Reducing Drift in Mosaicing Slit-Lamp Retinal Images

The construction of seamless and accurate mosaics from long slit-lamp retinal video sequences is an important and challenging task in navigated Pan-Retinal Photocoagulation. The main difficulty is accumulated registration drift due to the small number of features away from the optic nerve and the distortion induced by the geometry of the eye and the contact lens. We present a new approach to reduce the drift. Our main idea is to create long-term high precision point correspondences by associating a simple global model with local correction and perform key-frame based Bundle Adjustment. We evaluate the method's performance compared to state-of-the-art. The results obtained with our method show significantly lower accumulated error.