|
|
People-Tracking-by-Detection and People-Detection-by-Tracking
M. Andriluka, S. Roth, B. Schiele
In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'08), Anchorage, USA, June 2008
|
|
Paper | Slides | Videos | Datasets | Contact Us
|
Abstract: Both detection and tracking people are challenging
problems, especially in complex real world scenes that commonly
involve multiple people, complicated occlusions, and
cluttered or even moving backgrounds. People detectors
have been shown to be able to locate pedestrians even in
complex street scenes, but false positives have remained
frequent. The identification of particular individuals has
remained challenging as well. Tracking methods are able
to find a particular individual in image sequences, but
are severely challenged by real-world scenarios such as
crowded street scenes. In this paper, we combine the advantages
of both detection and tracking in a single framework.
The approximate articulation of each person is detected
in every frame based on local features that model
the appearance of individual body parts. Prior knowledge
on possible articulations and temporal coherency within a
walking cycle are modeled using a hierarchical Gaussian
process latent variable model (hGPLVM). We show how the
combination of these results improves hypotheses for position
and articulation of each person in several subsequent
frames. We present experimental results that demonstrate
how this allows to detect and track multiple people in cluttered
scenes with reoccurring occlusions.
|
The videos show detection and tracking of people on the "TUD Campus" sequence (left) and "TUD Crossing" sequence (right). Tracks of each person are visualized using unique combination of color and line type. The videos are created with the msmpeg4v2 codec (from ffmpeg).
|
These are the two datasets used to train our people detector. For each training image annotations of body-part positions as well as detailed segmentation of people are provided.
Test Data:
Test dataset containing 250 images with 311 fully visible people with significant variation in clothing and articulation. This dataset was used to evaluate the performance of single-frame detector.
Sequences:
Two sequences used to evaluate detection and tracking. Annotations are provided for all pedestrians occluded to less then 50%.
|
|
For further information please contact the authors: Micha Andriluka, Stefan Roth and Bernt Schiele.
|
|
