Real-time Dense Visual Tracking under Large Lighting Variations

This paper proposes a model for large illumination variations to improve direct 3D tracking techniques since they are highly prone to illumination changes. Within this context dense monocular and multi-camera tracking techniques are presented which each perform in real-time (45Hz). The proposed approach exploits the relative advantages of both model-based and visual odometry techniques for tracking. In the case of direct model-based tracking, photometric models are usually acquired under significantly greater lighting differences than those observed by the current camera view, however, model-based approaches avoid drift. Incremental visual odometry, on the other hand, has relatively less lighting variation but integrates drift. To solve this problem a hybrid approach is proposed to simultaneously minimise drift via a 3D model whilst using locally consistent illumination to correct large photometric differences. Direct 6 dof tracking is performed by an accurate method, which directly minimizes dense image measurements iteratively, using non-linear optimisation. A stereo technique for automatically acquiring the 3D photometric model has also been optimised for the purpose of this paper. Real experiments are shown on complex 3D scenes for a hand-held camera undergoing fast 3D movement and various illumination changes including daylight, artificial-lights, significant shadows, non-Lambertian reflections, occlusions and saturations.