Shopper Behaviour Analysis Based on 3D Situation Awareness Information

Mäkelä, Satu-Marja; Järvinen, Sari; Keränen, Tommi; Lindholm, Mikko; Vildjiounaite, Elena

doi:10.1007/978-3-319-12811-5_10

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tracking algorithm uses objects' locations, height, age, grouping information and Kalman filter to ensure the best matches from frame to frame and from one sensor field of view to another. Matching works as follows [17]: if a person is detected within a pre-defined distance from existing track in a previous frame/field of view, this is assumed to be continuation of the same track. If some track was recently lost (a pre-defined time threshold is used for deciding whether to discard lost tracks or to attempt at their re-identification), its continuation is searched for within larger distance.…”

Section: B Servermentioning

confidence: 99%

Predicting Consumers' Locations in Dynamic Environments via 3D Sensor-Based Tracking

Vildjiounaite

Mäkelä

Järvinen

et al. 2014

2014 Eighth International Conference on Next Generation Mobile Apps, Services and Technologies

Self Cite

View full text Add to dashboard Cite

Brick-and-mortar stores for non-food items allow customers to quickly try items and take them home, but lack certain convenient features of online shopping, such as personalised offers and recommendations for items of possible interest. Mobile in-store shopping applications would allow to combine these advantages if they would derive current customer needs from customer activities. A natural way to infer interests of shops' visitors is to analyse their motion and places where they stop. This paper presents a low-cost depth sensor -based people tracking system and a method to predict future customer locations, developed for environments where items are frequently re-located and customer routes change accordingly. The tracking system employs adaptive background modelling approach, allowing to quickly distinguish between moving humans and relocated objects. Similarity-based location predictions use fairly small datasets of recent tracks of other customers and allow predicting locations of future stops very soon after monitoring starts: after just a few minutes. Therefore this approach also provides for imperfect tracking, e.g., due to occlusions. In the tests with the data, acquired in a real clothing and cosmetics department during 50 days, future places of customers' interest were predicted with an average accuracy 60% and an average distance error half a metre.

show abstract

Section: B Servermentioning

confidence: 99%

Predicting Consumers' Locations in Dynamic Environments via 3D Sensor-Based Tracking

Vildjiounaite

Mäkelä

Järvinen

et al. 2014

2014 Eighth International Conference on Next Generation Mobile Apps, Services and Technologies

Self Cite

View full text Add to dashboard Cite

show abstract

Priming shoppers’ well-being goal in grocery stores: Moving toward healthier food choices?

Luomala

Järvinen

Peltola

et al. 2023

Food Quality and Preference

View full text Add to dashboard Cite

Improving retail efficiency through sensing technologies: A survey

Quintana

Menéndez

Álvarez

et al. 2016

Pattern Recognition Letters

View full text Add to dashboard Cite

Measuring customer reaction to new products for understanding their level of engagement is necessary for the future of retail. This work introduces a workflow to improve the quality and efficiency of the retail establishments in order to increase their attractiveness. Different research fields are explored to fulfill the requirements of the proposed scenario, remarking most useful works in the literature. The manuscript goes through relevant algorithms to infer properties of consumers like demography, attention or behavior based on their appearance (computer vision techniques), and on signal captured by generation sensors from smart mobile devices, that will add a great value for the retailers. This paper offers a complete overview of this research field which covers a great variety of innovative tools.

show abstract

Shopper Behaviour Analysis Based on 3D Situation Awareness Information

Cited by 4 publications

References 18 publications

Predicting Consumers' Locations in Dynamic Environments via 3D Sensor-Based Tracking

Predicting Consumers' Locations in Dynamic Environments via 3D Sensor-Based Tracking

Priming shoppers’ well-being goal in grocery stores: Moving toward healthier food choices?

Improving retail efficiency through sensing technologies: A survey

Contact Info

Product

Resources

About