Active learning for visual object detection

One of the most labor intensive aspects of developing accurate visual object detectors using machine learning is to gather sufficient amount of labeled examples. We develop a selective sampling method, based on boosting, which dramatically reduces the amount of human labor required for this task. We apply this method to the problem of detecting pedestrians from a video camera mounted on a moving car. We demonstrate how combining boosting and active learning achieves high levels of detection accuracy in complex and variable backgrounds.