METHOD AND SYSTEM FOR DETECTION OF PEDESTRIAN CROSSING USING A METHOD OF LIGHT WEIGHTED RANDOM FOREST CLASSIFICATION BY A SOFT TARGET LEARNING METHOD

摘要

The present invention relates to a method for detecting a pedestrian using a random forest classification method light-weighted by a soft target learning technique, which comprises the steps of: detecting a pedestrian candidate region; estimating a region of interest (ROI); extracting a Harr-like feature and an oriented center symmetric local binary pattern (OCS-LBP) feature; determining whether a pedestrian is present at a corresponding ROI; and determining a final pedestrian region.