Improved Object Detection and Pose Using Part-Based Models
Jiang, Fangyuan; Enqvist, Olof; Kahl, Fredrik; Åström, Karl (2013). Improved Object Detection and Pose Using Part-Based Models. Kämäräinen, Joni-Kristian; Koskela, Markus (Eds.). Lecture Notes in Computer Science (Image Analysis : 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings), 7944,, 396 - 407. 18th Scandinavian Conference on Image Analysis (SCIA 2013). Espoo, Finland: Springer
Conference Proceeding/Paper
|
Published
|
English
Authors:
Jiang, Fangyuan
;
Enqvist, Olof
;
Kahl, Fredrik
;
Åström, Karl
Editors:
Kämäräinen, Joni-Kristian
;
Koskela, Markus
Department:
Mathematics (Faculty of Engineering)
Centre for Mathematical Sciences
Mathematical Imaging Group
ELLIIT: the Linköping-Lund initiative on IT and mobile communication
eSSENCE: The e-Science Collaboration
Research Group:
Mathematical Imaging Group
Abstract:
Automated object detection is perhaps the most central task of computer vision and arguably the most difficult one. This paper extends previous work on part-based models by using accurate geometric models both in the learning phase and at detection. In the learning phase manual annotations are used to reduce perspective distortion before learning the part-based models. That training is performed on rectified images, leads to models which are more specific, reducing the risk of false positives. At the same time a set of representative object poses are learnt. These are used at detection to remove perspective distortion. The method is evaluated on the bus category of the Pascal dataset with promising results.
ISBN:
978-3-642-38885-9 (print)
Cite this