Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für Informatik     Collection: Computer Graphics Group     Display Documents



ID: 520481.0, MPI für Informatik / Computer Graphics Group
Class-Specific Hough Forests for Object Detection
Authors:Gall, Jürgen; Lempitsky, Victor
Language:English
Publisher:IEEE Computer Society
Place of Publication:Los Alamitos
Date of Publication (YYYY-MM-DD):2009
Title of Proceedings:IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09)
Start Page:1
End Page:8
Place of Conference/Meeting:Miami, USA
(Start) Date of Conference/Meeting
 (YYYY-MM-DD):
2009-06-20
End Date of Conference/Meeting 
 (YYYY-MM-DD):
2009-06-25
Audience:Experts Only
Intended Educational Use:No
Abstract / Description:We present a method for the detection of instances of an
object class, such as cars or pedestrians, in natural images.
Similarly to some previous works, this is accomplished via
generalized Hough transform, where the detections of individual
object parts cast probabilistic votes for possible
locations of the centroid of the whole object; the detection
hypotheses then correspond to the maxima of the Hough
image that accumulates the votes from all parts. However,
whereas the previous methods detect object parts using generative
codebooks of part appearances, we take a more discriminative
approach to object part detection. Towards this
end, we train a class-specific Hough forest, which is a random
forest that directly maps the image patch appearance
to the probabilistic vote about the possible location of the
object centroid. We demonstrate that Hough forests improve
the results of the Hough-transform object detection significantly
and achieve state-of-the-art performance for several
classes and datasets.
Last Change of the Resource (YYYY-MM-DD):2009-04-06
External Publication Status:published
Document Type:Conference-Paper
Communicated by:Hans-Peter Seidel
Affiliations:MPI für Informatik/Computer Graphics Group
Identifiers:LOCALID:C125675300671F7B-E043433D5A1EEF5DC125758300607EF2-...
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.