Automatic Image Quality Monitoring For Integrated Video Surveillance Systems Of Beijing Shanghai High-speed Railway

With the construction of high-speed railway in China, integrated video monitoring system has got rapid development and more and more extensive application. The railway integrated video monitoring systems involved in numerous equipment brands, types, functions and system platforms. But there is no uniform quantization standard to achieve the examination and maintenance. We can’t rely on human to detect the failures of the systems since it is time-consuming and low efficiency. It is an urgent need to establish an automatic monitoring and maintenance tool for railway integrated video system.This paper proposes an automatic image quality monitoring method for integrated video surveillance systems of Beijing Shanghai high-speed railway. Firstly, a fast lifting wavelet algorithm is developed for computationally efficient spatial-frequency deconstruction of images to extract the features of edges in sub-band images. Wavelet analysis with respect to noise, sharpness, brightness, contrast, and modulation transfer function reveals more detailed information to relate the quality of an image to the interpretation by using an artificial neutral network to optimize weightings and results in a promising quantitative measure of image quality. Then, an automatic image abnormality program is developed aiming at detecting and warning for the common image abnormalities, such as blur, noise, and color cast, etc.The algorithm was tested on the Beijing Shanghai high-speed railway surveillance systems. After analysis and test on various videos, the algorithm works well and shows a reliable result.