基于多尺度特征提取的城市绿色建筑空间多目标规划  

Multi-objective planning of urban green building space based on multi-scale feature extraction

作　　者：于利尧 YU Liyao(Jiangsu Fangyuan of Architectural Design and Research Co.,Ltd.,Shuyang 223600,China)

机构地区：[1]江苏省方圆建筑设计研究有限公司,江苏沭阳223600

出　　处：《四川建材》2025年第3期42-45,共4页Sichuan Building Materials

摘　　要：由于城市绿色空间用地类型多样且结构复杂,以往单一的规划模式很难保证空间适宜性,因此,提出基于多尺度特征提取的城市绿色建筑空间多目标规划。基于多尺度特征提取技术分割城市绿色建筑空间遥感影像,获取用地分类信息,以各类用地的紧凑度和经济效益最大化为目标,构建城市绿色建筑空间多目标规划模型,利用遗传算法求解模型,得到最优规划方案。实例结果表明,设计方法规划后的城市绿色建筑空间中高度适宜区占比高达75.87%,规划结果合理,验证了该方法的正确性。Due to the diverse types and complex structures of urban green space land use,it was difficult to ensure spatial suitability using a single planning model in the past.Therefore,a multi-objective planning of urban green building space based on multi-scale feature extraction was proposed.Based on multi-scale feature extraction technology,remote sensing images of urban green building space are segmented to obtain land classification information.With the goal of maximizing the compactness and economic benefits of various types of land,a multi-objective planning model for urban green building space is constructed.Genetic algorithm is used to solve the model and obtain the optimal planning scheme.The example results show that the proportion of highly suitable areas in the urban green building space planned by the design method is 75.87%,and the planning results are reasonable,verifying the correctness of the method.

关 键 词：多尺度特征提取 城市绿色建筑空间 多目标规划 空间规划 

分 类 号：TU984.113[建筑科学—城市规划与设计]