Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency
This work addresses the problem of detailed car part segmentation for computer vision applications, presenting an incremental advancement by incorporating segment appearance consistency into graphical models.
The paper tackles semantic part parsing of cars by formulating it as a landmark identification problem and proposing a novel mixture of graphical models that dynamically couples landmarks to a hierarchy of segments, showing good results on PASCAL VOC 2010 and CAR3D datasets with quantified improvements in part localization and segmentation accuracy.
This paper addresses the problem of semantic part parsing (segmentation) of cars, i.e.assigning every pixel within the car to one of the parts (e.g.body, window, lights, license plates and wheels). We formulate this as a landmark identification problem, where a set of landmarks specifies the boundaries of the parts. A novel mixture of graphical models is proposed, which dynamically couples the landmarks to a hierarchy of segments. When modeling pairwise relation between landmarks, this coupling enables our model to exploit the local image contents in addition to spatial deformation, an aspect that most existing graphical models ignore. In particular, our model enforces appearance consistency between segments within the same part. Parsing the car, including finding the optimal coupling between landmarks and segments in the hierarchy, is performed by dynamic programming. We evaluate our method on a subset of PASCAL VOC 2010 car images and on the car subset of 3D Object Category dataset (CAR3D). We show good results and, in particular, quantify the effectiveness of using the segment appearance consistency in terms of accuracy of part localization and segmentation.