基于机器学习的风景园林智能化分析应用研究
|
摘要
机器学习使实现数据的智能化处理及充分利用数据中蕴含的知识与价值成为可能。探索基于机器学习在风景园林领域智能化分析应用的途径,开展3个实验。其中2个与数据分析研究相关,提出基于调研图像色彩聚类分析的城市色彩印象和基于图像识别技术的景观视觉质量评估与网络应用平台部署实验。最后1个实验与数字化设计创作相关,提出用于设计方案遴选的地形生成方法,包括2个子项目:应用深度学习生成对抗网络(GAN)的地形生成和建立遮罩、预测未知区域的高程。3个实验应用到机器学习中分类、聚类和回归3个主要方向中的算法以及深度学习的生成对抗网络,对传统的研究问题提出了基于机器学习新的研究方法。因此,在应用机器学习风景园林领域,可以有效地从多源数据中学习相互增强的知识,发现问题,并提出解决问题的新方法。
Machine learning makes data intellectualization processing and full use of knowledge and value contained in data possible. To explore the approaches of intellectual analysis and application in landscape architecture based on machine learning, we carried out three experiments. Two experiments are related to data analysis study, to propose urban colour impression based on investigating image colour clustering analysis, and the landscape visual quality evaluation and network application platform deployment based on image recognition technology. The last experiment is related to digital design creation, to propose the terrain generation method for design scheme comparison, including two subitems, which are the terrain generation with the Generative Adversarial Networks of deep learning as well as predicting the elevation in the unknown area by building masks,respectively. All the three experiments employ the algorithms of classification, clustering, and regression, as well as the Generative Adversarial Networks of deep learning, to propose new study methods based on machine learning for traditional study issues. Therefore, with the application of machine learning to landscape architecture,we can effectively learn about the interaction enhancement knowledge from multi-source, find problems and propose new methods to solve problems.
Machine learning makes data intellectualization processing and full use of knowledge and value contained in data possible. To explore the approaches of intellectual analysis and application in landscape architecture based on machine learning, we carried out three experiments. Two experiments are related to data analysis study, to propose urban colour impression based on investigating image colour clustering analysis, and the landscape visual quality evaluation and network application platform deployment based on image recognition technology. The last experiment is related to digital design creation, to propose the terrain generation method for design scheme comparison, including two subitems, which are the terrain generation with the Generative Adversarial Networks of deep learning as well as predicting the elevation in the unknown area by building masks,respectively. All the three experiments employ the algorithms of classification, clustering, and regression, as well as the Generative Adversarial Networks of deep learning, to propose new study methods based on machine learning for traditional study issues. Therefore, with the application of machine learning to landscape architecture,we can effectively learn about the interaction enhancement knowledge from multi-source, find problems and propose new methods to solve problems.
引文
[1]刘思叶,田原,冯雨宁,等.游客微博主题情感分析方法比较研究[J].北京大学学报(自然科学版),2018,54(4):687-692.
[2]李小江,蔡洋,卡洛·拉蒂,等.基于街道图像与深度学习的城市景观研究[J].景观设计学,2018,6(2):20-29.
[3]甘欣悦,佘天唯,龙瀛.街道建成环境中的城市非正规性基于北京老城街景图片的人工打分与机器学习相结合的识别探索[J].时代建筑,2018(1):62-68.
[4]叶宇,张灵珠,颜文涛,等.街道绿化品质的人本视角测度框架:基于百度街景数据和机器学习的大规模分析[J].风景园林,2018,25(8):24-29.
[5]张郴,黄震方,张捷,等.基于机器学习的南京市旅游地个性及其文化景观表征[J].地理学报,2017,72(10):1886-1903.
[6]CHEN S,KAN G,LI J,et al.Investigating China’s Urban Air Quality Using Big Data,Information Theory,and Machine Learning[J].Polish Journal of Environmental Studies,2018,27(2):565-578.
[7]路旭,阴劼,丁宇,等.城市色彩调查与定量分析:以深圳市深南大道为例[J].城市规划,2010,34(12):88-92.
[8]路旭,秦涵,王志彬.寒地城市哈尔滨的城市色彩特征研究[J].中国园林,2017,33(2):43-47.
[9]刘毅娟,刘晓明,袁琨.苏州古典园林色彩元素的采集与数据化分析[J].中国园林,2016,32(6):46-51.
[10]周广坤,吴伟.英国城市色彩景观更新与保护机制研究[J].中国园林,2016,32(1):104-108.
[11]谭明,王一婧,成玉宁.五颜六色:数字化景观环境色彩构成研究:以南京赏樱风光带色彩规划设计为例[J].中国园林,2017,33(10):29-34.
