Unsupervised Lighting Reflectance Estimation for Robot Monitoring Under Poor Illuminance

Accurate visual detection under poor illuminance is arguably an important and challenging practice for robot monitoring. The purpose of this study is to build detectors for inspection robot under nonuniform and poor lighting conditions. To this end, we propose an unsupervised lighting reflectance estimation framework for dark image detection unsupervised lighting reflectance estimation network (ULRE-Net). Based on lightness-color consistency, the “true color” of objects merely depends on the reflectance regardless of the variations of illuminance. The proposed ULRE-Net extracts robust features for detection by estimating a simple and differentiable expression of reflectance, and the method formulates reflectance estimation in an unsupervised learning manner without relying on image pairs. Thorough experiments are conducted to validate the veracity and generality of the proposed method over existing ones.