Detecting curved objects against cluttered backgrounds
Jan Prokaj
Abstract
Abstract: This work addresses the problem of curved object detection against cluttered backgrounds. New
low-level and mid-level features are presented to function in these environments. The low-level features
are fast to compute, thanks to an integral image approach. The mid-level features are built from low-level
features, and are optimized for curved object detection. The usefulness of these features is tested by
designing an object detection algorithm using these features. Object detection is accomplished by
transforming the mid-level features into weak classifiers, which then produce a strong classifier using
AdaBoost. The object detection algorithm is tested on the problem of detecting heads with shoulders. The
resulting performance is encouraging.