TRUDI and TITUS: A Multi-Perspective Dataset and A Three-Stage Recognition System for Transportation Unit Identification

2025-08-04

AI Summary

The absence of publicly available benchmark datasets that capture the diversity and dynamism of real-world port logistics environments hinders the advancement of transport unit identification techniques. Method: This paper introduces TRUDI, the first large-scale, multi-view transport unit identification dataset, encompassing diverse unit types (e.g., shipping containers, tank containers, trailers) and complex port scenarios. We further propose TITUS, a generic three-stage identification system integrating instance segmentation, text detection, and OCR—designed to operate robustly without fixed viewpoint or scene constraints, enabling end-to-end recognition across viewpoints and varying weather conditions. Contribution/Results: Extensive experiments demonstrate that TITUS achieves high accuracy in identifying 11-character alphanumeric IDs under challenging environmental conditions, significantly improving robustness and generalization. TRUDI and TITUS jointly establish a reusable data foundation and technical framework for digital transformation in port logistics.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Motion & Tracking

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Identifying transportation units (TUs) is essential for improving the efficiency of port logistics. However, progress in this field has been hindered by the lack of publicly available benchmark datasets that capture the diversity and dynamics of real-world port environments. To address this gap, we present the TRUDI dataset-a comprehensive collection comprising 35,034 annotated instances across five categories: container, tank container, trailer, ID text, and logo. The images were captured at operational ports using both ground-based and aerial cameras, under a wide variety of lighting and weather conditions. For the identification of TUs-which involves reading the 11-digit alphanumeric ID typically painted on each unit-we introduce TITUS, a dedicated pipeline that operates in three stages: (1) segmenting the TU instances, (2) detecting the location of the ID text, and (3) recognising and validating the extracted ID. Unlike alternative systems, which often require similar scenes, specific camera angles or gate setups, our evaluation demonstrates that TITUS reliably identifies TUs from a range of camera perspectives and in varying lighting and weather conditions. By making the TRUDI dataset publicly available, we provide a robust benchmark that enables the development and comparison of new approaches. This contribution supports digital transformation efforts in multipurpose ports and helps to increase the efficiency of entire logistics chains.

Problem

• Lack of public datasets for diverse port logistics scenarios
• Need for reliable transportation unit ID recognition system
• Challenges in varying lighting and weather conditions

Innovation

• TRUDI dataset with 35,034 annotated instances
• TITUS pipeline: segment, detect, recognize ID
• Works in diverse lighting and weather conditions