Multi-Camera Worker Tracking in Logistics Warehouse Considering Wide-Angle Distortion

2025-10-22

AI Summary

In logistics warehouses, wide-angle cameras suffer from severe edge distortion—particularly in the vertical direction—leading to low cross-camera worker localization accuracy. To address this, we propose a multi-camera collaborative calibration method grounded on foot position estimation: it explicitly models and compensates for wide-angle lens distortion via ground-coordinate alignment and foot-sole projection constraints. Our approach integrates image distortion correction, ground-plane projection mapping, appearance-based feature matching, and a digital twin framework to achieve high-consistency, real-time localization. The key innovation lies in leveraging the foot as a stable geometric anchor—overcoming limitations of conventional methods relying solely on image rectification or feature matching—and thereby significantly enhancing cross-camera tracking robustness. Experiments demonstrate over 20% improvement in localization accuracy and confirm superior stability and generalizability in complex warehouse environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Large-scale security measurements

Abstract

With the spread of e-commerce, the logistics market is growing around the world. Therefore, improving the efficiency of warehouse operations is essential. To achieve this, various approaches have been explored, and among them, the use of digital twins is gaining attention. To make this approach possible, it is necessary to accurately collect the positions of workers in a warehouse and reflect them in a virtual space. However, a single camera has limitations in its field of view, therefore sensing with multiple cameras is necessary. In this study, we explored a method to track workers using 19 wide-angle cameras installed on the ceiling, looking down at the floor of the logistics warehouse. To understand the relationship between the camera coordinates and the actual positions in the warehouse, we performed alignment based on the floor surface. However, due to the characteristics of wide-angle cameras, significant distortion occurs at the edges of the image, particularly in the vertical direction. To address this, the detected worker positions from each camera were aligned based on foot positions, reducing the effects of image distortion, and enabling accurate position alignment across cameras. As a result, we confirmed an improvement of over 20% in tracking accuracy. Furthermore, we compared multiple methods for utilizing appearance features and validated the effectiveness of the proposed approach.

Problem

• Tracking workers in logistics warehouses using multiple wide-angle cameras
• Addressing image distortion from wide-angle lenses in camera alignment
• Improving multi-camera position accuracy for digital twin applications

Innovation

• Multi-camera system tracks workers in warehouse
• Foot position alignment reduces wide-angle distortion
• Ceiling-mounted cameras improve tracking accuracy