广西师范大学学报（自然科学版） ›› 2026, Vol. 44 ›› Issue (6): 211-224.doi: 10.16088/j.issn.1001-6600.2026012802

• 生态环境科学研究 • 上一篇    下一篇

桂林市山水公园景观视觉偏好研究

李昱晋1,2, 黄东3, 蓝旖旎1,2, 莫燕华1,2, 马姜明1,2, 张惠琴1,4*   

  1. 1.广西师范大学 可持续发展创新研究院, 广西 桂林 541006;
    2.广西漓江流域景观资源保育与可持续利用重点实验室(广西师范大学), 广西 桂林 541006;
    3.桂林市林业科学研究所, 广西 桂林 541004;
    4.广西师范大学 基建处, 广西 桂林 541006
  • 收稿日期:2026-01-28 修回日期:2026-03-27 出版日期:2026-11-05 发布日期:2026-11-10
  • 通讯作者: 张惠琴(1982— ), 女, 山西闻喜人, 广西师范大学高级工程师。E-mail: 56921766@qq.com
  • 基金资助:
    国家重点研发计划(2022YFC3800700);广西重点研发计划(桂科AB25069156);桂林市科技计划(20230102-6,20230102-7)

Research on landscape visual preference of Guilin Shanshui Park, China

Li Yujin1,2, Huang Dong3, Lan Yini1,2, Mo Yanhua1,2, Ma Jiangming1,2, Zhang Huiqin1,4*   

  1. 1. Institute for Sustainable Development and Innovation, Guangxi Normal University, Guilin Guangxi 541006, China;
    2. Guangxi Key Laboratory of Landscape Resources Conservation and Sustainable Utilization in Lijiang River Basin (Guangxi Normal University), Guilin Guangxi 541006, China;
    3. Guilin Forestry Science Research Institute, Guilin Guangxi 541004, China;
    4. Capital Construction Office, Guangxi Normal University, Guilin Guangxi 541006, China
  • Received:2026-01-28 Revised:2026-03-27 Online:2026-11-05 Published:2026-11-10

摘要： 为探究城市公园中自然与人工融合景观的视觉偏好特征,并验证眼动追踪技术与任意分割模型(segment anything model, SAM)在景观量化分析中的适用性,本文以桂林山水公园为研究对象,结合眼动追踪技术、美景度评价法(scenic beauty estimation,SBE)及SAM,构建景观特征、视觉行为和主观评价的多维评价体系。研究选取40名参试者,采集其眼动数据与审美评分,并借助SAM实现景观元素的自动分割与量化分析,系统比较山水公园不同功能区、不同景观元素及不同群体的景观视觉行为差异及其与审美评价的关联。结果表明:1) 核密度分析揭示公园2个主要高值核心区分别为文体娱乐区中南部与游览观光区东北部,平均注视时长与SBE评分呈极显著正相关,游览观光区注视次数最高(25.34次),休闲漫步区最低(22.72次);2) 不同参试者群体对景观元素的视觉偏好存在差异,长期居住组在城市主题广场等人工区域的注视时长显著更高,而短期停留组对景观小品等特色元素注视更久;3) 植物为公园主导景观元素,占比39.0%;SAM景观元素分割结果与眼动关注度指标呈显著相关,证明该模型量化指标可有效反映人类的视觉关注分布,为客观、高效的景观特征分析提供新途径。本文研究为桂林市山水城市公园的景观优化提供实证依据,拓展了眼动追踪与SAM在特定地域景观研究中的应用路径。

