The invention proposes an improved TLD tracking method based on improved Online Boosting and a Kalman filter, belonging to the technical fields of machine vision, artificial intelligence, human-computer interaction, and target tracking. The method includes the following steps: (1) initialization: use the initial sample set formed by selecting the target and affine transformation to initialize the improved Online Boosting classifier and P-N learner; (2) image tracking: select feature points, use twice The L-K optical flow method is used to track it, and the tracking error is compared with the threshold twice to obtain the tracking result; (3) Image detection: after Kalman filter, variance classifier, Online Boosting classifier, KNN classifier (4) Integrated tracking and detection results: evaluate the confidence of the tracker and detector results, and obtain the final module result; (5) Online learning: P-N learner is used to correct the tracker, Detector results, and enrich the sample set. The invention can effectively overcome the occlusion problem, increase the speed of the original method, and simultaneously effectively improve the accuracy and robustness of the detector.