A self tunable transformation function for enhancement of images captured in complex lighting and hazy weather conditions

Date of Award

2015

Degree Name

Ph.D. in Electrical Engineering

Department

Department of Electrical and Computer Engineering

Advisor/Chair

Advisor: Vijayan K. Asari

Abstract

In wide area video surveillance, there is a possibility of having extremely dark, bright and hazy regions in some image frames of a video sequence. The object details neither in the low intensity areas nor in the high intensity areas can be clearly interpreted. Several image processing techniques have been developed to retrieve meaningful information under such complex lighting and bad weather environment. In this dissertation, a new nonlinear transformation function, Self Tunable Trasformation Function (STTF) is proposed to enhance the images capured in such nonuniform lighting and poor weather conditions. The control parameter in this algorithm is determined adaptively based on image statistics.This research proposes a new algorithm to enhance the images with nonuniform lighting is capable of reducing the intensity of bright regions and at the same time enhancing dark regions by reserving the main structure of the illuminance - reflectance characteristics. The main core of the algorithm is a new nonlinear arc sine transfer function that is very flexible in enhancing the dark regions and compressing the intensity of overexposed regions in an image. A neighborhood dependent approach is employed for contrast enhancement. The Laplacian filtered image (reflectance) is added to the enhanced image to preserve the fine details. The quality of the enhanced image is further improved by applying a contrast stretch process. A basic linear color restoration process based on the chromatic information of the original image is employed to convert the enhanced intensity image back to a color image. It is observed that the proposed algorithm yields visually optimal results on images captured under extreme lighting conditions. It is envisaged that the new technique would be useful for improving the visibility of scenes for night time driving and night security situations. Vision based outdoor mobile systems are very sensitive to infelicitous weather circumstances like hazy conditions. The acquisition of image frames in such an environment deteriorates the scene contrast and biases the color information. This research also proposes a new method to recover such scene details, which takes a nonlinear approach, where the haze pixel intensity is manipulated effectively with proposed nonlinear function, STTF. This function is integrated with the optics based haze model to approximate the enhanced inverse transmission of the scene. The transformation function is composed with a variable parameter, which tunes automatically, to produce desired nonlinear mapping for each pixel while maintaining the local contrast. Unlike other state-of art haze removal techniques, which operates on local regions, the proposed method operates on each pixel to eliminate the blocking artifacts and minimizes the processing complexity. Experimental results with quantitative measures demonstrate that the proposed technique yields state-of-the-art performance on hazy images and is suitable to process a dynamic video scenes captured in adverse weather conditions.

Keywords

Photography Lighting, Photography Exposure, Video surveillance, Image processing Digital techniques, Electrical Engineering

Rights Statement

Copyright © 2015, author

Share

COinS