关键词: 美景度评价, 任意分割模型, 景观视觉偏好, 眼动追踪, 桂林山水公园

Abstract: To explore the visual preference characteristics of landscapes integrating natural and artificial elements in urban parks, and to verify the applicability of eye tracking technology and the segment anything model (SAM)in landscape quantitative analysis, this study selected Guilin Shanshui Park as the research object. A multi-dimensional evaluation system combining landscape features, visual behavior and subjective assessment was constructed byusing eye-tracking technology, the scenic beauty estimation (SBE) method and the SAM. Forty participants were recruited, and their eye movement data and aesthetic scores were collected. Automatic segmentation and quantitative analysis of landscape elements were carried out with the SAM. Differences in landscape visual behavior among different functional zones, landscape elements and groups in Shanshui Park, as well as their correlation with aesthetic evaluations were systematically compared. The results showed that: 1) Two main high-value cores in the park were revealed by Kernel density analysis, which were located in the south-central part of the Cultural and Sports Entertainment Zone and the northeastern part of the Sightseeing Zone. A highly significant positive correlation was observed between average fixation duration and SBE scores. The highest fixation count (25.34 times) was found in the Sightseeing Zone, while the lowest (22.72 times) was recorded in the Leisure Strolling Zone. 2) Significant differences in visual preferences for landscape elements were detected among different participant groups. The long-term resident group exhibited significantly longer fixation durations in artificial areas such as the Urban Theme Square, while the short-term stay group showed longer fixations on characteristic elements such as landscapesketches. 3) Plants were identified as the dominant landscape element in the park, accounting for 39.0%. A significant correlation between the landscape element segmentation results of the SAM and eye tracking attention indicators was confirmed, which indicates that the quantitative indexes of the model can effectively reflect human visual attention distribution and provide a new approach for objective and efficient landscape feature analysis. This study provided empirical evidence for the landscape optimization of Guilin′s landscape city parks and expanded the application paths of eye-tracking technology and the SAM in the research on landscapes of specific region.

Key words: scenic beauty estimation (SBE), segment anything model (SAM), landscape visual preference, eye tracking, Guilin Shanshui Park, China

