Apparatus and method for recognizing subject motion using a camera

Abstract

A method for recognizing a subject motion using a camera is provided, in which each of the previous and current image frames received from the camera is split into multiple image blocks, motion blocks are detected among the image blocks based on a difference between previous and current pixel values for each of the image frames, a motion center is detected based on positions of the motion blocks for each image frame, and the subject motion appearing in the previous and current image frames is recognized based on the motion centers of the previous and current image frames.

Description

PRIORITY[0001]This application claims priority under 35 U.S.C. §119(a) to a Korean Patent Application filed in the Korean Intellectual Property Office on Jul. 17, 2009 and assigned Serial. No. 10-2009-0065434, the entire disclosure of which is hereby incorporated by reference.BACKGROUND OF THE INVENTION[0002]1. Field of the Invention[0003]The present invention relates generally to an apparatus and method for detecting a subject's motions in captured images, and more particularly, to an apparatus and method for recognizing or detecting a user's hand motions in image frames received from a mobile camera, i.e., a camera embedded in a mobile terminal.[0004]2. Description of the Related Art[0005]Mobile terminals (also known as mobile communication terminals or portable terminals), which were originally developed for voice calls, have evolved into devices that provide many different types of services to users. For example, more recently developed mobile terminals also provide data service...

AI Technical Summary

Benefits of technology

[0009]The present invention is designed to address at least the aforementioned problems and / or disadvantages and to provide at least the advantages described below. Accordingly, aspects of the present invention provide a hand motion-based input method and a hand motion recognition apparatus and method, which are robust to various disturbing factors and high in speed, and can be applied to a variety of mobile applications. This may be accomplished by considering only motion characteristics of a target close in color to the skin in a way, which is robust to diverse disturbing factors like the lighting and scale without separately detecting hand shapes.

Problems solved by technology

Consequently, disturbing factors such as a change in lighting or scale, rotational displacement, background color, or covering, may significantly degrade recognition performance.

Additionally, a task such as hand shape recognition demands significant computing resources that are necessarily limited in the mobile environment.

Images