Day color transfer based night video enhancement for surveillance system

Abstract

A dark video captured during night surveillance is insufficient to recognize an action. In order to perform various video analysis operations, a night time video enhancement approach is required. A daytime coloring approach is proposed to improve the visual perception of night video. The day image is down sampled and its color features are applied to the night fusion video. The experimental results are compared with context enhancement fusion methods and objective metrics are used to evaluate the performance of the algorithm. The quality measures show that edge pixel strength and contrast of the surveillance videos are enhanced compared to other methods.

Simple Fusion Based Night Video Enhancement

“…Fig-5 and Fig-6 shows the enhanced result through traditionalcontrast enhancement using tone mapping and global histogram equalization. Some of the related papers denighting [3] and day colour transfer based approach [5] are also implemented and is shown in the Fig-7 and Fig-8. The result of proposed method are also compared with these method and is tabulated in Table-1 It shows the proposed system perform well as compared with the denighting and colour transfer based approach.…”

“…The following Fig-7, Fig-8 shows result of denighting [3] and day color transfer based method [5] and Fig-9 shows the result of proposed method. The table shows performance evaluation of proposed method as compared with other method.…”

“…There are different methods for night video enhancement [3][4][5][6][7][8] to produced improved results. Denighting [3] used retinex theory that produces illumination and reflectance component, illumination component is enhanced through the day time image.…”

“…But it results in object segmentation which is not an impressive one. Day color transfer method [5] uses day color transfer based scheme that maintain lighting of the night image but lack the enhancement of objects that are appeared in the video. Jiang et al [6] self enhancement method that is focus on histogram based contrast enhancement and moving objects region enhancement but it is not suitable when require high degree of brightness preservation and lost details of more darker areas.…”

An Event-Driven Multiple Objects Surveillance System

“…Appropriate luminance required for the smooth functioning of the system is provided by this module [27], [28]. The activation of the lighting module is controlled by the FEEP as a function of the event detector and luminosity sensors integrated in the lighting module outputs [29].…”