Ask the OWL: Object detection constrained by a probabilistic ontological model

The problem of object detection in computer vision is a difficult and interesting problem which is far from being solved due in no small part to the challenges of perception. Nevertheless, by introducing top-down priors such as semantics, the problem of segmenting and detecting objects becomes tractable. This paper proposes such an approach by relying on the ontological relationships that make up parts of objects in order to enhance their detection. The proposed method processes the point cloud of a scene and clusters it into pools of potential objects. Hypotheses on the object identity are generated using geometric and customized ontological definitions to generate probabilistic models, which constitute the building blocks for the decision making process, whereas an object labeling scheme derived by minimizing an energy function is presented. Finally, objects are replaced by matching them to generic CAD models. To evaluate the proposed method, we run our experiments on three well-known datasets and compare with results in the literature, showing superiority of the proposed method over prior art.