地理科学进展 ›› 2023, Vol. 42 ›› Issue (1): 104-115.doi: 10.18306/dlkxjz.2023.01.009

• 研究论文 • 上一篇    下一篇

基于街景图像的古镇旅游地商业同质化空间测度——以大理古城为例

李显正1(), 赵振斌1,2,*(), 刘阳1,2, 张大钊1, 张戬1, 张予倩1   

  1. 1.陕西师范大学地理科学与旅游学院,西安710119
    2.陕西省旅游信息科学重点实验室,西安 710119
  • 收稿日期:2022-05-18 修回日期:2022-08-06 出版日期:2023-01-28 发布日期:2023-03-28
  • 通讯作者: *赵振斌(1965— ),男,陕西洛南人,博士,教授,研究方向为人文地理与社区旅游。E-mail: zhaozhb@snnu.edu.cn
  • 作者简介:李显正(1998— ),男,山东济宁人,硕士生,研究方向为大数据与社区旅游。E-mail: lxzsnnu@163.com
  • 基金资助:
    国家自然科学基金项目(41971227);国家自然科学基金项目(42201245);中国博士后科学基金资助项目(2022M711998);陕西省科技计划重点研发计划项目(2023-YBSF-029)

Spatial measurement of commercial homogeneity of ancient town destination based on street view images: A case study of Dali ancient city

LI Xianzheng1(), ZHAO Zhenbin1,2,*(), LIU Yang1,2, ZHANG Dazhao1, ZHANG Jian1, ZHANG Yuqian1   

  1. 1. School of Geography and Tourism, Shaanxi Normal University, Xi'an 710119, China
    2. Shaanxi Key Laboratory of Tourism Informatics, Xi'an 710119, China
  • Received:2022-05-18 Revised:2022-08-06 Online:2023-01-28 Published:2023-03-28
  • Supported by:
    National Natural Science Foundation of China(41971227);National Natural Science Foundation of China(42201245);China Postdoctoral Science Foundation(2022M711998);The Key Research and Development Project of Shaanxi Provincial Science and Technology Plan(2023-YBSF-029)

摘要:

古镇类旅游地的商业同质化是该类旅游目的地同质化的主要表现,这种现象在一定程度上促进了旅游地的经济发展,但也影响到了游客的旅游体验,导致了目的地商业经营的无序局面。论文以大理古城为例,通过编程获取大理古城内部的街景图像数据,并利用计算机视觉、机器学习等技术识别出街景图像中的店铺标牌文字信息。在此基础上构建指标模型,对案例地商业同质化进行测度,探讨了古镇旅游地商业同质化的空间特征及其形成机制。结论如下:① 大理古城总体商业同质化的空间分布呈现核心—外围特征。商品经营型店铺在旅游核心区的商业同质化程度高,表现出街道分布的特点;而服务经营型店铺在旅游外围区的商业同质化程度高,表现出街区分布的特点。② 旅游资源分布、规划调控、区位条件和资本介入是导致商业同质化的主要因素,竞争和聚集是形成商业同质化的2种主导机制。③ 利用计算机视觉与机器学习等技术提取街景图像中的店铺标牌文字信息,将同类型店铺的重复数量和集聚水平作为指标构建模型并结合GIS空间分析方法,能够实现对古镇旅游地商业同质化的空间测度。该研究的数据处理方法与模型构建方法可丰富利用街景图像进行的社会景观研究,相关结论可为古镇旅游地的管理和高质量发展提供参考。

关键词: 商业同质化, 街景图像, 语言景观, 计算机视觉, 机器学习, 大理古城

Abstract:

The commercial homogenization of ancient town tourism destination is the main manifestation of the homogenization of this type of tourism destination. Although to some extent this phenomenon promotes the economic development of the tourism destination, it also affects the tourism experience of tourists and leads to the disorder of the commercial operation of the destination. Taking Dali ancient city as an example, this study obtained the street view image data inside the ancient city through programming, and used computer vision, machine learning, and other technologies to identify the shop sign text information in the street view images. On this basis, this study constructed an index model to measure the commercial homogeneity of the case, and examined the spatial characteristics and formation mechanism of the commercial homogenization of the ancient town tourism destination. The conclusions are as follows: 1) Spatially, the overall commercial homogeneity of Dali ancient city presents the characteristics of core-periphery distribution. The commercial homogenization degree of stores is high in the core tourism area, showing the characteristics of street-level distribution, while the commercial homogenization degree of service firms is high in the peripheral tourism area, showing the characteristics of city block-level distribution. 2) The distribution of tourism resources, planning and regulation, location conditions, and capital intervention are the main factors leading to commercial homogenization. Competition and spatial aggregation are the two leading mechanisms to form commercial homogenization. 3) Using computer vision and machine learning technologies to extract the shop sign text information in the street view images and taking the repetition number and agglomeration level of the same type of shops as indicators to build a model, combined with GIS spatial analysis method, we can realize the spatial measurement of the commercial homogeneity of the ancient town tourism destination.

Key words: commercial homogenization, street view images, language landscape, computer vision, machine learning, Dali ancient city