Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAVTarget Detection

2025-04-05

AI Summary

Infrared UAV imagery suffers from temperature-dependent low-frequency non-uniformity, severely degrading target contrast and limiting detection performance. To address this, we propose UniCD, the first end-to-end joint framework that co-optimizes non-uniformity correction (NUC) and UAV target detection. Methodologically, UniCD introduces a detection-aware joint modeling paradigm, incorporating mask-supervised loss and detection-guided self-supervised loss to align feature spaces between correction and detection; it further employs parametric non-uniformity modeling, multi-task joint optimization, and a lightweight backbone. Our contributions include: (1) introducing IRBFD—the first large-scale infrared UAV detection benchmark (50K images); and (2) demonstrating that UniCD improves corrected target contrast by 3.2× and mAP by 12.7% over baseline methods, while enabling real-time inference.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Infrared unmanned aerial vehicle (UAV) images captured using thermal detectors are often affected by temperature dependent low-frequency nonuniformity, which significantly reduces the contrast of the images. Detecting UAV targets under nonuniform conditions is crucial in UAV surveillance applications. Existing methods typically treat infrared nonuniformity correction (NUC) as a preprocessing step for detection, which leads to suboptimal performance. Balancing the two tasks while enhancing detection beneficial information remains challenging. In this paper, we present a detection-friendly union framework, termed UniCD, that simultaneously addresses both infrared NUC and UAV target detection tasks in an end-to-end manner. We first model NUC as a small number of parameter estimation problem jointly driven by priors and data to generate detection-conducive images. Then, we incorporate a new auxiliary loss with target mask supervision into the backbone of the infrared UAV target detection network to strengthen target features while suppressing the background. To better balance correction and detection, we introduce a detection-guided self-supervised loss to reduce feature discrepancies between the two tasks, thereby enhancing detection robustness to varying nonuniformity levels. Additionally, we construct a new benchmark composed of 50,000 infrared images in various nonuniformity types, multi-scale UAV targets and rich backgrounds with target annotations, called IRBFD. Extensive experiments on IRBFD demonstrate that our UniCD is a robust union framework for NUC and UAV target detection while achieving real-time processing capabilities. Dataset can be available at https://github.com/IVPLaboratory/UniCD.

Problem

• Addresses infrared UAV image nonuniformity correction and target detection jointly
• Enhances target detection by suppressing background and improving feature robustness
• Introduces a new benchmark dataset for infrared UAV target detection

Innovation

• End-to-end union framework for NUC and detection
• Detection-guided self-supervised loss balancing
• Parameter estimation driven by priors and data