Escape target tracking method and system based on intention reasoning

Abstract

The invention discloses an escape target tracking method and system based on intention reasoning, relates to the technical field of target tracking, and is used for solving the problems of poor escape target tracking effect and low tracking efficiency in the prior art. The method is technically characterized by comprising the following steps: calculating the probability that an escape target arrives at each destination in a destination set by utilizing a Bayesian reasoning method according to prior information; according to the obtained probability, utilizing a Monte Carlo sampling method to predict a future trajectory of the escape target; according to the predicted future trajectory, calculating and obtaining a probability of finding an escape target in a fixed time period; planning a search position at each moment by using a Monte Carlo sampling method according to the probability of finding the escape target; and searching the escape target according to the planned search position at each moment. According to the invention, the target escaping from the tracking view can be quickly searched, so that the continuous tracking of the target is realized. The method and system can be applied to real-time moving target tracking.

Description

Technical field [0001] The present invention relates to the field of target tracking techniques, and more particularly to an escape target tracking method and system based on intentional reasoning. Background technique [0002] Target tracking is generally predicted to predict the future trajectory, and then acts as an actuation of the probability of the future target or minimizes the uncertainty of the target state based on the prediction plan of the target future trajectory. Literature [1] proposed a path planning algorithm for tracking the mobile goals in the urban environment, the target status is modeled by the dynamic grid grid and predicted by the Bayesian filter, and a tree search is proposed. Path planning method to maximize the sum of the probability of detecting the target within a limited range. In order to more effectively utilize the observation state of the motion target in the urban environment, the literature [2] uses the machine learning algorithm to learn the t...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes an escaping target tracking method and system based on intention reasoning to solve the problems of poor tracking effect and low tracking efficiency of escaping targets in the prior art

Images