Backlit Traffic Scene Image Enhancement Based on Foreground and Background Characteristics
The characteristics of low foreground brightness and distorted background brightness in images collected under backlit traffic scenes result in low clarity,serious information loss,and poor identifiability of the collected images.To solve the above problems,a sub-regional enhancement method is proposed to study the different characteristics of the foreground/background of backlit images.Firstly,the maximum inter class variance(OTSU)method is used to segment the foreground and background of the backlight image;next,the LIME method is used globally for the backlight image to enhance foreground brightness while maintaining color distortion;then,the global histogram equalization results on the three RGB channels of background portion are individually mapped to the corresponding limited intervals,improving the contrast of the background.The Canny operator is used to detect the black edges at the stitching part between the foreground and background,and three adaptive filtering templates are generated based on the black edges to perform step-by-step mean filtering on the black edges,eliminating the black edges and improving the visual quality of the image.On a dataset CHD_B self-built in the laboratory,the proposed method is superior in terms of four commonly used objective evaluation indicators.Experimental results show that the proposed image enhancement algorithm can effectively eliminate the backlighting in images.
万方数据
维普
