You Only Look Once Version 5 and Deep Simple Online and Real-Time Tracking Algorithms for Real-Time Customer Behavior Tracking and Retail Optimization - Open access academic article

Aug 2, 2026

Upload by Miles

The paper investigates real-time computer vision and tracking methods to improve purchasing performance in brick-and-mortar retail environments. It evaluates YOLOv and DeepSORT for detecting products and tracking customer movements, enabling stores to identify popular items and high-traffic zones. The approach combines YOLOv5 for rapid object detection with DeepSORT for maintaining trajectories and interaction analysis. In-store camera and sensor data are used to infer behaviors such as repeatedly inspected products, dwell-time patterns, and product handling. Reported outcomes show modest increases in customer engagement, with conversion rising by about 3 percentage points and inventory waste decreasing from 88% to 75% after deployment.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages31

Reading Time1 h 18 min

AccessFree to download

Abstract

Keywords

Introduction

algorithms Article You Only Look Once Version 5 and Deep Simple Online and Real-Time Tracking Algorithms for Real-Time Customer Behavior Tracking and Retail Optimization Mohamed Shili 1, Osama Sohaib 2,3, * and Salah Hammedi 4,5 Citation: Shili, M.; Sohaib, O.; Hammedi, S. You Only Look Once Version 5 and Deep Simple Online and Real-Time Tracking Algorithms for Real-Time Customer Behavior Tracking and Retail Optimization. Algorithms 2024, 17, 525. [https://](https://)[ ](https://)[doi.org/10.3390/a17110525](doi.org/10.3390/a17110525) Academic Editor: Takeshi Yamada Received: 18 September 2024 Revised: 29 October 2024 Accepted: 13 November 2024 Published: 15 November 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Innov’COM Laboratory, National Engineering School of Carthage, University of Carthage, Charguia II, Carthage 2035, Tunisia; [mohamed.shili@fst.utm.tn](mohamed.shili@fst.utm.tn) 2 School of Computer Science, University of Technology Sydney, Sydney, NSW 2007, Australia 3 School of Business, American University of Ras Al Khaimah, Ras Al Khaimah 72603, United Arab Emirates 4 Networked Objects, Control, and Communication Systems (NOCCS) Laboratory, ENISo, University of Sousse, Sousse 4054, Tunisia; [salahhammedi@yahoo.com](salahhammedi@yahoo.com) 5 Electrical Engineering Department, National School of Engineers of Monastir, Monastir 5000, Tunisia * Correspondence: [osama.sohaib@uts.edu.au](osama.sohaib@uts.edu.au) Abstract: The speedy progress of computer vision and machine learning engineering has inaugurated novel means for improving the purchasing experiment in brick-and-mortar stores. This paper examines the utilization of YOLOv (You Only Look Once) and DeepSORT (Deep Simple Online and Real-Time Tracking) algorithms for the real-time detection and analysis of the purchasing penchant in brick-and-mortar market surroundings. By leveraging these algorithms, stores can track customer behavior, identify popular products, and monitor high-traffic areas, enabling businesses to adapt quickly to customer preferences and optimize store layout and inventory management. The methodology involves the integration of YOLOv5 for accurate and rapid object detection combined with DeepSORT for the effective tracking of customer movements and interactions with products. Information collected in in-store cameras and sensors is handled to detect tendencies in customer behavior, like repeatedly inspected products, periods expended in specific intervals, and product handling. The results indicate a modest improvement in customer engagement, with conversion rates increasing by approximately 3 percentage points, and a decline in inventory waste levels, from 88% to 75%, after system implementation. This study provides essential insights into the further integration of algorithm technology in physical retail locations and demonstrates the revolutionary potential of real-time behavior tracking in the retail industry. This research determines the foundation for future developments in functional strategies and customer experience optimization by offering a solid framework for creating intelligent retail systems. Keywords: DeepSORT; YOLOv5; e-commerce; machine learning; recommender system 1. Introduction Recently, deep learning methods have been proven to provide the most effective performance in many problems. With rapid advancements in artificial intelligence technology, brick-and-mortar stores face substantial difficulty compared with the immense data-driven understanding accessible to online vendors [1,2] . Although e-commerce platforms have access to an exhaustive assessment of customer preferen

FAQs

Which algorithms are used for detection and tracking in the proposed system?

The methodology integrates YOLOv5 for accurate and rapid object detection and DeepSORT for effective real-time tracking of customer movements and interactions with products.

How does the system derive insights about customer behavior in physical stores?

Data from in-store cameras and sensors are processed to detect patterns such as repeatedly inspected products, time spent in specific intervals, and product handling during shopping.

What impact does the system report on retail outcomes after implementation?

Results indicate improved customer engagement, with conversion rates increasing by approximately 3 percentage points, and inventory waste decreasing from 88% to 75% after system deployment.

Aug 2, 2026

Upload by Miles