Skip to Main Content
Road traffic monitoring using visual-based camera and real-time image processing techniques has been actively investigated over the years. Traffic image sequences are important information for the purpose of traffic system control and traffic accidents surveillance, for example, the determination of offending vehicles. In this paper, a semifragile watermarking method for authentication of traffic images is proposed using the pinned sine transform (PST). The watermarking system can localize the portions of image that have been tampered maliciously with high accuracy. In particular, the watermarking scheme is very sensitive to any texture alteration in the watermarked images, which is crucial for traffic image analysis. The overlapping block division in the process of PST renders the watermarking scheme resistant to content cutting and pasting counterfeiting attacks. Simulation results arc presented to demonstrate the effectiveness of the proposed method.