Acceleration of Object Detection Using Classifiers

Detection of objects in computer vision is a complex task. One of most popular and well explored  approaches is the use of statistical classifiers and scanning windows. In this approach, classifiers learned by AdaBoost algorithm (or some modification) are often used as they achieve low error rates, high detection rates and they are suitable for detection in real-time applications. Object detection run-time which uses such classifiers can be implemented by various methods and properties of underlying architecture can be used for speed-up of the detection.  For the purpose of acceleration, graphics hardware, multi-core architectures, SIMD or other means can be used. The detection is often implemented on programmable hardware.  The contribution of this thesis is to introduce an optimization technique which enhances object detection performance with respect to an user defined cost function. The optimization balances computations of previously learned classifiers between two or more run-time implementations in order to minimize the cost function.  The optimization method is verified on a basic example -- division of a classifier to a pre-processing unit implemented in FPGA, and a post-processing unit in standard PC.