[12]顾红男,江洪浪.数字技术支持下的城市色彩主色调量化控制方法:以安康城市色彩规划设计为例[J].规划师,2013,29(10):42-46.
[13]SHEPPARD S R J,CIZEK P.The ethics of Google Earth:crossing thresholds from spatial data to landscape visualization[J].Journal of Environment Management,2009,90:2102-2117.
[14]孙漪南,赵芯,王宇泓,等.基于VR全景图技术的乡村景观视觉评价偏好研究[J].北京林业大学学报,2016,38(12):104-112.
[15]郭素玲,赵宁曦,张建新,等.基于眼动的景观视觉质量评价:以大学生对宏村旅游景观图片的眼动实验为例[J].资源科学,2017,39(6):1137-1147.
[16]DUPONT L,OOMS K,ANTROP M,et al.Comparing saliency maps and eyetracking focus maps:The potential use in visual impact assessment based on landscape photographs[J].Landscape and Urban Planning,2016,148:17-26.
[17]吴榛,王浩,范榕.紫金山国家森林公园景观视觉评价[J].西北林学院学报,2017,32(3):277-283.
[18]JOSHI P.Python机器学习经典实例[M].陈俊杰,陈小莉,译.北京:人民邮电出版社,2017,8:182-185.
[19]吕帅,徐卫国,燕翔.基于快速反馈的建筑方案数字设计方法研究[J].建筑学报,2017(5):18-23.
文中图片均由作者绘制。
[2]李小江,蔡洋,卡洛·拉蒂,等.基于街道图像与深度学习的城市景观研究[J].景观设计学,2018,6(2):20-29.
[3]甘欣悦,佘天唯,龙瀛.街道建成环境中的城市非正规性基于北京老城街景图片的人工打分与机器学习相结合的识别探索[J].时代建筑,2018(1):62-68.
[4]叶宇,张灵珠,颜文涛,等.街道绿化品质的人本视角测度框架:基于百度街景数据和机器学习的大规模分析[J].风景园林,2018,25(8):24-29.
[5]张郴,黄震方,张捷,等.基于机器学习的南京市旅游地个性及其文化景观表征[J].地理学报,2017,72(10):1886-1903.
[6]CHEN S,KAN G,LI J,et al.Investigating China’s Urban Air Quality Using Big Data,Information Theory,and Machine Learning[J].Polish Journal of Environmental Studies,2018,27(2):565-578.
[7]路旭,阴劼,丁宇,等.城市色彩调查与定量分析:以深圳市深南大道为例[J].城市规划,2010,34(12):88-92.
[8]路旭,秦涵,王志彬.寒地城市哈尔滨的城市色彩特征研究[J].中国园林,2017,33(2):43-47.
[9]刘毅娟,刘晓明,袁琨.苏州古典园林色彩元素的采集与数据化分析[J].中国园林,2016,32(6):46-51.
[10]周广坤,吴伟.英国城市色彩景观更新与保护机制研究[J].中国园林,2016,32(1):104-108.
[11]谭明,王一婧,成玉宁.五颜六色:数字化景观环境色彩构成研究:以南京赏樱风光带色彩规划设计为例[J].中国园林,2017,33(10):29-34.
[12]顾红男,江洪浪.数字技术支持下的城市色彩主色调量化控制方法:以安康城市色彩规划设计为例[J].规划师,2013,29(10):42-46.
[13]SHEPPARD S R J,CIZEK P.The ethics of Google Earth:crossing thresholds from spatial data to landscape visualization[J].Journal of Environment Management,2009,90:2102-2117.
[14]孙漪南,赵芯,王宇泓,等.基于VR全景图技术的乡村景观视觉评价偏好研究[J].北京林业大学学报,2016,38(12):104-112.
[15]郭素玲,赵宁曦,张建新,等.基于眼动的景观视觉质量评价:以大学生对宏村旅游景观图片的眼动实验为例[J].资源科学,2017,39(6):1137-1147.
[16]DUPONT L,OOMS K,ANTROP M,et al.Comparing saliency maps and eyetracking focus maps:The potential use in visual impact assessment based on landscape photographs[J].Landscape and Urban Planning,2016,148:17-26.
[17]吴榛,王浩,范榕.紫金山国家森林公园景观视觉评价[J].西北林学院学报,2017,32(3):277-283.
[18]JOSHI P.Python机器学习经典实例[M].陈俊杰,陈小莉,译.北京:人民邮电出版社,2017,8:182-185.
[19]吕帅,徐卫国,燕翔.基于快速反馈的建筑方案数字设计方法研究[J].建筑学报,2017(5):18-23.
文中图片均由作者绘制。