Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Annotation driven MAP search space estimation for sliding-window based person detection

: Becker, Stefan; Hübner, Wolfgang; Arens, Michael

Volltext urn:nbn:de:0011-n-3476524 (1.3 MByte PDF)
MD5 Fingerprint: d3f57e0b83db1ce3066ae33e7bd0cf8e
Erstellt am: 14.7.2015

International Association for Pattern Recognition -IAPR-; Institute of Electrical and Electronics Engineers -IEEE-:
Fourteenth IAPR International Conference on Machine Vision Applications, MVA 2015. Proceedings : May 18-22, 2015, Tokyo, Japan
Piscataway, NJ: IEEE, 2015
ISBN: 978-4-901122-15-3
International Conference on Machine Vision Applications (MVA) <14, 2015, Tokyo>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

A common method for performing multi-scale person detection is a sliding window classification. For every window location and scale a binary classification is done. Many state-of-the-art person detectors follow this sliding window paradigm. Not only this exhaustive search space strategy is computationally expensive, it usually produces large number of false positives. In order to estimate an optimal reduced search space, we derive a maximum a posteriori probability (MAP) solution given only the person annotations of a dataset. The proposed MAP solution considers the naturally height distribution of persons, deviations from a flat world assumption, and annotation uncertainty. The effectiveness compared to the traditional uniform sliding window selection strategy is shown on different realistic monocular pedestrian detection datasets. Moreover the MAP search space estimation provides design parameters for modeling the tradeoff between detection performance and runtime constraints.