RelCom: Relational Combinatorics Features for Rapid Object Detection

The authors present a simple yet elegant feature, RelCom, and a boosted selection method to achieve a very low complexity object detector. They generate combinations of low-level feature coefficients and apply relational operations such as margin based similarity rule over each possible pair of these combinations to construct a proposition space. From this space they define combinatorial functions of Boolean operators to form complex hypotheses that model any logical proposition. In case these coefficients are associated with the pixel coordinates, they encapsulate higher order spatial structure within the object window.