@misc {pub2915,
	title = {A Two-stage Classifier Architecture for Detecting Objects under Real-world Occlusion Patterns },
	author = {Marvin Struwe AND Stephan Hasler AND Ute Bauer-Wersing},
	year = {2015},
	month = {March},
	abstract = {Despite extensive efforts, state-of-the-art detection approaches show a strong degradation of performance with increasing level of occlusion. In this paper we investigate a strategy to improve the detection of occluded objects based on the analytic feature framework from \cite{struwe13} and compare the results in a car detection task. Motivated by an analysis of annotated traffic scenes we focus on a general concept to handle vertical occlusion patterns. For this we describe a two stage classifier architecture that detects vertical car parts in the first stage and combines the local responses in the second. As an extension we provide depth information for the individual car parts helping the classifier in the second stage to reason about typical occlusion patterns. The results reveal that this general strategy can provide a substantial performance improvement for appearance-based detection approaches.},
	publisher = {Heidelberger Bildverarbeitungsforum},
	booktitle = {Heidelberger Bildverarbeitungs Forum}
}