.png){kind=icon}
Return
Viewpoint-aware object detection and continuous pose estimation
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2012.09.006.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We describe an approach to category-level detection and viewpoint estimation for rigid 3D objects from single 2D images. In contrast to many existing methods, we directly integrate 3D reasoning with an appearance-based voting architecture. Our method relies on a nonparametric representation of a joint distribution of shape and appearance of the object class. Our voting method employs a novel parameterization of joint detection and viewpoint hypothesis space, allowing efficient accumulation of evidence. We combine this with a re-scoring and refinement mechanism, using an ensemble of view-specific support vector machines. We evaluate the performance of our approach in detection and pose estimation of cars on a number of benchmark datasets. Finally we introduce the Weizmann Cars ViewPoint (WCVP) dataset, a benchmark for evaluating continuous pose estimation. (C) 2012 Elsevier B.V. All rights reserved.
Keywords:
Viewpoint-aware
Object detection
Pose estimation
3D model
Viewpoint estimation
Structure from motion
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.2
Papers:
4.1K
Citations:
6.7K
Organization
Cited Papers
ShareSaveShareSaveShareSaveShareSaveCompromised Mitochondrial Fatty Acid Synthesis in Transgenic Mice Results in Defective Protein Lipoylation and Energy Disequilibrium.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAIShareSave no more
no more