Cross-Articulation Learning for Robust Detection of Pedestrians

Recognizing categories of articulated objects in real-world scenarios is a challenging problem for today's vision algorithms. Due to the large appearance changes and intra-class variability of these objects, it is hard to define a model, which is both general and discriminative enough to capture the properties of the category. In this work, we propose an approach, which aims for a suitable trade-off for this problem. On the one hand, the approach is made more discriminant by explicitly distinguishing typical object shapes. On the other hand, the method generalizes well and requires relatively few training samples by cross-articulation learning. The effectiveness of the approach is shown and compared to previous approaches on two datasets containing pedestrians with different articulations.