Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement

TL;DR

This paper introduces a novel infrared image enhancement method that improves scene detail and target saliency without amplifying noise, thereby boosting the performance of downstream vision tasks like detection and segmentation.

Contribution

The paper presents a new task-oriented infrared image enhancement technique combining layer decomposition and morphological reconstruction-based saliency extraction, which outperforms existing methods.

Findings

Enhanced infrared images improve object detection accuracy.

Saliency extraction effectively highlights targets without noise amplification.

Method outperforms state-of-the-art approaches in quality metrics.

Abstract

Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets like bicycles, which significantly affects the performance of downstream high-level vision tasks. Furthermore, achieving contrast enhancement without amplifying noise and losing important information remains a challenge. To address these challenges, we propose a task-oriented infrared image enhancement method. Our approach consists of two key components: layer decomposition and saliency information extraction. First, we design an layer decomposition method for infrared images, which enhances scene details while preserving dark region features, providing more features for subsequent saliency information extraction. Then, we propose a morphological reconstruction-based saliency extraction method that effectively extracts and enhances target information without amplifying noise. Our method improves the image quality for object detection and semantic segmentation tasks. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods.