A Novel Infrared Image Enhancement Based on Correlation Measurement of Visible Image for Urban Traffic Surveillance Systems

Abstract

Infrared imaging sensors are widely employed in urban traffic systems since they are not affected by lighting conditions. However, due to the limitation of hardware and imaging environment, it is difficult to obtain infrared (IR) images at the desired quality. IR images always lack detailed information, which leads to unsatisfying IR image enhancement results with the conventional method. Compared with the IR images, the visible (VIS) images contain detailed information, which could help to enhance the quality of the corresponding IR images. In this article, we propose an effective method to enhance IR images by applying the multi-sensors image. First, we adopt the edge-preserving filter to decompose the IR and VIS images into illumination and reflectance components according to Retinex theory. Second, each region in the IR and VIS image is classified into the related region and non-related region according to the correlation between IR and VIS images. Finally, an adaptive fuzzy plateau HE (AFPHE) is utilized to enhance the illumination component, and a strategy is employed to enhance the detail of the IR reflectance component with the help of VIS images. Experimental results demonstrate that the proposed method can effectively improve the contrast and enhance the detail of the IR images.

Keywords:

• Urban traffic
• IR image enhancement
• Retinex theory
• image correlation

Additional information

Funding

The research in our article is sponsored by National Natural Science Foundation of China (No.61711540303, No.61701327), Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No. MJUKF-IPIC201803).