Abstract: A method for determining posture-related information of a subject using the subject's image is provided. The method comprises: determining, from a first image, first positions of a first pair of joints and a first body segment length of a first body segment associated with the first pair of joints; determining, from a second image, second positions of a second pair of joints and a second body segment length of a second body segment associated with the second pair of joints; determining, based on an algorithm that reduces a difference between the first and second body segment lengths, whether the first and second pairs of joints correspond to a pair of joints; If the first and second pairs of joints are determined to correspond to a pair of joints, determining, based on the second positions, information of a posture of the subject; and providing an indication regarding the information.

Abstract: A method for determining posture-related information of a subject using the subject's image is provided. The method comprises: determining, from a first image, first positions of a first pair of joints and a first body segment length of a first body segment associated with the first pair of joints; determining, from a second image, second positions of a second pair of joints and a second body segment length of a second body segment associated with the second pair of joints; determining, based on an algorithm that reduces a difference between the first and second body segment lengths, whether the first and second pairs of joints correspond to a pair of joints; If the first and second pairs of joints are determined to correspond to a pair of joints, determining, based on the second positions, information of a posture of the subject; and providing an indication regarding the information.

Abstract: A method for monitoring postural and movement balance for fall prevent is provided. The method includes the following steps. Multiple sensing signals of a human body are obtained. A center of mass (COM) signal and a center of pressure (COP) signal are modeling according to the sensing signals. A correlation coefficient is calculated according to a mediolateral velocity of the COM signal and the COP signal. A threshold is obtained according to at least one regression model stored in a database. Whether the correlation coefficient is smaller than the threshold is determined. An alert is produced when the correlation coefficient is smaller than the threshold.