Abstract.
The ob jective of this work is the detection of ob ject classes, such as airplanes or horses. Instead of using a model based on salient im- age fragments, we show that ob ject class detection is also possible using only the ob ject’s boundary. To this end, we develop a novel learning tech- nique to extract class-discriminative boundary fragments. In addition to their shape, these “codebook” entries also determine the ob ject’s centroid (in the manner of Leibe et al. [19]). Boosting is used to select discrim- inative combinations of boundary fragments (weak detectors) to form a strong “Boundary-Fragment-Model” (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation. We demonstrate the following results: (i) the BFM detector is able to represent and detect ob ject classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several ob ject classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).