FEATURE REPRESENTATION EXTRACTING METHOD FOR RECONIZING HUMAN ACTIVITY AND ACTIVITY RECOGNITION APPRATUS THEREOF

摘要

Disclosed is a method for extracting feature information for human behavior recognition. A method for extracting feature information for human behavior recognition according to an embodiment of the present invention includes receiving sensing data from an acceleration sensor and a direction sensor to generate a first feature set array; Sequentially moving a first window in the first feature set array to generate a first window average array based on an average value in the first window; Generating a second feature set array by combining the first feature set array and the first window average array; Rearranging the second feature set array to sequentially move a second window in the third feature set array to generate a second window average array based on the average value in the second window; Generating a fourth feature set array by combining the third feature set array and the second window average array; And outputting the fourth feature set array to a learning module in units of rows.