| Abstract |
Green space is an important part of the construction of living environment. Planning of urban high-density green space has become a hot spot in urban space research. The data of urban high-density green space energy-saving planning data is of a diversified nature. The existing methods have poor correlation in the way of data recording, which has led to the problem of long planning time and single plant species. In this paper, we propose a method for energy-saving planning of urban high-density green space based on digital remote sensing images. The multi-scale segmentation method is used to segment the acquired digital remote sensing images, which can help us obtain information about the highly dense urban green space. The population size of the study area is predicted based on the ecological footprint. Based on the minimum cumulative resistance model, combined with the population size prediction results, an urban high-density green space energy-saving planning model is constructed to realize the urban high-density green space energy-saving planning. The experimental results show that the planning time of the proposed method is less than 2 min in multiple experimental iterations, and the plant diversity coefficient is higher than 7. This shows that the proposed method has the shortest planning time, and the plant diversity characteristics after planning are better. |
