室内POI显著度评价的Fisher判别法模型

doi:10.11947/j.AGCS.2023.20210547

测绘学报 ›› 2023, Vol. 52 ›› Issue (4): 679-688.doi: 10.11947/j.AGCS.2023.20210547

室内POI显著度评价的Fisher判别法模型

李华蓉¹, 郑嘉欣¹, 李天童²

1. 重庆交通大学智慧城市学院, 重庆 400074;
2. 重庆市规划和自然资源调查监测院, 重庆 401120

收稿日期:2021-10-09 修回日期:2022-10-21 发布日期:2023-05-05
通讯作者: 郑嘉欣 E-mail:622200900012@mails.cqjtu.edu.cn
作者简介:李华蓉(1980-),女,博士,副教授,研究方向为时空数据可视分析、室内地图表达与大数据分析处理。E-mail:990020040625@cqjtu.edu.cn
基金资助:
重庆市研究生联合培养基地项目(JDLHPYJD2020005);重庆交通大学研究生科研创新项目资助(2022S0089)

An indoor fisher discriminant model for indoor POI salience evaluation

LI Huarong¹, ZHENG Jiaxin¹, LI Tiantong²

1. School of Smart City, Chongqing Jiaotong University, Chongqing 400074, China;
2. Chongqing Planning and Natural Resources Survey and Monitoring Institute, Chongqing 401120, China

Received:2021-10-09 Revised:2022-10-21 Published:2023-05-05
Supported by:
Chongqing Postgraduate Joint Training Base Project (No. JDLHPYJD2020005);Chongqing Postgraduate Research and Innovation Project (No. 2020S0089)

摘要/Abstract

摘要： 随着社会经济的快速发展,大型建筑物内部结构越来越复杂,室内空间的位置服务愈显重要。地标作为室内空间中的基础要素,能够帮助人们在室内认清方向和定位。但是,现有的室内地标的选取方式大多牵引于室外准则,未考虑室内POI独有的特点,导致所选取出的地标与用户的认知不匹配。针对这一问题,本文在室内空间POI显著度影响因素探究试验基础上,采用Fisher判别法(FDA)对试验数据进行语义信息量化、构建模型、模型回判和交叉互判处理,确定了室内POI显著度评价模型,并用于室内地标的提取。结果表明,建立的判别模型对室内POI显著度的判别和分级效果显著,选取出的地标能够与用户认知结果相一致。

关键词: 空间认知, 室内空间, 显著度模型, POI, Fisher判别分析

Abstract: In the rapid development of the social economy, the structure of large buildings is more and more complex, and people are easily lost in it, so the indoor location service becomes increasingly significant. Landmarks are the basic elements of the indoor space that can help people recognize the indoor orientation and location. However, many existing methods of indoor landmark selection ignore the unique features of indoor POIs and are guided by the outdoor criteria, resulting in a mismatch between the selected landmarks and users' cognition. The paper adopts the fisher discriminant analysis (FDA) for the above problem to process test data from the experiment of exploring factors affecting indoor POIs salience, including quantifying semantic information, building model, model self-judgment and cross-validation. And the model of indoor POI salience evaluation is confirmed to select indoor landmarks. The results indicated that the established model significantly affects discriminating and classifying indoor POI's salience, and the selected landmarks can be consistent with the user's cognitive results.

Key words: spatial cognition, indoor space, salience model, POI, Fisher discriminant analysis

中图分类号:

P208

李华蓉, 郑嘉欣, 李天童. 室内POI显著度评价的Fisher判别法模型[J]. 测绘学报, 2023, 52(4): 679-688.

LI Huarong, ZHENG Jiaxin, LI Tiantong. An indoor fisher discriminant model for indoor POI salience evaluation[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(4): 679-688.

