Chapter 8 Object Detection

Over the past twenty years, data-driven methods have become a dominant paradigm for computer vision, with numerous practical successes. In difficult computer vision tasks, such as the detection of object categories (for example, the detection of faces of various gender, age, race, and pose, under various illumination and background conditions), researchers generally learn a classifier that can distinguish an image patch that contains the object of interest from all other image patches. Ensemble learning methods have been very successful in learning classifiers for object detection. The task of object detection, however, poses new challenges for ensemble learning, which we will discuss in detail in Sect. 8.2. We summarize these challenges into three aspects: scale, speed, and asymmetry. Various research contributions have been made to overcome these difficulties. In this chapter, we mainly focus on those methods that use the cascade classifier structure together with ensemble learning methods (e.g., AdaBoost). The cascade classifier structure for object detection was first proposed by Viola and Jones [41], who presented the first face detection system that could both run in real-time and achieve high detection accuracy. We will describe this work in Sect. 8.3, with ensemble learning methods being one of the key components in this system.