Wavelet Energy-Based Adaptive Retinex Algorithm for Low Light Mobile Video Enhancement

Abstract

In today's world, smartphones are ubiquitous and feature high-quality cameras and video recording capabilities. The camera shake, shadows, or other environmental factors lead to poor video, even in low-lighting situations with a high-end camera. To preserve and enhance low-light mobile video, a wavelet energy-based adaptive retinex algorithm is proposed. The first step in the method is to extract frames from the composite video before it is fed into the algorithm in HSV space. The authors then apply the wavelet energy-based adaptive retinex algorithm to the dynamic range-extended value channel. Lighting conditions that cause video degradation are restored adaptively to their natural brightness. A color restoration technique that improves the conventional retinex method fixes the gray world violation problem. Wavelet energy is used as a metric in concurrence with the retinex algorithm to objectively validate image enhancement quality. An experimental work of more than 300 still images and videos show that the proposed technique outperforms the current state of the art.