中图分类号:  TU986.5

[1] 杨瑞卿, 杨学民, 徐德兰. 生态园林城市建设驱动下的城市绿地景观格局变化研究[J]. 广西师范大学学报(自然科学版), 2020, 38(6): 140-147. DOI: 10.16088/j.issn.1001-6600.2020.06.016.
[2] 李芝也, 王学润, 许烁钰. 视觉感知对热舒适判断的影响机制: 以城市口袋公园为切入点[J]. 生态学报, 2025, 45(12): 5660-5673. DOI: 10.20103/j.stxb.202408312086.
[3] 宋海宁, 张惠琴, 莫燕华, 等. 人地耦合关系下城市绿地景观特征评估: 以桂林市七星区为例[J]. 广西师范大学学报(自然科学版), 2025, 43(1): 121-132. DOI: 10.16088/j.issn.1001-6600.2024052102.
[4] 朱玄戈, 陈翚. 基于情绪认知与眼动追踪的太平街历史文化街区视觉景观评价[J]. 中南林业科技大学学报, 2025, 45(8): 218-228. DOI: 10.14067/j.cnki.1673-923x.2025.08.021.
[5] 张蕊, 李锦涛. 基于深度学习的场景分割算法研究综述[J]. 计算机研究与发展, 2020, 57(4): 859-875. DOI: 10.7544/issn1000-1239.2020.20190513.
[6] 莫秋凡, 高飞, 张兴, 等. 不同声环境下苏州园林视听感知偏好[J]. 中国城市林业, 2024, 22(3): 1-9. DOI: 10.12169/zgcsly.2023.11.13.0003.
[7] 陆诗樱, 田密蜜. 基于眼动技术的杭州富义仓文化公园恢复性环境评价研究[J]. 湖南包装, 2024, 39(4): 34-38, 56. DOI: 10.19686/j.cnki.issn1671-4997.2024.04.009.
[8] 罗玮菁, 袁媛, 王琳婷, 等. 神经科学实验城市蓝色空间对放松情绪与偏好的影响研究: 基于近红外脑功能成像与眼动技术的[J]. 中国园林, 2025, 41(1): 47-54. DOI: 10.19775/j.cla.2025.01.0047.
[9] Pang X X, Jia M Q, Zhang Y. Campus landscape perception decoded by surveys combined with eye tracking: visual and cultural perception for user well-being[J]. Building and Environment, 2025, 283: 113341. DOI: 10.1016/j.buildenv.2025.113341.
[10]Xu X, Dong R, Li Z X, et al. Research on visual experience evaluation of fortress heritage landscape by integrating SBE-SD method and eye movement analysis[J]. Heritage Science, 2024, 12: 281. DOI: 10.1186/s40494-024-01397-w.
[11]周祥, 谭子媚, 陈素青, 等. 基于眼动追踪的历史文化街区城市景观体验评价: 以广州永庆坊为例[J]. 中国园林, 2023, 39(12): 54-59. DOI: 10.19775/j.cla.2023.12.0054.
[12]田德宇, 张耀南, 赵国辉, 等. 基于卷积神经网络的遥感沙漠绿地提取方法[J]. 遥感技术与应用, 2018, 33(1): 151-157.
[13]彭金涛, 王莉, 杨玖贤, 等. 人工神经网络模型在河流减水河段景观质量评价中的应用[J]. 水电站设计, 2011, 27(4): 77-82. DOI: 10.3969/j.issn.1003-9805.2011.04.020.
[14]李晶晶, 张剑飞, 沈守云. 基于历史文化名城山水格局视野下的昆明大观公园景观重构[J]. 园林, 2020, 37(8): 29-33. DOI: 10.12193/j.laing.2020.08.0029.006.
[15]李晓颖, 王浩, 申世广. 景观·产业·游憩: 三位一体生态农业观光园规划设计[J]. 江苏农业科学, 2010, 38(5): 271-273. DOI: 10.15889/j.issn.1002-1302.2010.05.209.
[16]Kerimova N, Sivokhin P, Kodzokova D, et al. Visual processing of green zones in shared courtyards during renting decisions: an eye-tracking study[J]. Urban Forestry & Urban Greening, 2022, 68: 127460. DOI: 10.1016/j.ufug.2022.127460.
[17]刘霈霖, 滕津霖, 周腾, 等. 性别视角下城市绿地环境心理恢复性差异研究: 以南昌市八大山人梅湖景区为例[J]. 现代城市研究, 2025(11): 102-110.
[18]张文婷, 王欢, 刘君君. 西安环城西苑植物景观视觉质量评价[J]. 中国城市林业, 2025, 23(4): 81-88. DOI: 10.12169/zgcsly.2024.12.23.0002.
[19]李成, 祁哲玮, 闫雨, 等. 乡村康养景观规划设计: 以泰安市北石槽村为例[J]. 山东建筑大学学报, 2020, 35(4): 86-93.
