An image mosaicing module for wide-area surveillance

This paper presents a fully automatic image mosaicing method for needs of wide-area video surveillance. A pure feature-based approach was adopted for finding the registration between the images. This approach provides us with several advantages. Our method is robust against illumination variations, moving objects, image rotation, image scaling, imaging noise, and is relatively fast to calculate. We have tested the performance of the proposed method against several video sequences captured from real-world scenes. The results clearly justify our approach.