Pavement texture characteristics can reflect early performance decay, skid resistance, and other information. However, most statistical texture indicators cannot express this difference. This study adopts 3D image camera equipment to collect texture data from laboratory asphalt mixture specimens and actual pavement. A pre-processing method was carried out, including data standardisation, slope correction, missing value and outlier processing, and envelope processing. Then the texture data were calculated based on texture separation, texture power spectrum, grey level co-occurrence matrix, and fractal theory to acquire six leading texture indicators and eight extended indicators. The Pearson correlation coefficient was used to analyse the correlation of different texture indicators. The distinction vector based on the information entropy is calculated to analyse the distinction of the indicators. High correlations between ENE (energy) and ENT (entropy), ENT and D (Minkowski dimension) were found. The CON (contrast) has low correlations with HT (macro-texture power spectrum area), ENT and D. However, the differentiation of ENE and HT is more prominent, and the differentiation of the CON is smaller. ENE, ENT, CON and D indicators based on macro-texture and the corresponding original texture have strong linear correlations. However, the microtexture indicators are not linearly correlated with the corresponding original texture indicators. D, WT (micro-texture power spectrum area) and ENT exhibit high degrees of numerical concentration for the same road sections and may be more statistically helpful in distinguishing the characteristics of the pavement performance decay of the road sections.

General face recognition is currently one of the key technologies in the field of computer vision, and it has achieved tremendous success with the support of deep-learning technology. General face recognition models currently exhibit extremely high accuracy on some high-quality face datasets. However, their performance decreases in challenging environments, such as low-light scenes. To enhance the performance of face recognition models in low-light scenarios, we propose a face recognition approach based on feature decoupling and fusion (DeFFace). Our main idea is to extract facial-related features from images that are not influenced by illumination. First, we introduce a feature decoupling network (D-Net) to decouple the image into facial-related features and illumination-related features. By incorporating the illumination triplet loss optimized with unpaired identity IDs, we regulate illumination-related features to minimize the impact of lighting conditions on the face recognition system. However, the decoupled features are relatively coarse. Therefore, we introduce a feature fusion network (F-Net) to further extract the residual facial-related features from the illumination-related features and fuse them with the initial facial-related features. Finally, we introduce a lighting-facial correlation loss to reduce the correlation between the two decoupled features in the specific space. We demonstrate the effectiveness of our method on four real-world low-light datasets and three simulated low-light datasets. We retrain multiple general face recognition methods using our proposed low-light training sets to further validate the advanced performance of our method. Compared to general face recognition methods, our approach achieves an average improvement of more than 2.11 percentage points on low-light face datasets. In comparison with image enhancement-based solutions, our method shows an average improvement of around 16 percentage points on low-light datasets, and it also delivers an average improvement of approximately 5.67 percentage points when compared to illumination normalization-based methods.