Real-time video analysis for retail stores

Ehtesham Hassan; Avinash Kumar Maurya

doi:10.1117/12.2179969

4 March 2015 Real-time video analysis for retail stores

Ehtesham Hassan, Avinash Kumar Maurya

Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 94432B (2015) https://doi.org/10.1117/12.2179969
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China

Abstract

With the advancement in video processing technologies, we can capture subtle human responses in a retail store environment which play decisive role in the store management. In this paper, we present a novel surveillance video based analytic system for retail stores targeting localized and global traffic estimate. Development of an intelligent system for human traffic estimation in real-life poses a challenging problem because of the variation and noise involved. In this direction, we begin with a novel human tracking system by an intelligent combination of motion based and image level object detection. We demonstrate the initial evaluation of this approach on available standard dataset yielding promising result. Exact traffic estimate in a retail store require correct separation of customers from service providers. We present a role based human classification framework using Gaussian mixture model for this task. A novel feature descriptor named graded colour histogram is defined for object representation. Using, our role based human classification and tracking system, we have defined a novel computationally efficient framework for two types of analytics generation i.e., region specific people count and dwell-time estimation. This system has been extensively evaluated and tested on four hours of real-life video captured from a retail store.

Citation Download Citation

Ehtesham Hassan and Avinash Kumar Maurya "Real-time video analysis for retail stores", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94432B (4 March 2015); https://doi.org/10.1117/12.2179969

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available