A robust feature detection algorithm for the binary encoded single-shot structured light system
Hualie Jiang, Zhan Ping Song · 2016
This work introduces a novel feature detection algorithm for the decoding of a binary encoded structured light pattern. To make the structure light pattern insensitive to surface color and texture, some geometrical shapes are used as the pattern elements. Grid-point between each two adjacent rhombic pattern element is defined as the feature points. Affected by the inner structure of pattern element, classical two-fold symmetry-based grid-point detector cannot be applied. A more efficient template-based approach is firstly investigated. By designing the filter with X-shape and a weighting function is associated with different filter elements. And thus, the filter is less affected by the pattern elements. Moreover, to make the detector applicable for surface regions with huge distortions, a multi-template strategy is also proposed. Experiments are conducted with a variety of objects with different color and shapes, and compared with a classical feature detector. And the results show that, the proposed grid-point detector is much more robust and can localize the pattern feature points accurately without spending more computing time.