Based on the D2S (Dempster2Shafer) evidence theory, the fusion methods of related data and unrelated data are compared and studied, and the algorithms of multi-sensor data fusion are analyzed: centralized fusion algorithm and distributed fusion algorithm. Experiments have shown that the best effect is achieved when the distributed feedback fusion algorithm is executed. Then, using this algorithm, a recognition method combined with a linear interpolation neural network is proposed. Using the high-resolution one-dimensional range image of the stepped frequency radar of four aircraft, the recognition results of the neural network are sent to the sensors as evidence for fusion and recognition research. Experiments have shown that compared with the method of simply using neural networks, the correct recognition rate of the target has been improved. Keywords: recognition; high resolution; neural network; multi-sensor; data fusion
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore