Bit-Planes: Dense Subpixel Alignment of Binary Descriptors
This addresses the need for robust and fast dense alignment in vision applications like template tracking, offering an incremental improvement by combining existing binary descriptor robustness with dense alignment speed.
The paper tackled the problem of dense image alignment being sensitive to illumination changes by proposing bit-planes, a dense binary descriptor integrated into a Lucas & Kanade framework, achieving state-of-the-art robustness and faster than real-time performance (400+ fps on laptops, 100+ fps on mobile devices).
Binary descriptors have been instrumental in the recent evolution of computationally efficient sparse image alignment algorithms. Increasingly, however, the vision community is interested in dense image alignment methods, which are more suitable for estimating correspondences from high frame rate cameras as they do not rely on exhaustive search. However, classic dense alignment approaches are sensitive to illumination change. In this paper, we propose an easy to implement and low complexity dense binary descriptor, which we refer to as bit-planes, that can be seamlessly integrated within a multi-channel Lucas & Kanade framework. This novel approach combines the robustness of binary descriptors with the speed and accuracy of dense alignment methods. The approach is demonstrated on a template tracking problem achieving state-of-the-art robustness and faster than real-time performance on consumer laptops (400+ fps on a single core Intel i7) and hand-held mobile devices (100+ fps on an iPad Air 2).