Night Vision Anti-Halation Algorithm of Different-Source Image Fusion Based on Low-Frequency Sequence Generation

The abuse of high beam lights dazzles the opposite drivers when vehicles meet at night, which can easily cause traffic accidents. existing night vision anti-halation algorithms based on different-source image fusion eliminate halation and obtain images with rich color details. However, mistakenly some high-brightness important information. In order to address problem, a algorithm low-frequency sequence generation is proposed. model constructed generate sequences different degrees elimination. According estimated illuminance for sequences, proposed synthesis visual information maximization assigns large weight areas good brightness so as without four typical scenes covering most cases driving, effectively eliminates while retaining useful has better universality than other seven advanced comparison algorithms. experimental results show that obtained by more suitable human perception helps improve driving safety.