Detecting zebra crossings utilizing AdaBoost

This paper introduces a visual zebra crossing detector based on the Viola-Jones approach. The basic properties of this cascaded classifier and the use of integral images are explained. Additional pre- and postprocessing for this task are introduced and evaluated.

• Type: Conference
• Year: 2008
• Where: ESANN
• Authors: Ludwig Lausser, Friedhelm Schwenker, Günther Palm
• Keywords: Basic Properties, ESANN 2008, Integral Images, Neural Networks, Zebra Crossing Detector