DocumentCode :
2399960
Title :
Viewpoint-independent object class detection using 3D Feature Maps
Author :
Liebelt, Joerg ; Schmid, Cordelia ; Schertler, Klaus
Author_Institution :
IW-SI, EADS Innovation Works, Munich
fYear :
2008
fDate :
23-28 June 2008
Firstpage :
1
Lastpage :
8
Abstract :
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a few discrete views. We propose instead to build 3D representations of object classes which allow to handle viewpoint changes and intra-class variability. Our approach extracts a set of pose and class discriminant features from synthetic 3D object models using a filtering procedure, evaluates their suitability for matching to real image data and represents them by their appearance and 3D position. We term these representations 3D Feature Maps. For recognizing an object class in an image we match the synthetic descriptors to the real ones in a 3D voting scheme. Geometric coherence is reinforced by means of a robust pose estimation which yields a 3D bounding box in addition to the 2D localization. The precision of the 3D pose estimation is evaluated on a set of images of a calibrated scene. The 2D localization is evaluated on the PASCAL 2006 dataset for motorbikes and cars, showing that its performance can compete with state-of-the-art 2D object detectors.
Keywords :
feature extraction; filtering theory; image classification; image representation; object detection; object recognition; pose estimation; 3D bounding box; 3D feature map; 3D image position representation; 3D object class representation; 3D voting scheme; class discriminant feature extraction; discrete view classifier; filtering procedure; object class recognition; pose estimation; real image data matching; synthetic 3D model; synthetic image descriptor; viewpoint-independent object class detection; Computer vision; Data mining; Filtering; Image recognition; Layout; Matched filters; Object detection; Robustness; Voting; Yield estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Conference_Location :
Anchorage, AK
ISSN :
1063-6919
Print_ISBN :
978-1-4244-2242-5
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2008.4587614
Filename :
4587614
Link To Document :
بازگشت