城市街道景观色彩对游客情感感知影响——基于街景图像的研究
齐子吟(2000— ),女,陕西西安人,硕士生,主要从事旅游地理与在线旅游等研究。E-mail: qzyin612@163.com |
Copy editor: 蒋树芳 黄光玉
收稿日期: 2023-04-07
修回日期: 2023-08-03
网络出版日期: 2024-03-27
基金资助
国家自然科学基金面上项目(42071169)
国家自然科学基金面上项目(42271468)
陕西省重点研发项目(2019ZDLSF07-04)
The Influence of Urban Streetscape Color on Tourists' Emotional Perception Based on Streetscape Images
Received date: 2023-04-07
Revised date: 2023-08-03
Online published: 2024-03-27
Supported by
National Natural Science Foundation of China(42071169)
National Natural Science Foundation of China(42271468)
Shaanxi Province Key Research and Development Program(2019ZDLSF07-04)
街道是城市旅游的重要吸引物,探讨街道景观色彩特征对游客情感感知的影响,对城市街道景观合理规划和布局具有重要的参考价值。本研究以西安市主要建成区为案例地,运用全卷积神经网络(FCN)和随机森林(RF)算法,构建街景图像情感感知数据集,基于街景图像利用机器学习对街道景观的色彩特征进行提取,构建色彩量化指标并将其进行空间可视化;最后,运用随机森林回归算法探讨街道景观色彩特征与游客情感感知之间的关系,并得出最佳色彩特征参数。结果表明:① 游客情感感知具有明显的空间分布格局,美丽和活泼情感由中心区域向外逐渐增加,安全和富有在主城区外二环以内区域得分较高,无聊在该范围内则较低,压抑情感由中心区域向外逐渐降低,游客在非惯常环境中的情感感知与居民在惯常环境中的情感感知在空间分布上具有一定的同质性;② 街道景观色彩特征与游客情感感知呈现出复杂的非线性关系。色彩复杂度对美丽和活泼的影响小于色彩协调度,对无聊、压抑、安全、富有的影响大于色彩协调度,当色彩复杂度取值为0.86,色彩协调度取值为0.84时,游客在六个维度可以获得较好的情感感知;③ 一般情况下,街道景观色彩特征越显著,越能够带给游客较好的情感感知。研究在理论上印证了环境色彩越协调,游客体验感越好这一结论;在方法上,丰富了街景大数据和机器学习方法在旅游情感领域的应用。本研究为城市管理者了解游客的街道景观视觉偏好以及优化街道景观设计提供参考。
齐子吟 , 李君轶 , 贺哲 , 杨喜平 . 城市街道景观色彩对游客情感感知影响——基于街景图像的研究[J]. 地球信息科学学报, 2024 , 26(2) : 514 -529 . DOI: 10.12082/dqxxkx.2024.230181
Streets are an important attraction for urban tourism. Exploring the influence of street landscape color characteristics on tourists' emotional perception holds important reference value for the rational planning and layout of urban street landscape. This study takes the built-up area within the third ring road of Xi'an city as a study case, and employs the Full Convolutional Neural Network (FCN) and Random Forest (RF) algorithms to construct an emotional perception dataset of street images. We use the streetscape images as the basis to extract the color features of the streetscape using machine learning algorithms, and color quantifiers are constructed and spatially visualized; The RF regression algorithm is used to explore the relationship between streetscape color characteristics and tourists' emotional perception, and the optimal color characteristic parameters are derived. The results show that: (1) There is a distinct spatial distribution pattern of tourists' emotional perception. The emotions of beauty and liveness gradually increase from the central area outward, and emotions of safety and wealth emotions score higher in the area within the second ring road outside the main city. While boring emotions score lower in this area, and depressing emotions gradually decrease from the central area outward. This suggests that the spatial distribution pattern of emotional perception shares somewhat homogeneity between tourists' emotional perception in non-routine environment and residents' perception in familiar environment; (2) The color characteristics of the streetscape show a complex non-linear relationship with tourists' emotional perception. For example, color complexity has less effect on emotions of beauty and liveness compared to color coordination and has a greater effect on emotions of boredom, depression, safety, and wealth than color coordination. Moreover, when the value of color complexity is 0.86 and the value of color coordination is 0.84, tourists can obtain better emotional perception across six dimensions; (3) Under non-routine conditions, the more significant the color characteristics of the street landscape, the better the emotional perception of visitors. Theoretically, this study confirms the conclusion that the more colorful environment leads to better experience for tourists; and methodologically, this paper not only expands the traditional text-based and manually-assigned research methods in the field of tourism emotion, but also enriches the application of streetscape big data and machine learning methods in the field of tourism. This study provides a reference for city managers to understand tourists' visual preferences for streetscapes and to optimize streetscape design.
