An AI-Based Solution for Warehouse Safety: Video Surveillance System Based Anomaly Detection in Equipment-Human Interactions with Vanilla Autoencoder

Abstract

The significant growth of the logistics sector in recent years has resulted in the expansion of warehouse operations and an increased use of equipment, leading to a rise in workplace accidents. These incidents are predominantly attributed to factors such as carelessness, fatigue, high work intensity, individual behaviors, lack of experience, insufficient training, and employee negligence. To enhance warehouse safety, it is essential to implement a system capable of real-time prediction of human-equipment interactions. This study proposes a comprehensive video surveillance framework designed to improve occupational safety in warehouse environments. The system integrates key components, including object detection, object tracking, action recognition, and alarm classification, to effectively reduce risks and prevent accidents.The system employs YOLOv7, a deep learning model with the ability to quickly and accurately detect objects in a single network pass, as the object detection methodology, and DeepSORT, an algorithm for object tracking that assigns unique identifiers to each object and utilizes deep learning techniques to improve tracking performance. The action detection component of the system introduces a novel approach by analyzing and identifying actions and movements while detecting anomalies and potential risks. By leveraging features such as the speed, tags, movement direction, and coordinate data of individuals and equipment, the system estimates alarm levels and generates corresponding alarms, providing an innovative and dynamic solution for real-time risk assessment. The system, tested to demonstrate technological capabilities such as real-time responsiveness and high operational success rates, is designed to predict accidents in warehouse environments, generate alarms, and significantly reduce the risk of occupational accidents. © 2025 The Franklin Institute. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.