@InProceedings{JrSilvVieiOliv:2019:DeLeAp,
author = "Jr. , Val{\'e}rio Nogueira and Silva, Jos{\'e} Augusto and
Vieira, Thales and Oliveira, Krerley",
affiliation = "{Federal University of Alagoas (UFAL)} and {Federal University of
Alagoas (UFAL)} and {Federal University of Alagoas (UFAL)} and
{Federal University of Alagoas (UFAL)}",
title = "RetailNet: A deep learning approach for people counting and hot
spots detection in retail stores",
booktitle = "Proceedings...",
year = "2019",
editor = "Oliveira, Luciano Rebou{\c{c}}as de and Sarder, Pinaki and Lage,
Marcos and Sadlo, Filip",
organization = "Conference on Graphics, Patterns and Images, 32. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "deep learning, computer vision, people counting, crowd
estimation.",
abstract = "Customer behavior analysis is an essential issue for retailers,
allowing for optimized store performance, enhanced customer
experience, reduced operational costs, and consequently higher
profitability. Nevertheless, not much attention has been given to
computer vision approaches to automatically extract relevant
information from images that could be of great value to retailers.
In this paper, we present a low-cost deep learning approach to
estimate the number of people in retail stores in real-time and to
detect and visualize hot spots. For this purpose, only an
inexpensive RGB camera, such as a surveillance camera, is
required. To solve the people counting problem, we employ a
supervised learning approach based on a Convolutional Neural
Network (CNN) regression model. We also present a four channel
image representation named RGBP image, composed of the
conventional RGB image and an extra binary image P representing
whether there is a visible person in each pixel of the image. To
extract the latter information, we developed a
foreground/background detection method that considers the
peculiarities of people behavior in retail stores. The P image is
also exploited to detect the hot spots of the store, which can
later be visually analyzed. Several experiments were conducted to
validate, evaluate and compare our approach using a dataset
comprised of videos that were collected from a surveillance camera
placed in a real shoe retail store. Results revealed that our
approach is sufficiently robust to be used in real world
situations and outperforms straightforward CNN approaches.",
conference-location = "Rio de Janeiro, RJ, Brazil",
conference-year = "28-31 Oct. 2019",
doi = "10.1109/SIBGRAPI.2019.00029",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2019.00029",
language = "en",
ibi = "8JMKD3MGPEW34M/3U2AEMS",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/3U2AEMS",
targetfile = "cameraready.pdf",
urlaccessdate = "2024, Apr. 28"
}