Complex city background abnormal target self-learning detection method and device

Through the combination of multimodal vision sensors and uncertainty models, the accuracy problem of target identification in complex urban contexts is solved, and reliable monitoring and accurate identification of abnormal targets is achieved.

CN119693785AActive Publication Date: 2025-03-25BEIJING INST OF TECH
8 Cites 0 Cited by

Patent Information

Application Number
CN202411588861.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2025-03-25
Estimated Expiration
2044-11-08

AI Technical Summary

Technical Problem

In the context of complex cities, existing methods are difficult to ensure accurate identification of targets, especially when multiple factors such as atmospheric refraction and ground reflection are coupled, resulting in high false alarm rate or false alarm rate for spectral variant aliasing and abnormal target recognition.

Method used

A self-learning detection method for complex urban background anomaly targets is proposed. Data is collected through multimodal vision sensors, preliminary anomaly detection is carried out, and uncertainty model is constructed using prior knowledge and data tuning, relative entropy is calculated to adjust data weights, and multi-factor coupled reasoning is performed to determine anomaly targets.

Benefits of technology

It has achieved reliable monitoring of abnormal goals in complex urban background environments in an unsupervised environment, improved the precise identification of goals, and reduced the uncertainty of decision-making.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a complex city background abnormal target self-learning detection method, and relates to the technical field of information, and the method comprises the steps: collecting city scene data through a multi-modal visual sensor, and carrying out the preliminary anomaly detection of the collected multi-modal data, and obtaining a preliminary anomaly detection result; adding uncertainty knowledge to the preliminary anomaly detection result by using priori knowledge and data tuning, and constructing an uncertainty model; on the basis of an uncertainty model, calculating and comparing relative entropies among different modal data, determining a resampling magnitude according to the difference of the relative entropies, and adjusting weights of the different modal data; and based on the adjusted weight, performing multi-factor coupling reasoning on the acquired multi-modal data to obtain an anomaly detection result. By adopting the scheme, the abnormal target in a complex urban background environment can be reliably monitored in an unsupervised environment.
Need to check novelty before this filing date? Find Prior Art