LRCN-RetailNet: A recurrent neural network architecture for accurate people counting
- PDF / 1,596,335 Bytes
- 21 Pages / 439.642 x 666.49 pts Page_size
- 26 Downloads / 180 Views
LRCN-RetailNet: A recurrent neural network architecture for accurate people counting Lucas Massa1 · Adriano Barbosa2 · Krerley Oliveira3 · Thales Vieira1 Received: 12 May 2020 / Revised: 27 August 2020 / Accepted: 24 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Measuring and analyzing the flow of customers in retail stores is essential for a retailer to better comprehend customers’ behavior and support decision-making. Nevertheless, not much attention has been given to the development of novel technologies for automatic people counting. We introduce LRCN-RetailNet: a recurrent neural network architecture capable of learning a non-linear regression model and accurately predicting the people count from videos captured by low-cost surveillance cameras. The input video format follows the recently proposed RGBP image format, which is comprised of color and people (foreground) information. Our architecture is capable of considering two relevant aspects: spatial features extracted through convolutional layers from the RGBP images; and the temporal coherence of the problem, which is exploited by recurrent layers. We show that, through a supervised learning approach, the trained models are capable of predicting the people count with high accuracy. Additionally, we present and demonstrate that a straightforward modification of the methodology is effective to exclude salespeople from the people count. Comprehensive experiments were conducted to validate, evaluate and compare the proposed architecture. Results corroborated that LRCN-RetailNet remarkably outperforms both the previous RetailNet architecture, which was limited to evaluating a single image per iteration; and two state-of-the-art neural networks for object detection. Finally, computational performance experiments confirmed that the entire methodology is effective to estimate people count in real-time. Keywords People counting · Retail analysis · Surveillance · Deep learning · LRCN
1 Introduction Customer behavior analysis is an essential task to gain relevant insights and drive the decision-making process of retailers. As a result, a merchant may enhance customer
Thales Vieira
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
experience, optimize operational costs and store performance, and consequently maximize profitability [12, 22]. In particular, an inadequate sales staff scheduling may result both in low rates of conversion, i.e. transforming a browsing customer into a buying customer; and in sub-optimal labor costs, which is widely known to be a relevant expenditure in the budget of a retail store [16]. Although buying behaviors can be easily tracked through transaction logs, it is not straightforward to comprehend more hidden patterns such as the flow of non-buyers, since they are usually harder to track. Fortunately, surveillance cameras have become ubiquitous in public indoor environments and particularly in retail stores. Su
Data Loading...
