Non-rectangular Part Discovery for Object Detection

The deformable part-based model (DPM) is commonly used for object detection and many efforts have been made to improve the model. However, much less work has been done to discover parts for DPM. Most DPM-based methods adopt the greedy search approach proposed in [2] to initialize a predefined number of parts of rectangular shapes, which may not be optimal for some object categories. Moreover, object structures are not well exploited by the approach. In [4], a three-layer spatial pyramid structure is used to simplify the initialization of parts. An AndOr tree model [3] is proposed to select discriminative part configurations by a dynamic programming algorithm. Although the method can determine part sizes automatically, part shapes are still restricted to rectangles. To address the limitations of these methods, we propose a novel datadriven approach to discover non-rectangular parts by exploiting object structures. Figure 1 shows rectangular and non-rectangular parts obtained by the greedy search approach and our approach, respectively. Generally, the parts obtained by our approach can better cover object regions.