表1 游客人口学特征Tab. 1 Demographic characteristics of tourists |
名称 | 类别 | 频数 | 百分比/% | 名称 | 类别 | 频数 | 百分比/% |
---|---|---|---|---|---|---|---|
性别 | 男 | 22 | 44.90 | 硕士及以上 | 20 | 40.82 | |
女 | 27 | 55.10 | 在校学生 | 10 | 20.41 | ||
年龄 | 18~30 | 25 | 51.02 | 公司职员 | 11 | 22.45 | |
31~40 | 21 | 42.86 | 专业人员(教师/医生/律师等) | 4 | 8.16 | ||
41~50 | 3 | 6.12 | 职业 | 事业单位/公务员/政府工作人员 | 16 | 32.65 | |
地区 | 西安 | 6 | 12.24 | 服务业人员 | 2 | 4.08 | |
陕西省内非西安 | 5 | 10.20 | 工人 | 1 | 2.04 | ||
陕西省外 | 38 | 77.55 | 自由职业 | 2 | 4.08 | ||
受教育程度 | 高中/中专 | 1 | 2.04 | 其他 | 3 | 6.12 | |
本科/专科 | 28 | 57.14 | 合计 | 49 | 100.00 |
表2 “情感感知”相关性分析Tab. 2 "Emotion perception" correlation analysis |
美丽 | 无聊 | 压抑 | 活泼 | 安全 | 富有 | |
---|---|---|---|---|---|---|
美丽 | 1 | -0.814** | -0.638** | 0.907** | 0.706** | 0.753** |
无聊 | 1 | 0.237** | -0.870** | -0.903** | -0.844** | |
压抑 | 1 | -0.474** | -0.059** | -0.131** | ||
活泼 | 1 | 0.809** | 0.813** | |||
安全 | 1 | 0.877** | ||||
富有 | 1 |
注:**表示在 0.01 的水平上,相关性显著。 |
表3 色彩-情感感知相关性分析Tab. 3 Color-emotion perception correlation analysis |
美丽 | 无聊 | 压抑 | 活泼 | 安全 | 富有 | |
---|---|---|---|---|---|---|
复杂度-色彩 | -0.005 | -0.188** | 0.325** | 0.055** | 0.245** | 0.214** |
协调度-色彩 | 0.046** | 0.088** | -0.227** | -0.053** | -0.113** | -0.067** |
注:**表示在 0.01 的水平上,相关性显著。 |
表4 色彩复杂度与游客情感感知回归分析Tab. 4 Regression analysis of color complexity and visitor emotional perception |
模型 | 非标准化系数 | 标准化系数 | t | |
---|---|---|---|---|
B | Std. Error | Beta | ||
(常量) | 82.057** | 0.510 | - | 160.984 |
美丽 | 0.043** | 0.005 | 0.132** | 8.876 |
无聊 | -0.058** | 0.004 | -0.179** | -14.365 |
压抑 | 0.090** | 0.002 | 0.394** | 45.240 |
活泼 | -0.052** | 0.004 | -0.154** | -12.057 |
安全 | 0.023** | 0.004 | 0.064** | 5.079 |
富有 | 0.026** | 0.003 | 0.084** | 8.144 |
注:**表示系数在0.01的水平上显著。 |
表5 色彩协调度与游客情感感知回归分析Tab. 5 Regression analysis of color coordination and visitor emotional perception |
模型 | 非标准化系数 | 标准化系数 | t | |
---|---|---|---|---|
B | Std. Error | Beta | ||
(常量) | 87.749** | 0.811 | - | 108.231 |
美丽 | 0.050** | 0.008 | 0.101** | 6.470 |
无聊 | 0.046** | 0.006 | 0.093** | 7.116 |
压抑 | -0.131** | 0.003 | -0.381** | -41.607 |
活泼 | -0.244** | 0.007 | -0.475** | -35.392 |
安全 | 0.055** | 0.007 | 0.102** | 7.682 |
富有 | 0.086** | 0.005 | 0.183** | 16.876 |
注:**表示系数在0.01的水平上显著。 |
[1] |
|
[2] |
毕芳菲, 蔺宝钢, 刘昊天. 城市景观设计与公共街道造景艺术设计的界定——评《公共环境艺术设计》[J]. 热带作物学报, 2021, 42(9):2744.
[
|
[3] |
简雅各布斯. 美国大城市的死与生[M]. 南京: 译林出版社, 1961.
[
|
[4] |
|
[5] |
曾诗晴, 谢彦君, 史艳荣. 从城市意象到街道体验——城市旅游多层级消费决策中的景观迭代过程[J]. 旅游学刊, 2022, 37(1):68-84.
[
|
[6] |
|
[7] |
王萌, 李君轶. 城市历史文化街区景观对游客情感及行为意向影响研究 ——以西安历史文化街区为例[J]. 西南大学学报(自然科学版), 2021, 43(10):146-153.
[
|
[8] |
|
[9] |
|
[10] |
|
[11] |
|
[12] |
|
[13] |
|
[14] |
|
[15] |
|
[16] |
孙晓涵, 李君轶. 中国本土游客情感体验量表开发与检验[J]. 干旱区资源与环境, 2021, 35(1):189-195.
[
|
[17] |
|
[18] |
杜莹莹, 李君轶. 国内外游客景区情感体验时空变化对比研究——以秦始皇帝陵博物院为例[J]. 地域研究与开发, 2022, 41(4):125-130.
[
|
[19] |
刘丹萍, 金程. 旅游中的情感研究综述[J]. 旅游科学, 2015, 29(2):74-85.
[
|
[20] |
|
[21] |
|
[22] |
|
[23] |
张帆, 刘瑜. 街景影像——基于人工智能的方法与应用[J]. 遥感学报, 2021, 25(5):1043-1054.
[
|
[24] |
|
[25] |
|
[26] |
|
[27] |
|
[28] |
|
[29] |
|
[30] |
|
[31] |
赵文婷. 基于空间分析视角的西安市路网交通效率分析[D]. 西安: 西北大学, 2018.
[
|
[32] |
沈晓萌. 基于景观感知的乡村自然教育营地规划设计研究——以乌镇横港村自然教育营地为例[D]. 北京: 北京林业大学, 2019.
[
|
[33] |
|
[34] |
|
[35] |
|
[36] |
|
[37] |
|
/
〈 | 〉 |