Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TBC: A Target-Background Contrast Metric for Low-Altitude Infrared and Visible Image Fusion

Yufeng Xie

TL;DR

<3-5 sentence high-level summary> The paper tackles the inadequacy of traditional no-reference metrics (e.g., Entropy and Average Gradient) for evaluating infrared–visible image fusion in low-altitude, nighttime UAV settings, where sensor noise can masquerade as detail. It introduces Target-Background Contrast (TBC), a metric grounded in Weber's Law that assesses the relative contrast between a thermal target and its immediate background using infrared priors and a local background annulus. TBC calculation uses a binary target mask derived from infrared imagery, a surrounding background mask via dilation, and a ratio of mean intensities to penalize background noise while rewarding salient targets. Experimental validation on DroneVehicle and MSRS datasets demonstrates TBC’s better alignment with human perception, monotonic behavior under degradation, and superiority over EN/AG in low-light fusion scenarios, offering a practical standard for evaluating and guiding low-altitude image fusion.

Abstract

Infrared and visible image fusion is a pivotal technology in low-altitude UAV reconnaissance missions, providing high-quality data support for downstream tasks such as target detection and tracking by integrating thermal saliency with background texture details.However, traditional no-reference metrics fail(Specifically,like Entropy (EN) and Average Gradient (AG)) in complex low-light environments. They often misinterpret high-frequency sensor noise as valid detail. This creates a "Noise Trap," paradoxically assigning higher scores to noisy images and misguiding fusion algorithms.To address this, we propose the Target-Background Contrast (TBC) metric. Inspired by Weber's Law, TBC focuses on the relative contrast of salient targets rather than global statistics. Unlike traditional metrics, TBC penalizes background noise and rewards target visibility. Experiments on the DroneVehicle dataset demonstrate that TBC aligns better with human perception and provides a reliable standard for low-altitude scenarios.

TBC: A Target-Background Contrast Metric for Low-Altitude Infrared and Visible Image Fusion

TL;DR

<3-5 sentence high-level summary> The paper tackles the inadequacy of traditional no-reference metrics (e.g., Entropy and Average Gradient) for evaluating infrared–visible image fusion in low-altitude, nighttime UAV settings, where sensor noise can masquerade as detail. It introduces Target-Background Contrast (TBC), a metric grounded in Weber's Law that assesses the relative contrast between a thermal target and its immediate background using infrared priors and a local background annulus. TBC calculation uses a binary target mask derived from infrared imagery, a surrounding background mask via dilation, and a ratio of mean intensities to penalize background noise while rewarding salient targets. Experimental validation on DroneVehicle and MSRS datasets demonstrates TBC’s better alignment with human perception, monotonic behavior under degradation, and superiority over EN/AG in low-light fusion scenarios, offering a practical standard for evaluating and guiding low-altitude image fusion.

Abstract

Infrared and visible image fusion is a pivotal technology in low-altitude UAV reconnaissance missions, providing high-quality data support for downstream tasks such as target detection and tracking by integrating thermal saliency with background texture details.However, traditional no-reference metrics fail(Specifically,like Entropy (EN) and Average Gradient (AG)) in complex low-light environments. They often misinterpret high-frequency sensor noise as valid detail. This creates a "Noise Trap," paradoxically assigning higher scores to noisy images and misguiding fusion algorithms.To address this, we propose the Target-Background Contrast (TBC) metric. Inspired by Weber's Law, TBC focuses on the relative contrast of salient targets rather than global statistics. Unlike traditional metrics, TBC penalizes background noise and rewards target visibility. Experiments on the DroneVehicle dataset demonstrate that TBC aligns better with human perception and provides a reliable standard for low-altitude scenarios.

Paper Structure

This paper contains 16 sections, 7 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Limitations of Traditional Metrics
  4. Entropy (EN)
  5. Average Gradient (AG)
  6. Target-Background Contrast
  7. Weber's Law
  8. Calculation Steps
  9. Why TBC Works
  10. Metric Validation
  11. Experimental Setup
  12. Result Analysis
  13. Conclusion and Future Work
  14. Conclusion
  15. Discussion
  16. ...and 1 more sections

Figures (2)

  • Figure 1: 00942 of Infrared(a) and Visable(b)
  • Figure 2: Trend of DroneVehicle and MSRS