Viewpoint-aware object detection and continuous pose estimation
Image and Vision Computing
3D2PM - 3d deformable part models
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
View-Invariant object detection by matching 3d contours
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Hi-index | 0.00 |
This paper addresses view-invariant object detection and pose estimation from a single image. While recent work focuses on object-centered representations of point-based object features, we revisit the viewer-centered framework, and use image contours as basic features. Given training examples of arbitrary views of an object, we learn a sparse object model in terms of a few view-dependent shape templates. The shape templates are jointly used for detecting object occurrences and estimating their 3D poses in a new image. Instrumental to this is our new mid-level feature, called bag of boundaries (BOB), aimed at lifting from individual edges toward their more informative summaries for identifying object boundaries amidst the background clutter. In inference, BOBs are placed on deformable grids both in the image and the shape templates, and then matched. This is formulated as a convex optimization problem that accommodates invariance to non-rigid, locally affine shape deformations. Evaluation on benchmark datasets demonstrates our competitive results relative to the state of the art.