Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Resolution-aware constrained local model with mixture of local experts

: Qu, C.; Monari, Eduardo; Schuchert, Tobias


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society; IEEE Computer Society:
10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013 : Krakow, Poland, 27 - 30 August 2013; including Activity Monitoring by Multiple Distributed Sensing (AMMDS) Workshop, Low-Resolution Face Analysis (LRFA) Workshop, Vehicle Retrieval in Surveillance (VRS) Workshop
Piscataway, NJ: IEEE, 2013
ISBN: 978-1-4799-0704-5
ISBN: 978-1-4799-0703-8
International Conference on Advanced Video and Signal Based Surveillance (AVSS) <10, 2013, Krakow>
Fraunhofer IOSB ()

Deformable model fitting to high-resolution facial images has been extensively studied for over two decades. However, due to the ill-posed problem caused by low-resolution images, most existing work cannot be applied directly and degrades quickly as the resolution decreases. To address this issue, this paper extends the Constrained Local Model (CLM) to a multi-resolution model consisting of a 4-level patch pyramid, and deploys various feature descriptors for the local patch experts as well. We evaluate the proposed work on the BioID, the MUCT and the Multi-PIE datasets. Superior results are achieved on almost all resolution levels, demonstrating the effectiveness and necessity of our resolution-aware approach for the low-resolution fitting. Improved performance of patch models employing several feature combinations over the single intensity feature under different conditions is also presented.