Abstract: 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.

Key words: Constrained optimization evolutionary,Image information extraction,Time frequency weighted