[20]Zhou X C, Cen Q Y, Qiu H F. Effects of urban waterfront park landscape elements on visual behavior and public preference: evidence from eye-tracking experiments[J]. Urban Forestry & Urban Greening, 2023, 82: 127889. DOI: 10.1016/j.ufug.2023.127889.
[21]刘思文, 陈烨. 眼动仪应用于公园景观兴趣点研究初探: 以南京市玄武湖公园驳岸场景为例[J]. 城市建筑, 2021, 18(6): 163-165, 169. DOI: 10.19892/j.cnki.csjz.2021.06.49.
[22]侯瑀, 刘东. 基于高频桌面式眼动仪的驾驶人视觉注意特性研究[J]. 辽宁警察学院学报, 2025, 27(2): 97-103.
[23]罗玮菁, 袁媛, 王琳婷, 等. 滨水空间视觉特征的注意力和情绪效应: 基于高校在校学生眼动追踪实验的证据[J]. 中山大学学报(自然科学版中英文), 2025, 64(1): 207-217. DOI: 10.13471/j.cnki.acta.snus.ZR20240187.
[24]邬伟萍. 基于景观三元论的漓江滨水景观探析: 以桂林市城区段为例[J]. 柳州师专学报, 2014, 29(4): 101-104.
[25]Li J Y, Huang Z L, Zheng D L, et al. Effect of landscape elements on public psychology in urban park waterfront green space: a quantitative study by semantic segmentation[J]. Forests, 2023, 14(2): 244. DOI: 10.3390/f14020244.
[26]肖晴, 王雪娟, 连洪燕. 基于SD-SBE法的公园秋季植物景观视觉质量评价[J]. 安徽科技学院学报, 2021, 35(6): 13-18. DOI: 10.19608/j.cnki.1673-8772.2017.1002.
[27]宁春娇, 董雨琴, 杨喻明, 等. 福州飞凤山奥体公园绿道景观视觉评价研究[J]. 江苏林业科技, 2022, 49(5): 9-17. DOI: 10.3969/j.issn.1001-7380.2022.05.003.
[28]陈诗琪, 杨学, 朱荣强, 等. 面向遥感图像解译的参数高效微调研究综述[J]. 中国图象图形学报, 2026, 31(1): 212-242.
[29]蒙小英, 郭志成. 动态视景下的铁路沿线景观偏好研究: 以京秦铁路北京中心城区段为例[J]. 建筑与文化, 2025(2): 116-119. DOI: 10.19875/j.cnki.jzywh.2025.02.035.
[30]肖艳琦, 刘敏, 王宁, 等. 大学校园滨水景观偏好研究[J]. 安徽建筑, 2024, 31(2): 3-6. DOI: 10.16330/j.cnki.1007-7359.2024.2.001.
[31]李嘉晋, 文斌, 唐贤巩. 基于SBE法的乡村森林景观美学质量评估及优化策略: 以长沙市曾家桥村为例[J]. 农业与技术, 2025, 45(13): 105-111. DOI: 10.19754/j.nyyjs.20250715021.
[32]Hayes T R, Henderson J M. Deep saliency models learn low-, mid-, and high-level features to predict scene attention[J]. Scientific Reports, 2021, 11: 18434. DOI: 10.1038/s41598-021-97879-z.
[33]张昕, 徐琪, 胡海辉. 基于心电眼动数据的城市公园景观质量评价[J]. 天津师范大学学报(自然科学版), 2025, 45(5): 67-73. DOI: 10.19638/j.issn1671-1114.20250510.
[34]俞丽娜, 张璇, 李健. 基于自然语言处理的郊野公园景观多维感知研究: 以上海7个郊野公园为例[J]. 园林, 2025, 42(5): 80-89.
[35]Zhang X Y, Xiong X, Chi M H, et al. Research on visual quality assessment and landscape elements influence mechanism of rural greenways[J]. Ecological Indicators, 2024, 160: 111844. DOI: 10.1016/j.ecolind.2024.111844.
[36]谭红树. 基于MSPA分析成都锦江公园景观连通性研究[J]. 现代园艺, 2023, 46(2): 178-181. DOI: 10.14051/j.cnki.xdyy.2023.02.051.
[37]张又天, 许哲源, 陈陆洋, 等. 总体规划中城市景观特色塑造研究: 以柳林县中心城区为例[J]. 智能建筑与智慧城市, 2025(1): 58-60. DOI: 10.13655/j.cnki.ibci.2025.01.016.
[38]戴月, 封雪晴, 张聪, 等. 梅溪湖象鼻窝森林公园规划设计[J]. 世界林业研究, 2025, 38(3): 148-149. DOI: 10.3969/j.issn.1001-4241.2025.03.027.
[1] 青果, 胡金龙, 艾烨, 陈慧婷, 李佩. 基于空间句法和POI数据的综合性公园可达性研究——以成都市中心城区为例[J]. 广西师范大学学报（自然科学版）, 2023, 41(2): 201-212.
[2] 李倩, 刘兴诏, 连欣欣, 林赛男, 李佳芯. 基于空间句法的福州南台岛公园绿地可达性研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(4): 181-195.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发