Acoustic Haar feature extraction method and system for underwater target recognition
A technology for underwater target and feature extraction, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of low recognition accuracy, achieve strong practicability and improve training efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0056] like figure 1As shown, embodiments of the present invention proposes an acoustic HAAR feature extraction method for target recognition in water. The method first converts the first-dimensional raw target signal after the pre-treated generates an acoustic time-frequency feature and extracts acoustic characteristics based on Haar-LIKE. Since the extraction is huge, it is difficult to use the training of classification identification algorithm. It is proposed that the feature screening algorithm based on Adaboost is proposed, and the feature combination for identifying representative, and the feature combination after screening constitutes an acoustic haar feature vector, this feature The input of the subsequent classifier is used for training and target recognition of the classifier.
[0057] In the first step, the target signal in the original one-dimensional water is changed to the two-dimensional acoustic time-frequency feature.
[0058] The acoustic time flow diagram cont...
Embodiment 2
[0086] Embodiment 2 of the present invention proposes an acoustic HAAR feature extraction system for the target recognition in water, based on the method of Embodiment 1, the system includes: a pre-processing module, a time-frequency feature conversion module, a mixing acoustic HAAR feature extraction module And significant acoustic feature extraction modules;
[0087] The pretreatment module is used to prepare the target water acoustic signal in the received water;
[0088] The time-frequency feature conversion module is configured to time-frequency feature conversion of the pre-treated signal, generate an acoustic video characteristic;
[0089] The hybrid acoustic HAAR feature extraction module is used to characterize the acoustic time-frequency characteristics based on Haar-Like features.
[0090] The significant acoustic feature extraction module is used to complete a significant acoustic feature extraction based on the AdapBoost algorithm.
[0091] The present invention uses ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


