Author(s): Gall, Jürgen Lempitsky, Victor dblp dblp Not MPG Author(s): Lempitsky, Victor Editor(s): BibTeX cite key*: Gall2009c

Title*: Class-Specific Hough Forests for Object Detection Booktitle*: IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09)

URL of the conference: http://www.cvpr2009.org/ URL for downloading the paper: Event Address*: Miami, USA Language: English Event Date* (no longer used): Organization: Event Start Date: 20 June 2009 Event End Date: 25 June 2009

Name*: IEEE Computer Society URL: Address*: Los Alamitos Type:

Series: Volume: Number: Month: Pages*: 1-8 Year*: 2009 VG Wort Pages: 27 ISBN/ISSN: Sequence Number: DOI:

(LaTeX) Abstract: 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. Download Access Level: Public

MPG Unit: Max-Planck-Institut für Informatik MPG Subunit: Computer Graphics Group Audience: experts only Appearance: MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort

BibTeX Entry:
@INPROCEEDINGS{Gall2009c,
AUTHOR = {Gall, J{\"u}rgen and Lempitsky, Victor},
TITLE = {Class-Specific Hough Forests for Object Detection},
BOOKTITLE = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09)},
PUBLISHER = {IEEE Computer Society},
YEAR = {2009},
PAGES = {1--8},
ADDRESS = {Miami, USA},
}