INTUITIONISTIC FUZZY RANDOM FOREST-BASED METHOD AND DEVICE FOR TARGET TRACKING

摘要

Disclosed are an intuitionistic fuzzy random forest-based method and device for target tracking, comprising: performing motion detection with respect to a current video frame, making possible moving objects detected as observation results; associating the observation results with prediction results for targets, the targets comprising a reliable target and a temporary target; performing trajectory management with respect to an unassociated observation result and prediction result, comprising online tracking of the prediction result of an unassociated reliable target to acquire a candidate result, utilizing an intuitionistic fuzzy random forest for the unassociated reliable target for matching the candidate resu utilizing the association result and the matching result to acquire trajectories of the targets, utilizing the trajectories of the targets of the current frame for prediction, and updating the intuitionistic fuzzy random forest for a successfully associated or successfully matched reliable target. Also disclosed is an intuitionistic fuzzy random forest-based device for target tracking.