Multiple-sensor and multiple-object information fusing method

Abstract

Transducers of different distributions detect the existence of targets of environment first and a test information composition system mixes the results detected by transducers to follow up the state and pick-up the character of the target. The state information composition system and the character dinformation composition system composite the traced states and identification results of character vector separately by each transducer to get relative accurate state parameter and identified results and information composition makes the entire systematic composition to provide favorable decision for next step, to increase systematic detecting probability, estimated accuracy and identified probability and more resonable algorithm.

Description

Technical field: [0001] The invention relates to a multi-sensor and multi-target information fusion method, which is an intelligent maneuvering target state accurate estimation and tracking method, and is used for maneuvering targets in systems such as intelligent transportation, robots, avionics, anti-ballistic missile defense, and precision guidance. Accurate positioning and forecasting belong to the field of intelligent information processing technology. Background technique: [0002] With the rapid development of sensor technology and the emergence of a large number of multi-sensor systems, complex engineering systems have a large amount of data about the environment and the detected dynamic process, people are facing a revolution in the field of sensor technology, this revolution will make information The processing and overall transmission capabilities have been greatly improved, and the system performance has experienced a qualitative leap. Intelligent Information Fu...

AI Technical Summary

Problems solved by technology

[0005] In general, although the research on information fusion theory has been put forward and developed greatly since the 1980s, due to the troubles of traditional computing theories and methods, the multi-sensor and multi-target information fusion in non-equilibrium complex environment this difficult problem has not been well solved, mainly due to the non-repeatability of target maneuver characteristics, strong randomness of environment and clutter, high degree of ambiguity of target measurement, limited use of prior information, limited database and knowledge Database construction experience and severe combinatorial explosion phenomenon in computing load, etc., all of these pose severe challenges to modern multi-sensor information fusion systems

[0006] Traditional information processing, statistical detection and artificial intelligence methods have been unable to obtain a complete solution to the IIF problem.

A rule-based expert system approach may be effective if the environment and objectives vary in a known, limited fashion, but current AI systems often exhibit fragile robustness due to their greater sensitivity to certain assumptions. Especially when the environment and goals change in an unknown form, traditional methods have become powerless, and there is an urgent need to develop new theories and tools

Images