A Lightweight Multi-Metric No-Reference Image Quality Assessment Framework for UAV Imaging

TL;DR

This paper presents MM-IQA, a fast, lightweight no-reference image quality assessment framework combining multiple interpretable cues to evaluate UAV images without needing a reference image.

Contribution

Introduces a novel multi-metric NR-IQA framework that is computationally efficient, interpretable, and validated on multiple benchmark datasets for UAV image quality assessment.

Findings

Achieved SRCC values from 0.647 to 0.830 on five benchmark datasets.

Demonstrated consistent cue behavior on synthetic agricultural data.

Implemented in Python/OpenCV with approximately 2 seconds per image.

Abstract

Reliable image quality assessment is essential in applications where large volumes of images are acquired automatically and must be filtered before further analysis. In many practical scenarios, a pristine reference image is unavailable, making no reference image quality assessment (NR-IQA) particularly important. This paper introduces Multi-Metric Image Quality Assessment (MM-IQA), a lightweight multi-metric framework for NR-IQA. It combines interpretable cues related to blur, edge structure, low resolution artifacts, exposure imbalance, noise, haze, and frequency content to produce a single quality score in the range [0,100].MM-IQA was evaluated on five benchmark datasets (KonIQ-10k, LIVE Challenge, KADID-10k, TID2013, and BIQ2021) and achieved SRCC values ranging from 0.647 to 0.830. Additional experiments on a synthetic agricultural dataset showed consistent behavior of the designed cues. The Python/OpenCV implementation required about 1.97 s per image. This method also has modest memory requirements because it stores only a limited number of intermediate grayscale, filtered, and frequency-domain representations, resulting in memory usage that scales linearly with image size. The results show that MM-IQA can be used for fast image quality screening with explicit distortion aware cues and modest computational cost.