参考文献

[1] LI K J, LEE J Y. Basic concepts of indoor spatial information candidate standard indoor GML and its applications[J].Korea Spatial Information Society, 2013, 21(3): 1-10.
[2] SORROWS M E, HIRTLE S C. The nature of landmarks for real and electronic spaces[C]//Proceedings of 1999 International Conference of COSIT. Berlin, Germany: Springer, 1999: 37-50.
[3] RAUBAL M, WINTER S. Enriching way finding instructions with local landmarks[C]//Proceedings of 2002 International Conference of Geographic Information Science. Boulder, FL, USA:Springer, 2002: 243-259.
[4] KLIPPEL A, WINTER S. Structural salience of landmarks for route directions[C]//Proceedings of 2005 International Conference of Spatial Information Theory. Ellicottville, NY, USA: Springer, 2005: 347-362.
[5] DUCKHAM M, WINTER S, ROBINSON M. Including landmarks in routing instructions[J]. Journal of Location Based Services, 2010, 4(1): 28-52.
[6] GÖTZE J, BOYE J. Learning landmark salience models from users' route instructions[J]. Journal of Location Based Services, 2016, 10(1): 47-63.
[7] FELLNER I, HUANG H, GARTNER G. “Turn left after the WC, and use the lift to go to the 2nd floor”—generation of landmark-based route instructions for indoor navigation[J]. ISPRS International Journal of Geo-Information, 2017, 6(6): 183.
[8] ELIAS B. Extracting landmarks with data mining methods[C]//Proceedings of 2003 International Conference of Spatial Information Theory. Kartause Ittingen, Switzerland: Springer, 2003: 375-389.
[9] HUANG H, GARTNER G. A survey of mobile indoor navigation systems[J]. Cartography in Central and Eastern Europe, 2009: 305-319.
[10] SIEGEL A, WHITE S. The development of spatial representations of large-scale environments [J]. Advances in Child Development and Behavior, 1975, 10:9-55.
[11] 毛凯. 面向室内外寻路的地标认知强度网格模型研究[D]. 武汉: 武汉大学, 2017. MAO Kai. Research on landmark-based cognition strength grid model for outdoor and indoor wayfinding[D]. Wuhan: Wuhan University, 2017.
[12] MILLONIG A, SCHECHTNER K. Developing landmark-based pedestrian-navigation systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(1): 43-49.
[13] RUSSO D, ZLATANOVA S, CLEMENTINI E. Route directions generation using visible landmarks[C]//Proceedings of the 6th ACM Sigspatial International Workshop on Indoor Spatial Awareness. Texas, TX, USA: ACM Press, 2014: 1-8.
[14] HUND A A. Visuospatial working memory facilitates indoor wayfinding and direction giving[J]. Journal of Environmental Psychology, 2016, 45: 233-238.
[15] LI Lin, MAO Kai, LI Guozhong, et al. A Landmark-based cognition strength grid model for indoor guidance[J]. Survey Review, 2018, 50(361): 336-346.
[16] LÜ Hao, YU Zhonghai, MENG Liqiu. A computational method for indoor landmark extraction[J]. Progress in Location-Based Services 2014, 2015: 45-59.
[17] ZHU L, ŠVEDOVÁ H, SHEN J, et al. An instance-based scoring system for indoor landmark salience evaluation[J]. Geografie, 2019, 124(2): 103-131.
[18] LI X, WU X Q, YIN Z H, et al. The influence of spatial familiarity on the landmark salience sensibility in pedestrian navigation environment[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-2/W7: 83-89.
[19] HU Xuke, DING Lei, SHANG Jianga, et al. Data-driven approach to learning salience models of indoor landmarks by using genetic programming[J]. International Journal of Digital Earth, 2020, 13(11): 1230-1257.
[20] ZHOU Zhiyong, WEIBEL R, HUANG Haosheng. Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach[J]. International Journal of Geographical Information Science, 2022, 36(3): 514-546.
[21] BHATTARAI B, YADAV R K, GANG H S, et al. Geomagnetic field based indoor landmark classification using deep learning[J]. IEEE Access, 2019, 7: 33943-33956.
[22] GOLDSTONE R L, LEYDESDORFF L. The import and export of cognitive science[J]. Cognitive Science, 2006, 30(6): 983-993.
[23] LI Zhilin. Information theory of cartography: a framework for entropy-based cartographic communication theory[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020,43: 11-16.
[24] 赵丽娜. Fisher判别法的研究及应用[D]. 哈尔滨: 东北林业大学, 2013. ZHAO Lina. Research and improvement of fisher discriminant analysis method[D]. Harbin: Northeast Forestry University, 2013.
[25] LIU C, WECHSLER H. A shape- and texture-based enhanced Fisher classifier for face recognition[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2001, 10(4): 598-608.
[26] 杨超, 史秀志. 基于Fisher判别法模型的矿山安全标准化等级评价[J]. 黄金科学技术, 2018, 26(2): 187-194. YANG Chao, SHI Xiuzhi. Mine safety standardization grade evaluation based on fisher discriminant model[J]. Gold Science and Technology, 2018, 26(2): 187-194.

