Feature-based real-time endoscopic mosaicking

In the field of minimally invasive surgery one barrier in clinical practice is the limited field of view provided by endoscopic cameras. We propose an image mosaicking approach to extend the field of view for real-time visualization by stitching several video frames. The approach is based on feature tracking and a robust estimation of the image-to-image transformations. We compare its performance to that of a state-of-the-art approach. Our method shows superior accuracy at frame rates of 6.8 to 8.1 frames per second, which allows for real-time visualization of the extended field of view.