Multi-sensor fusion system

Abstract

The invention relates to a multi-sensor fusion system. The multi-sensor fusion system comprises multiple ZigBee-based wireless monitoring nodes; data of each wireless monitoring node are respectively connected to a data pre-processing unit; the data pre-processing unit is connected with a data fusion center; and the data pre-processing unit assigns a a probability value to data of each node; fusion of data of each sensor is carried out by using a preset fusion rule by the data fusion center, and a decision result is obtained according to a decision rule. According to different assigned probability values of sensor data, data of multiple sensors are fused, the final result is obtained according to different rules, all-round monitoring can be obtained, the system has the advantages of low cost, high flexibility, easy configuration, high reliability and the like, and performances of the whole system are improved.

Description

technical field [0001] The invention relates to the field of wireless sensor networks, in particular to a multi-sensor fusion system. Background technique [0002] Wireless sensor networks have been widely used in monitoring in various fields, but most of the current monitoring systems use a single type of sensor, and some systems use multiple types of sensors, but they still reflect information in isolation from multiple aspects. There is not much fusion between them, so the accuracy rate is low in the state discrimination process. Moreover, most of the current monitoring systems are costly, and after wireless networking, there is great instability in data transmission, making it difficult to achieve comprehensive monitoring of the target environment, especially complex environments. Contents of the invention [0003] In order to overcome the disadvantages of the above-mentioned prior art, the object of the present invention is to provide a multi-sensor fusion system, wh...

AI Technical Summary

Problems solved by technology

[0002] Wireless sensor networks have been widely used in monitoring in various fields, but most of the current monitoring systems use a single type of sensor, and some systems use multiple types of sensors, but they still reflect information in isolation from multiple aspects. There is not much fusion between them, so the accuracy rate is low in the state discrimination process

Moreover, most of the current monitoring systems are costly, and after wireless networking, data transmission is very unstable, making it difficult to achieve comprehensive monitoring of target environments, especially complex environments

Images