Particle Filter-based Fingertip Tracking with Circular Hough Transform Features

In this work, we present a fingertip tracking framework which allows observation of finger movements in task space. By applying a multi-scale edge extraction technique, an edge map is generated in which low contrast edges are preserved while noise is suppressed. Based on circular image features, determined from the map using Hough transform, the fingertips are accurately tracked by combining a particle filter and a subsequent mean-shift procedure. To increase the robustness of the proposed method, dynamical motion models are trained for the prediction of the finger displacements. Experiments were conducted on various image sequences from which statements on the performance of the framework can be derived.