室内POI显著度评价的Fisher判别法模型

An indoor fisher discriminant model for indoor POI salience evaluation

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	禹文豪, 魏铖, 陈佳鑫. 面向不平衡POI类别分布的电子地图多层次标签预测模型[J]. 测绘学报, 2023, 52(2): 318-328.
[2]	高俊, 曹雪峰. 空间认知推动地图学学科发展的新方向[J]. 测绘学报, 2021, 50(6): 711-725.
[3]	万刚, 武易天. 地图空间认知的数学基础[J]. 测绘学报, 2021, 50(6): 726-738.
[4]	应申, 张雯博, 苏俊如, 黄丽娜. 地球球观认知分析:以谷歌地球上的寻路任务为例[J]. 测绘学报, 2021, 50(6): 739-748.
[5]	晏雄锋, 艾廷华, 杨敏, 郑建滨. 地图空间形状认知的自编码器深度学习方法[J]. 测绘学报, 2021, 50(6): 757-765.
[6]	郑束蕾. 地理空间认知理论与地图工具的发展[J]. 测绘学报, 2021, 50(6): 766-776.
[7]	黄丽娜, 张定娆, 应申, 艾廷华. 桌面式虚拟环境与真实环境中个体特征影响空间认知能力的差异分析[J]. 测绘学报, 2021, 50(4): 509-521.
[8]	魏智威, 郭庆胜, 程璐, 刘洋, 童莹. 建筑物图形形状相似性计算的序列分析法[J]. 测绘学报, 2021, 50(12): 1683-1693.
[9]	朱婷婷, 涂伟, 乐阳, 钟晨, 赵天鸿, 黎秋平, 李清泉. 利用地理标签数据感知城市活力[J]. 测绘学报, 2020, 49(3): 365-374.
[10]	杜萍, 刘涛, 李鼎凯, 杨晓霞. 应急场景快速制图及地图信息传输[J]. 测绘学报, 2019, 48(6): 747-755.
[11]	刘晓刚, 孙中苗, 管斌, 范昊鹏. 航空重力测量数据向下延拓的改进Poisson积分迭代法[J]. 测绘学报, 2018, 47(9): 1188-1195.
[12]	王圣音, 刘瑜, 陈泽东, 施力, 张晶. 大众点评数据下的城市场所范围感知方法[J]. 测绘学报, 2018, 47(8): 1105-1113.
[13]	万刚, 曹雪峰. 地理空间信息网格的历史演变与思考[J]. 测绘学报, 2016, 45(S1): 15-22.
[14]	邓非, 吴幼丝, 胡玉雷, 崔红霞. 球形全景影像位姿估计的改进EPnP算法[J]. 测绘学报, 2016, 45(6): 677-684.
[15]	刘敏, 黄谟涛, 欧阳永忠, 邓凯亮, 翟国君, 吴太旗. 顾及地形效应的重力向下延拓模型分析与检验[J]. 测绘学报, 2016, 45(5): 521-530.