The invention discloses a people recognition method and device based on video images. The people recognition method includes the steps of firstly, extracting N images from target video images, and determining a 
background image and a foreground area in the target video images, wherein the foreground area includes a 
body contour image; secondly, extracting a plurality of 
body contour characteristic points from the 
body contour image; thirdly, setting up a three-dimensional body model based on a 
human skeleton, wherein the three-dimensional body model includes a plurality of three-dimensional 
joint angle parameters; fourthly, conducting rectangular projection on the three-dimensional body model to obtain a body smooth curve; fifthly, matching the body contour characteristic points extracted from the images with the body smooth curve to determine all the three-dimensional 
joint angle parameters; sixthly, conducting 
dimensionality reduction on all the three-dimensional 
joint angle parameters to obtain 
gait data to be recognized; seventhly, matching the 
gait data to be recognized with well-trained 
gait data to complete people recognition. According to the technical scheme, the people recognition method and device have the advantages of improving the capacity for analyzing the body contour characteristic information, reducing the operational amount, being high in robustness, and the like.