Multi-category target recognition method and system for unattended sensor system

Abstract

The invention discloses a multi-category target recognition method and system for an unattended sensor system. The method comprises the following steps: S1, data preprocessing: framing original data collected by unattended sensor equipment; s2, signal feature extraction: extracting multiple segments of independent time domain features of the framed data at the same time; s3, convolutional neural network model training: taking the multiple segments of independent time domain features obtained in the step S2 as training samples, inputting the training samples into a convolutional neural network for training, and establishing a convolutional neural network model; and S4, signal recognition: recognizing the signal through the convolutional neural network model established in the step S3 to obtain an recognition result. The invention has the advantages of being easy and convenient to operate, small in calculation amount, high in recognition rate, capable of being applied to an embedded system and the like.

Description

technical field [0001] The invention mainly relates to the technical field of multi-target pattern recognition, in particular to a multi-class target recognition method and system for an unattended sensor system. Background technique [0002] Target recognition methods in traditional unattended sensor systems include: zero-crossing analysis, wavelet transform, convolutional neural network, cyclic neural network, etc. The first two recognition methods are relatively simple, but their performance is poor and their environmental adaptability is not good. The latter two methods have a large amount of calculation and are difficult to apply to microprocessors with relatively limited computing resources, and their practical applications are limited. Contents of the invention [0003] The technical problem to be solved by the present invention lies in: aiming at the technical problems existing in the prior art, the present invention provides a multi-category target recognition met...

AI Technical Summary

Problems solved by technology

[0002] Target recognition methods in traditional unattended sensor systems include: zero-crossing analysis, wavelet transform, convolutional neural network, cyclic neural network, etc. The first two recognition methods are relatively simple, but their performance is poor and their environmental adaptability is not good. The latter two have a large amount of calculation, which is difficult to apply to microprocessors with relatively limited computing resources, and their practical applications are limited.

Images