With the continuous advancement of big data technology, there are many drawbacks in the past urban greenway design. The environment, population distribution, geographic location, spatial distribution, and other factors affect the greenway design. At the same time, a large amount of historical data is mixed. The systematic arrangement has indirectly led to the fact that urban greenway design does not know how to analyze and use past data. There is always a waste of various resources. While greenways bring many positive impacts, they also have negative impacts: it is difficult for the wild animals in the greenways to move along the predetermined passages, and most animals spread in the greenways in a disorderly manner, so that the greenways accelerate the invasion of alien species and diseases to a certain extent. Using big data technology can enable us to allocate resources more reasonably and accurately. The purpose of this article is to study the use of big data technology to rationalize our urban greenway design. This paper adopts a calculation method that closely combines quantitative and qualitative features to study its features. The local feature analysis algorithm can extract and analyze urban spatial data. Spatial remote sensing image technology can deepen our knowledge and understanding of urban spatial characteristics, conduct data mining, provide all the information of urban space, analyze the content and type, and classify it; then filter and integrate the big data in the greenway planning and design information. The information about greenway planning and design in the big data of Dao Design is digitized. This information can be composed of traditional data and dynamic data. Finally, after scientific analysis, the data is subjected to scenario assumptions, modeling, and output, we applied various analysis results to actual operations, and we obtain the final inspection. In fact, this is also going out from actual work, summing up the experience we have done, and again starting from the perspective of specific practice. Compared with our traditional field investigation before, with the guidance of big data analysis, the experimental results of this article show that under the use of big data technology, the wrong resolution of the SegNet semantic classification algorithm for buildings is 9.6%, and the others are 10.9%, 16%, 20%, etc., which are all greater than 9.6%, so the segNet model has a higher image acquisition accuracy. It can solve the problems caused by the lag of the past questionnaires and the small sample size, improve the accuracy of data extraction through algorithms, find some features and problems of greenway design, and complete the urban greening rate through computer algorithms. Calculation and analysis can better provide the most reasonable method for greenway design site selection and route selection.
Read full abstract