CITI--Robust Multi-View Car Detection using Unsupervised Sub-Categorization
- LecturerDr. Cheng-Hao Kuo (Computer Vision Lab, University of Southern California.)
Host: Dr. Yu-Chiang Wang - Time2010-01-12 (Tue.) 10:30 – 11:30
- LocationAuditorium 101 at new IIS Building
Abstract
Abstract:
We present a novel approach for multi-view car detection using
unsupervised sub-categorization instead of manual labeling. Cars have
large variability of models and the view-point makes the appearance
change dramatically. For object classes with a large intra-class
variation like cars, a divide-and-conquer strategy may be applied.
Instead of using manually predefined intra-class subcategorization,
we examine several non-linear dimension reduction methods and group
samples in the low-dimension embedding in an unsupervised way. The
clustered samples have strong view-point similarities internally. A
boosting-based cascade tree classifier is trained based on these
subcategorizations.
To demonstrate the capability of our multiview car detector, we create
a more challenging test set with annotations. Compared to the UIUC
side-view car data set, our test set contains a large range of car
models, view points, and complex backgrounds. We compare our approach
with previous methods and the result shows that ours outperforms the
state-of-the-art methods.
Bio:
Cheng-Hao Kuo was born in Taipei, Taiwan. He received the BS degree
in electrical engineering from National Taiwan University in 2002, and
the MS degree in electrical and computer engineering from Carnegie
Mellon University in 2005. He is currently a PhD student in the computer
vision lab at University of Southern California, under the supervision
of Professor Ram Nevatia. His research interests include computer
vision and machine learning, especially for object detection and
pedestrian tracking.