Target track fuzzy data fusion method based on video monitoring

Abstract

The invention relates to a target track fuzzy data fusion method based on video monitoring and is applied to actual police work. Police officers cannot acquire GPS position data through active uploading of abnormal objects, and only acquires the positioning information through a monitoring sensor network. Most of behaviors generated by suspected objects of various cases in different stages such ascollusion, implementation, hiding and the like have subjective invisibility, so that the data acquired by the monitoring network is fuzzy data, and through the target track fuzzy data fusion method based on video monitoring, a fuzzy track can be recovered, and help is brought to police work and target tracking.

Description

technical field [0001] The invention relates to a fuzzy data fusion method of a target track based on video monitoring, and belongs to the technical field of target track tracking. Background technique [0002] In the field of trajectory fusion, the commonly used methods are mainly fusion based on prediction models and fusion based on filtering algorithms. Doug Cox et al. proposed a new Markov algorithm for low-frequency and low-fidelity data of sensor networks. chain reorganization schemes, and use the new schemes to generate probabilistic trajectories based on the original data. P Zhang et al proposed a fusion algorithm combining stable position and Kalman filtering. At the same time, AO B Wang et al proposed a distributed multi-target tracking algorithm based on the multi-Bernoulli (MB) filter of generalized covariance intersection (G-CI). However, in the actual recognition process, due to a variety of complex scene conditions, as well as the subjective concealment and ...

AI Technical Summary

Problems solved by technology

For low-precision position information, redundancy can restore the true distribution to a certain extent, but the error data will not provide any useful information, which will only further increase the error

Furthermore, the trajectories to be tracked are often anomalous

Whether based on filters or predictive models, it is easy to lose true anomaly information in the fusion

Images