Visual analysis of indoor trajectories based on AOI division

Abstract

Abstract: In large-scale indoor activities, the acquired indoor trajectories data has the characteristics of high spatial and temporal complexity, high-dimensionality and irregularity, which bring many challenges to visual analysis. In order to solve this problem, a visual analysis method based on the area of interest(AOI) division of indoor trajectories was designed for the problems of spatial and temporal distribution of indoor personnel, crowd movement patterns, and abnormal behavior patterns. Users can customize the area of interest and conduct indoor trajectory analysis based on this unit to determine its spatio-temporal pattern, movement pattern or abnormal behavior. Finally, the data of China Vis2019 Challenge was used to verify the effectiveness of the method, and valuable information was obtained through exploratory analysis of indoor personnel trajectories.

Key words: area of interest(AOI) division, visual analysis of indoor trajectory data, spatio-temporal distribution pattern, movement pattern, abnormal behavior pattern

CLC Number:

TP391

HE Huaiqing, ZHANG Yumin, LIU Haohan. Visual analysis of indoor trajectories based on AOI division[J]. Journal of Civil Aviation University of China, 2022, 40(6): 45-52.

References

[1] CHEN Y, YUAN P S, QIU M, et al． An indoor trajectory frequent pat－ tern mining algorithm based on vague grid sequence[J]． Expert Systems with Applications, 2019, 118: 614-624．

[2] RADAELLI L, SABONIS D, LU H, et al． Identifying typical movements among indoor objects: concepts and empirical study [C]//2013 IEEE 14th International Conference on Mobile Data Management, June 3-6, 2013, Milan, Italy． IEEE, 2013: 197-206．

[3] JIANG J G, LV X N, ZHANG Y F, et al． Research on hotspots finding in indoor space based on regression analysis[C]//2018 International Con－ ference on Computing and Data Engineering, May, 2018, Shanghai, China． New York: ACM, 2018: 98-102．

[4] ALSHAMAA D, CHKEIR A, MOURAD-CHEHADE F, et al． A hidden Markov model for indoor trajectory tracking of elderly people[C]//2019 IEEE Sensors Applications Symposium, March 11 -13, 2019, Sophia Antipolis, France． IEEE, 2019: 1-6．

[5] LI L, LI X, YANG Y, et al． Indoor tracking trajectory data similarity analysis with a deep convolutional autoencoder[J]． Sustainable Cities and Society, 2019, 45: 588-595．

[6] KIM J S, KANG H Y, LEE T H, et al． Topology of the prism model for 3D indoor spatial objects[C]//2009 10th International Conference on Mobile Data Management: Systems, Services and Middleware, May 1820, 2009, Taipei, China． IEEE, 2009: 698-703．

[7] 王祖超, 袁晓如．轨迹数据可视分析研究[J]．计算机辅助设计与图形学学报, 2015, 27(1): 9-25．

[8] 蒲剑苏, 屈华民, 倪明选．移动轨迹数据的可视化[J]．计算机辅助设计与图形学学报, 2012, 24(10): 1273-1282． [9] AGRAWAL R, FALOUTSOS C, SWAMI A． Efficient similarity search in sequence databases[M]//Foundations of Data Organization and Algo－ rithms． Berlin, Heidelberg: Springer Berlin Heidelberg, 1993: 69-84．

[10] CHEN L, TAMER魻ZSU M, ORIA V． Robust and fast similarity search for moving object trajectories[C]//2005 ACM SIGMOD International Conference on Management of Data, June 14 -16, 2005, Baltimore, Maryland． New York: ACM, 2005: 491-502．

[11] MARUTA M, SANO Y, YAMAGUCHI K, et al． Visitor behavior analysis based on large-scale Wi-Fi location data [C]//2015 IIAI 4th Interna－ tional Congress on Advanced Applied Informatics, July 12 -16, 2015, Okayama, Japan． IEEE, 2015: 55-60．

[12] YE Y, ZHENG Y, CHEN Y K, et al． Mining individual life pattern based on location history [C]//2009 10th International Conference on Mobile Data Management: Systems, Services and Middleware, May 1820, 2009, Taipei, China． IEEE, 2009: 1-10．

[13] 承达瑜, 秦坤, 裴韬, 等．基于室内定位数据的群体时空行为可视化分析[J]．地球信息科学学报, 2019, 21(1): 36-45．

[14] LIANG W C, WU Z A, CAO J, et al． Understanding customer behavior in shopping mall from indoor tracking data[C]//2018 IEEE 22nd Inter－ national Conference on Computer Supported Cooperative Work in De－ sign, May 9-11, 2018, Nanjing, China． IEEE, 2018: 648-653．

[15] PETRENKO A, SIZO A, QIAN W, et al． Exploring mobility indoors: an application of sensor-based and GIS systems[J]． Transactions in GIS, 2014, 18(3): 351-369．

[16] WEI Y G, YANG D, ZHAO S S, et al． Analysis and application of campus student location data[J]． DEStech Transactions on Computer Science and Engineering, 2018(wicom): 33-35．

[17] PRENTOW T, THOM A, BLUNCK H, et al． Making sense of trajectory data in indoor spaces[C]//2015 16th IEEE International Conference on Mobile Data Management, June 15 -18, 2015, Pittsburgh, PA, USA． IEEE, 2016: 116-121．

[18] GIANNOTTI F, NANNI M, PINELLI F, et al． Trajectory pattern mining [C]//13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 12-15, 2007, San Jose, California, USA． New York: ACM, 2007: 330-339．

[19] MONREALE A, PINELLI F, TRASARTI R, et al． Where Next: a location predictor on trajectory pattern mining[C]//15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, June, 2009, Paris, France． New York: ACM, 2009: 637-646．

[20] 陈为, 沈则潜, 陶煜波．数据可视化[M]．北京: 电子工业出版社, 2013．

[21] H魧GERSTRAND T． What about people in regional science?[J]． Papers of the Regional Science Association, 1970, 24(1): 6-21．

[22] ChinaVis data challenge 2019 home[EB/OL]. (2019-07-07). [2021-0310] http://www.chinavis.org/2019/challenge.html.