RelCom: Relational combinatorics features for rapid object detection

We present a simple yet elegant feature, RelCom, and a boosted selection method to achieve a very low complexity object detector. We generate combinations of low-level feature coefficients and apply relational operators such as margin based similarity rule over each possible pair of these combinations to construct a proposition space. From this space we 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. Our results on benchmark datasets prove that the boosted RelCom features can match the performance of HOG features on SVM-RBF while providing 5× speed up and significantly outperform SVM-linear while reducing the false alarm rate 5×~20×. In case of intensity features the improvement in false alarm rate over SVM-RBF is 14× with a 128× speed up. We also demonstrate that RelCom based on pixel features is very suitable and efficient for small object detection tasks.