摘要
现有方法对城市生态敏感区建筑群体的规划易受高维空间的影响,规划效果较差,为此,提出一种城市生态敏感区建筑群体高维空间规划方法。采用矩形拟合优化方法对生态敏感区建筑群体图像进行处理,基于多尺度特征,对优化后的建筑群体图像进行分割。以分割后的图像为基础,将建筑群体数据转换为高维空间数据,建立建筑规划目标模型,并采用微粒群算法对目标模型进行求解,得到目标模型的全局最优值,完成对城市生态敏感区建筑群体高维空间的规划。实验结果表明,所提方法的建筑图像拟合误差最大不超过2.9%,拟合精度较高,且分割效果优于传统方法,目标模型最优值寻找耗时低于传统方法40%,规划效果评价结果良好。
The existing methods are vulnerable to the impact of high-dimensional space on the planning of building groups in urban ecological sensitive areas,and the planning effect is poor.Therefore,a high-dimensional space planning method for building groups in urban ecological sensitive areas was proposed.Rectangular fitting optimization method is used to process the building group image in the ecological sensitive area.Based on multi-scale features,the optimized building group image is segmented.Based on the segmented image,the building group data is transformed into high-dimensional spatial data,and the objective model of building planning is established.The particle swarm optimization algorithm is used to solve the objective model.The global optimal value of the objective model was obtained,and the high-dimensional space planning of the building group in the urban ecological sensitive area is completed.The experimental results show that the maximum fitting error of the proposed method is less than2.9%,and the fitting accuracy is higher.The segmentation effect is better than that of the traditional method.The searching time of the optimal value of the target model is less than 40%of that of the traditional method,and the evaluation result of the planning effect is good.
作者
田婷
刘文涛
TIAN Ting;LIU Wen-tao(Guizhou University of Finance and Economics,School of Management Science and Engineering,Guiyang 550025,China)
出处
《科学技术与工程》
北大核心
2019年第27期413-418,共6页
Science Technology and Engineering
基金
贵州省科学技术厅项目(黔科合体R字[2010]LKC2012)
关键词
生态敏感区
建筑群
图像
规划
拟合
分割
目标模型
ecologically sensitive area
architectural complex
image
planning
fitting
segmentation
objective model
