城市型风景区边界区域城市空间优化设计方法研究  

Research on the Optimization Design Methods of Urban Space In the Boundary Area of Chinese Urban National Parks

作　　者：胡一可[1] 丁梦月 吴德雯[2] Hu Yike;Ding Mengyue;Wu Dewen

机构地区：[1]天津大学建筑学院 [2]东北大学江河建筑学院

出　　处：《南方建筑》2016年第4期50-55,共6页South Architecture

基　　金：国家自然科学基金青年科学基金项目:城市型风景名胜区边界划定与管理量化研究;项目编号:51208347/E080202;高等学校学科创新引智计划资助项目:低碳城市与建筑创新引智基地;项目编号:B13011

摘　　要：针对城市型风景区边界城市空间较少考虑观景效果、利用率低、活动不便、吸引力差的问题,文章采用计算机视觉技术中的人群行为分析技术对以可达性分析和可视性分析确定的风景区周边具有观景价值的城市公共空间进行研究。首先进行视频处理,基于视频监控技术,建立摄像头传感器网络;然后,进行轨迹识别;其三,在轨迹模式识别和轨迹聚类的基础上进行行为分析;最后,结合人眼对视频帧的判断和现场观察验证数据准确性,匹配活动类型与空间范围,并形成行为原型。由行为原型借助模型分析空间要素与行为原型的关系,形成形态原型。研究结论为基于空间范围和构成要素的空间原型,作为最小的空间构成单元用于城市型风景区边界区域城市空间优化设计中,使空间布局便捷、紧凑、设施完备。Crowd Behavior Analysis technology of Computer Vision Technology can research on valuablepublic urban spaces near the boundary of Urban National Parks, aiming at some problems of urban spaces ofthat area, such as lack of viewing effect, low rate of utilization and attraction, inconvenience for activities. Firstly,use Video Surveillance Technology,and found a camera sensor network. Then,recognize tracks using sensornetworks. Next, analyze behavior based on track recognition and trajectory clustering. Finally,match the activitytypes with space ranges and develop behavior prototypes,coordinating with judgment of human eyes,groundtruth observation and questionnaire investigation. The pattern prototypes will be formed consequently accordingto the relationships between space elements and behavior prototypes which are achieved by model analysis.The achievements of the research are expected to obtain space prototypes near the boundary of Urban NationalParks. The space prototypes,as the smallest unit of urban spaces,can improve urban space layout to be moreconvenient,compact and complete.

关 键 词：风景园林 城市型风景区边界 城市空间原型 视频处理 轨迹识别 行为分析 

分 类 号：TU986.2[建筑科学—城市规划与设计] TU985.12