Share Email Print
cover

Proceedings Paper

Automated generation of high-quality training data for appearance-based object models
Author(s): Stefan Becker; Arno Voelker; Hilke Kieritz; Wolfgang Hübner; Michael Arens
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Methods for automated person detection and person tracking are essential core components in modern security and surveillance systems. Most state-of-the-art person detectors follow a statistical approach, where prototypical appearances of persons are learned from training samples with known class labels. Selecting appropriate learning samples has a significant impact on the quality of the generated person detectors. For example, training a classifier on a rigid body model using training samples with strong pose variations is in general not effective, irrespective of the classifiers capabilities. Generation of high-quality training data is, apart from performance issues, a very time consuming process, comprising a significant amount of manual work. Furthermore, due to inevitable limitations of freely available training data, corresponding classifiers are not always transferable to a given sensor and are only applicable in a well-defined narrow variety of scenes and camera setups. Semi-supervised learning methods are a commonly used alternative to supervised training, in general requiring only few labeled samples. However, as a drawback semi-supervised methods always include a generative component, which is known to be difficult to learn. Therefore, automated processes for generating training data sets for supervised methods are needed. Such approaches could either help to better adjust classifiers to respective hardware, or serve as a complement to existing data sets. Towards this end, this paper provides some insights into the quality requirements of automatically generated training data for supervised learning methods. Assuming a static camera, labels are generated based on motion detection by background subtraction with respect to weak constraints on the enclosing bounding box of the motion blobs. Since this labeling method consists of standard components, we illustrate the effectiveness by adapting a person detector to cameras of a sensor network. While varying the training data and keeping the detection framework identical, we derive statements about the sample quality.

Paper Details

Date Published: 1 November 2013
PDF: 12 pages
Proc. SPIE 8899, Emerging Technologies in Security and Defence; and Quantum Security II; and Unmanned Sensor Systems X, 889916 (1 November 2013); doi: 10.1117/12.2028714
Show Author Affiliations
Stefan Becker, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation (Germany)
Arno Voelker, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation (Germany)
Hilke Kieritz, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation (Germany)
Wolfgang Hübner, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation (Germany)
Michael Arens, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation (Germany)


Published in SPIE Proceedings Vol. 8899:
Emerging Technologies in Security and Defence; and Quantum Security II; and Unmanned Sensor Systems X
Edward M. Carapezza; Keith L. Lewis; Mark T. Gruneisen; Miloslav Dusek; Richard C. Hollins; Thomas J. Merlet; John G. Rarity, Editor(s)

© SPIE. Terms of Use
Back to Top