Video Enhancement for Intelligent Surveillance in Poor Lighting Conditions

Abstract

This work deals with the research work involved in the design of efficient system for intelligent video surveillance applications. A system of video/image fusion and enhancement for visibility improvement is proposed in this work for intelligent surveillance at night or under bad weather conditions. Two videos are acquired, one by a color CCD camera, and the other by a infrared camera (IR). Before performing multispectral fusion, image registration and image preprocessing (denoising, Normalization and enhancement) are required. The IR image and the visible image are then fused. First, a pixel-level multi-resolution based image fusion method is applied to source images. Techniques which will be used in multispectral fusion are Discrete Wavelet Transform(DWT) then the Dual-Tree Complex Wavelet Transform (DT-CWT). After image fusion, a color restoration is performed on fused images with the chromatic information of visible images. We will propose a Modified Look-Up Table (LUT) technique to color the night video. The entire image processing and analysis system will be developed in Matlab/Simulink environment. Preliminary results of fusion obtained in some experiments are presented.