约束优化进化的夜间图像时频复合加权提取

Extraction of Nighttime Images with Time Frequency Weighted and Constrained Optimization Evolutionary Algorithm

研究了一种约束优化进化的夜间图像时频复合加权提取技术。对多帧夜间图像的时域与频域同时加权处理是一种深度检索夜间图像信息的先进技术。夜间图像质量低,传统的夜间图像信息检索技术采用单独的时域检索方法,无法对多帧夜间图像的频谱特性进行分析和信息检索。为此,提出一种约束优化进化的夜间图像时频复合加权提取技术。首先在频域和时域同时对多帧原始图像进行处理,提取多帧图像之间的相关信息;然后做加权处理,形成新的图像特征;在此基础上,通过约束优化进化算法对图像信息检索的结果不断进行循环优化,最终达到较好的效果。采用一组夜间图像进行了实验测试,结果显示,采用约束优化进化的夜间图像时频复合加权提取,多帧图像之间的时域和频域特征得到了很好的加权利用,最终实现了图像信息的深度提取。该方法在图像检索领域具有很好的应用价值。

The extraction of nighttime images with time frequency weighted and constrained optimization evolutionary algorithm was studied.The treat ment of multi-frame nighttime images in time domain and frequency domain is an important method for information extraction.In traditional processing method,the low quality nighttime images are treated with a separate time-domain retrieval method,so the whole domain information cannot be used.The extraction of nighttime images with time frequency weighted and constrained optimization evolutionary algorithm was proposed.Firstly,the nighttime images were processed in the time domain and frequency domain simultaneously.Then the multi-frame images were weighted,and the new feature was formed.On this basis,the effect of the images was cyclically improved through constrained optimization evolutionary algorithm,and ultimately a better result was achieved.A team of nighttime images was used to test the ability.The result shows that the information of time domain and frequency domain can be used well,and the image information is extracted with good performance.The algorithm has good value for image information extraction.