortions and gaps from street view images, allowing for automatic generation of standardized perspectives over the universe and over time,” explains senior author Fukuda Moda. “The technology will help repair the Brownfield site or improve existing parks using diversity in plant shapes, colors and growth patterns.”
This framework provides a new perspective on 4D urban design and shapes the fundamental techniques to support future urban green space assessment and planning.
“Urban planners can use a variety of plants that add color and interest throughout the year to expand the economic, ecological and happy benefits of vegetation,” Hu says.
Figure 1
Overall workflow for multifaceted urban green vegetation visualization analysis framework
Credit: 2025 Anqi Hu et al. , Landscape Ecology
Figure 2
Comparison of original images and segmentation results for different plant species
Credit: 2025 Anqi Hu et al. , Landscape Ecology
Figure 3
Vegetation distribution along Sansikisai Road in Susa city
Credit: 2025 Anqi Hu et al. , Landscape Ecology
Notes
/Public release. This material of the Organization of Origin/Author is a point-in-time nature and may be edited for clarity, style and length. Mirage.news does not take any institutional position or aspect, and all views, positions and conclusions expressed here are the views of the authors alone.
