A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulation

2025-05-16

AI Summary

To address insufficient local-global feature fusion and challenges in modeling long-range dependencies in thermal infrared (TIR) image detection, this paper proposes CRT-YOLO—a computationally efficient TIR object detection framework based on centralized feature regulation. Its core contributions are threefold: (1) the Centralized Feature Pyramid (CFP), the first of its kind, enabling global cross-scale feature coordination; (2) an Efficient Multi-scale Attention (EMA) module that captures long-range contextual dependencies with minimal computational overhead; and (3) YOLO architecture optimizations coupled with TIR-specific feature enhancement strategies. Evaluated on two mainstream TIR benchmarks—FLIR and KAIST—CRT-YOLO achieves state-of-the-art performance, improving mAP by 5.2% over prior methods while maintaining real-time inference speed. Ablation studies comprehensively validate the effectiveness and necessity of each component.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Thermal Infrared (TIR) technology involves the use of sensors to detect and measure infrared radiation emitted by objects, and it is widely utilized across a broad spectrum of applications. The advancements in object detection methods utilizing TIR images have sparked significant research interest. However, most traditional methods lack the capability to effectively extract and fuse local-global information, which is crucial for TIR-domain feature attention. In this study, we present a novel and efficient thermal infrared object detection framework, known as CRT-YOLO, that is based on centralized feature regulation, enabling the establishment of global-range interaction on TIR information. Our proposed model integrates efficient multi-scale attention (EMA) modules, which adeptly capture long-range dependencies while incurring minimal computational overhead. Additionally, it leverages the Centralized Feature Pyramid (CFP) network, which offers global regulation of TIR features. Extensive experiments conducted on two benchmark datasets demonstrate that our CRT-YOLO model significantly outperforms conventional methods for TIR image object detection. Furthermore, the ablation study provides compelling evidence of the effectiveness of our proposed modules, reinforcing the potential impact of our approach on advancing the field of thermal infrared object detection.

Problem

• Enhancing local-global information extraction in TIR object detection
• Improving feature attention for thermal infrared domain applications
• Reducing computational overhead while capturing long-range dependencies

Innovation

• Centralized feature regulation for global interaction
• Efficient multi-scale attention modules
• Centralized Feature Pyramid network