Shopper behaviour analysis based on 3D situation awareness information

Satu-Marja Mäkelä, Sari Järvinen, Tommi Keränen, Mikko Lindholm, Elena Vildjiounaite (Corresponding author)

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

The customer behaviour understanding is of major importance to brick and mortar retail struggling to keep their market share and competing with online retail. In this paper, we propose a customer behaviour tracking solution based on 3D data. We can cover large areas using numerous inexpensive networked 3D sensors for monitoring and tracking people and we have adopted an adaptive background model in order to be able to react to changes in the store environment. Experiments with people tracking and analysis of the trajectories in a department store show that use of inexpensive 3D sensors and lightweight computation allows classifying shopping behaviour into three classes (passers-by, decisive customers, exploratory customers) with 80 % accuracy.
Original languageEnglish
Title of host publicationVideo Analytics for Audience Measurement
Subtitle of host publicationFirst International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers
PublisherSpringer
Pages134-145
ISBN (Electronic)978-3-319-12811-5
ISBN (Print)978-3-319-12810-8
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
EventVideo Analytics for Audience Measurement: First International Workshop, VAAM 2014, 24 August 2014, Stockholm, Sweden - Stockholm, Sweden
Duration: 24 Aug 2014 → …

Publication series

SeriesLecture Notes in Computer Science
Volume8811
ISSN0302-9743

Conference

ConferenceVideo Analytics for Audience Measurement: First International Workshop, VAAM 2014, 24 August 2014, Stockholm, Sweden
CountrySweden
CityStockholm
Period24/08/14 → …

Fingerprint

Retail stores
Sensors
Brick
Mortar
Trajectories
Monitoring
Experiments

Keywords

  • behaviour analysis
  • shopper behaviour
  • depth sensor based people tracking
  • depth sensor based situtation awareness

Cite this

Mäkelä, S-M., Järvinen, S., Keränen, T., Lindholm, M., & Vildjiounaite, E. (2014). Shopper behaviour analysis based on 3D situation awareness information. In Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers (pp. 134-145). Springer. Lecture Notes in Computer Science, Vol.. 8811 https://doi.org/10.1007/978-3-319-12811-5_10
Mäkelä, Satu-Marja ; Järvinen, Sari ; Keränen, Tommi ; Lindholm, Mikko ; Vildjiounaite, Elena. / Shopper behaviour analysis based on 3D situation awareness information. Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers. Springer, 2014. pp. 134-145 (Lecture Notes in Computer Science, Vol. 8811).
@inproceedings{ed1d37857f52412ba61041c391531c85,
title = "Shopper behaviour analysis based on 3D situation awareness information",
abstract = "The customer behaviour understanding is of major importance to brick and mortar retail struggling to keep their market share and competing with online retail. In this paper, we propose a customer behaviour tracking solution based on 3D data. We can cover large areas using numerous inexpensive networked 3D sensors for monitoring and tracking people and we have adopted an adaptive background model in order to be able to react to changes in the store environment. Experiments with people tracking and analysis of the trajectories in a department store show that use of inexpensive 3D sensors and lightweight computation allows classifying shopping behaviour into three classes (passers-by, decisive customers, exploratory customers) with 80 {\%} accuracy.",
keywords = "behaviour analysis, shopper behaviour, depth sensor based people tracking, depth sensor based situtation awareness",
author = "Satu-Marja M{\"a}kel{\"a} and Sari J{\"a}rvinen and Tommi Ker{\"a}nen and Mikko Lindholm and Elena Vildjiounaite",
year = "2014",
doi = "10.1007/978-3-319-12811-5_10",
language = "English",
isbn = "978-3-319-12810-8",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "134--145",
booktitle = "Video Analytics for Audience Measurement",
address = "Germany",

}

Mäkelä, S-M, Järvinen, S, Keränen, T, Lindholm, M & Vildjiounaite, E 2014, Shopper behaviour analysis based on 3D situation awareness information. in Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers. Springer, Lecture Notes in Computer Science, vol. 8811, pp. 134-145, Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, 24 August 2014, Stockholm, Sweden, Stockholm, Sweden, 24/08/14. https://doi.org/10.1007/978-3-319-12811-5_10

Shopper behaviour analysis based on 3D situation awareness information. / Mäkelä, Satu-Marja; Järvinen, Sari; Keränen, Tommi; Lindholm, Mikko; Vildjiounaite, Elena (Corresponding author).

Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers. Springer, 2014. p. 134-145 (Lecture Notes in Computer Science, Vol. 8811).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Shopper behaviour analysis based on 3D situation awareness information

AU - Mäkelä, Satu-Marja

AU - Järvinen, Sari

AU - Keränen, Tommi

AU - Lindholm, Mikko

AU - Vildjiounaite, Elena

PY - 2014

Y1 - 2014

N2 - The customer behaviour understanding is of major importance to brick and mortar retail struggling to keep their market share and competing with online retail. In this paper, we propose a customer behaviour tracking solution based on 3D data. We can cover large areas using numerous inexpensive networked 3D sensors for monitoring and tracking people and we have adopted an adaptive background model in order to be able to react to changes in the store environment. Experiments with people tracking and analysis of the trajectories in a department store show that use of inexpensive 3D sensors and lightweight computation allows classifying shopping behaviour into three classes (passers-by, decisive customers, exploratory customers) with 80 % accuracy.

AB - The customer behaviour understanding is of major importance to brick and mortar retail struggling to keep their market share and competing with online retail. In this paper, we propose a customer behaviour tracking solution based on 3D data. We can cover large areas using numerous inexpensive networked 3D sensors for monitoring and tracking people and we have adopted an adaptive background model in order to be able to react to changes in the store environment. Experiments with people tracking and analysis of the trajectories in a department store show that use of inexpensive 3D sensors and lightweight computation allows classifying shopping behaviour into three classes (passers-by, decisive customers, exploratory customers) with 80 % accuracy.

KW - behaviour analysis

KW - shopper behaviour

KW - depth sensor based people tracking

KW - depth sensor based situtation awareness

U2 - 10.1007/978-3-319-12811-5_10

DO - 10.1007/978-3-319-12811-5_10

M3 - Conference article in proceedings

SN - 978-3-319-12810-8

T3 - Lecture Notes in Computer Science

SP - 134

EP - 145

BT - Video Analytics for Audience Measurement

PB - Springer

ER -

Mäkelä S-M, Järvinen S, Keränen T, Lindholm M, Vildjiounaite E. Shopper behaviour analysis based on 3D situation awareness information. In Video Analytics for Audience Measurement: First International Workshop, VAAM 2014, Stockholm, Sweden, August 24, 2014. Revised Selected Papers. Springer. 2014. p. 134-145. (Lecture Notes in Computer Science, Vol. 8811). https://doi.org/10.1007/978-3-319-12811-5_10