Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.