A method is presented for extracting pedestrian information from an image sequence taken by a monocular camera. The method makes use of hybrid sensing of depth and gray information and it is shown to work well in an indoor environment. A split-and-merge strategy is proposed to process depth data for object and human detection. Furthermore, human tracking and event detection are also presented to recognize simple behavior such as hand-shaking. This method does not use background subtraction, and therefore it is applicable for scenes taken from mobile platforms. Experimental results are presented to validate our approach.