Pedestrian trajectory classification method by machine learning using data of laser-scanner tracking system

被引：0

作者：

Kaneko H. ^{[1
]}

Osaragi T. ^{[2
]}

机构：

[1] School of Environment and Society, Tokyo Institute of Technology

来源：

Journal of Environmental Engineering (Japan) | 2017年 / 82卷 / 742期

关键词：

Classication of trajectory; Laser-Scanner; Pedestrian trajectory data; Restricted Boltzmann machine;

D O I：

10.3130/aije.82.1051

中图分类号：

TN2 [光电子技术、激光技术];

学科分类号：

0803 ; 080401 ; 080901 ;

摘要：

The trajectory analysis of pedestrians using the tracking system of laser-scanners is an effective approach for understanding the usage of facility spaces. However, it requires a heavy load to manually extract the features from pedestrian trajectories and classify them into characterized patterns. Hence, it is highly desirable to achieve this task automatically. In this paper, we propose a method of pedestrian trajectory classification using the Restricted Boltzmann machine, by which we can automatically find the inherent features. This method is applied to a hospital outpatient waiting area. Comparing manual and automatic classification, we demonstrate the usefulness of our proposed method.

引用

页码：1051 / 1059

页数：8

共 10 条

[1]

Kaneko H., Osaragi T., Estimation of sitting-and-moving behavior and face-to-face communication of office-workers using laser-scanner trajectory data, Journal of Environmental Engineering (Transactions of AIJ), 79, 706, pp. 1083-1092, (2014)

[2]

Kaneko H., Osaragi T., Extraction of the spatio-temporal activity of office-workers using laser-scanner trajectory data, Journal of Environmental Engineering (Transactions of AIJ), 80, 712, pp. 559-566, (2015)

[3]

Senin P., Dynamic Time Warping Algorithm Review, Information and Computer Science Department, University of Hawaii at Manoa, (2008)

[4]

Ukai M., Nagamine N., Development of Image Processing Method for Detection of Suspicious Acts, RIRI REPORT, 21, 11, pp. 17-22, (2007)

[5]

Hinton G.E., Osindero S., Teh Y., A fast learning algorithm for deep belief nets, Neural Computation, 18, pp. 1527-1554, (2006)

[6]

Bishop C.M., Pattern Recognition and Machine Learning, (2006)

[7]

Asou H., Et al., Deep learning, Kindaikagakusha, (2015)

[8]

Okatani T., Deep learning (machine learning professional series, Koudansha, (2015)

[9]

Osawa M., Hagiwara M., Analysis of learning characteristics of rbm and automatic method for deciding the number of hidden neurons, IEICE Technical Report NC2014-22, (2014)

[10]

Kaneko H., Osaragi T., Feature Extraction for Pedestrian Trajectory Classification Using Laser-scanner Trajectory Data, Summaries of Technical Papers of Annual Meeting, Architectural Institute of Japan, Information Systems Technology, pp. 19-20, (2016)

← 1 →