Search

This paper studies off-line control and on-line control based on Adaptive Dynamical Programming and proposes an optimal adaptive algorithm with the combination of off-line and on-line training; The method using off-line value iteration algorithm gets off-line opitical controller, then using on-line policy iteration algorithm of Q learning improves the off-line opitical controller. Simulation results show that the proposed approach is effective. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel approach for object detection via foreground feature selection and part-based shape model. It automatically learns a shape model from cluttered training images without need to explicitly given bounding box on objects. Our approach commences by extracting a set of feature descriptors, and iteratively selects the foreground features using Earth Movers Distances based matching. This leads to a part-based shape model that can be used for object detection. Experimental results show that the proposed method has comparable performance with the state-of-the-art shape-based detection methods but with less requirements on the data at the training stage. [ABSTRACT FROM PUBLISHER]