Target Tracking Method, Target Tracking System and Electronic Device

A target tracking system, comprising:

• a camera, configured to sequentially acquire N frames of images, wherein N is an integer greater than or equal to 2;
• a target detector, connected with the camera and configured to perform target detection on an N-th frame of image through a target detection algorithm to generate a target area;
• an optical flow prediction module, connected to the camera and the target detector and configured to perform optical flow calculation on a target area in an (N−1)-th frame of image to generate an optical flow predicted target area in the N-th frame of image;
• a Kalman prediction module, connected with the camera and the target detector, and configured to perform Kalman Filter prediction on the target area in the (N−1)-th frame of image to generate a Kalman Filter predicted target area in the N-th frame of image;
• and
• a first matching module, connected with the target detector, the optical flow prediction module and the Kalman prediction module, and is configured to perform a first matching between the target area in the N-th frame of image from the target detector and the optical flow predicted target area in the N-th frame of image from the optical flow prediction module, wherein:
• in response to the target area in the N-th frame of image being matched with the optical flow predicted target area in the N-th frame of image, the first matching module is further configured to output the target area in the N-th frame of image which passes the first matching to update an Kalman Filter model and perform optical flow point resampling;
• in response to the target area in the N-th frame of image being not matched with the optical flow predicted target area in the N-th frame of image, the first matching module is further configured to output the target area in the N-th frame of image which does not pass the first matching to a second matching module, wherein the second matching module is configured to perform a second matching between the target area in the N-th frame of image which does not pass the first matching and the Kalman Filter predicted target area in the N-th frame of image from the Kalman prediction module;
• in response to the target area in the N-th frame of image which does not pass the first matching being matched with the Kalman Filter predicted target area in the N-th frame of image, the second matching module is further configured to output the target area in the N-th frame of image which passes the second matching, to update the Kalman Filter model and perform the optical flow point resampling;
• in response to the target area in the N-th frame of image which does not pass the first matching being not matched with the Kalman Filter predicted target area in the N-th frame of image, the second matching module is further configured to output the target area in the N-th frame of image which does not passes the first matching and the second matching, to create and initialize a Kalman motion model and perform an optical flow point sampling;
• the second matching module is further configured to output the Kalman Filter predicted target area in the N-th frame of image which does not pass the second matching to a determination module, and the determination module is configured to make a prediction condition determination;
• in response to the determination being that the prediction condition is not met, the determination module is further configured to delete the Kalman motion model;
• in response to the determination being that the prediction condition is met, the determination module is further configured to update the Kalman Filter model and perform the optical flow point resampling by using the optical flow predicted target area in the N-th frame of image which is from the optical flow prediction module and corresponds to the Kalman Filter predicted target area in the N-th frame of image which does not pass the second matching;
• and
• the Kalman Filter predicted target area in the N-th frame of image which does not pass the second matching and the corresponding optical flow predicted target area in the N-th frame of image correspond to a same target.