Underwater target intelligent detection system and method and storage medium

An underwater target, intelligent detection technology, applied in the field of computer vision, can solve problems such as the development limit of target detection technology, and achieve the effect of improving computing speed

Pending Publication Date: 2021-12-07
HUBEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its technology is widely used in military drones and consumer drones. The real-time target detection function is one of the very important functions of smart devices at present and in the future. However, due to hardware facilities such as memory and computing power However, the development of target detection technology is greatly restricted, so it is of great research value to prune and lightweight the target detection network.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Underwater target intelligent detection system and method and storage medium
  • Underwater target intelligent detection system and method and storage medium
  • Underwater target intelligent detection system and method and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, this embodiment provides an underwater target intelligent detection system, which specifically includes:

[0059] The image preprocessing module M1 is used to perform data cleaning and data sorting operations on the acquired underwater target images to obtain preprocessed images;

[0060] An image data division module M2, configured to perform data division on the preprocessed image to obtain a training set and a test set;

[0061] The target detection network training module M3 is used to train the YOLOv3-SC network model by using the training set to obtain the trained YOLOv3-SC network model and the underwater target information to be detected output by the YOLOv3-SC network model;

[0062] The target monitoring network testing module M4 is used to test the trained YOLOv3-SC network model by using the test set to obtain the mAP value of the trained YOLOv3-SC network model;

[0063] The threshold comparison module M5 is used to compare the ...

Embodiment 2

[0100] Such as Figure 5 As shown, this embodiment provides a method for intelligent detection of underwater targets applied to the system of Embodiment 1, and the specific steps include:

[0101] S1: Perform data cleaning and data sorting operations on the acquired underwater target images to obtain preprocessed images;

[0102] S2: performing data division on the preprocessed image to obtain a training set and a test set;

[0103] S3: using the training set to train the YOLOv3-SC network model to obtain the trained YOLOv3-SC network model and the underwater target information to be detected output by the YOLOv3-SC network model;

[0104] S4: Using the test set to test the trained YOLOv3-SC network model to obtain the mAP value of the trained YOLOv3-SC network model;

[0105] S5: Compare the mAP value with the preset threshold a, if the mAP value is less than or equal to the preset threshold a, then return to the image data division module, adjust the ratio of the data divi...

Embodiment 3

[0107] Such as Image 6 As shown, this embodiment provides a computer-readable storage medium on which a computer program P1 is stored.

[0108] When the computer program is executed by the processor, the steps described in the intelligent underwater target detection method in Embodiment 2 are realized.

[0109] Similarly, the storage medium may be a ROM, a USB flash drive, or a mechanical hard disk, a solid state hard disk, or a mobile hard disk. Its readable state can be read and run by any one or more mobile terminals such as computers, mobile phones, and tablet computers. Certainly, this embodiment only provides a kind of basic structure, in Image 6 On the basis of the storage medium, one or at least two components are added, and the specific types of components include but are not limited to the above-mentioned hardware. Any hardware or software that can implement one or more steps in the method in Embodiment 2 falls within the protection scope of the present inventio...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an underwater target intelligent detection system and method and a storage medium. The invention belongs to the technical field of computer vision processing. The image is sliced and spliced by using the Slice-Concat network structure, the sliced image without data loss can be obtained, and the width and the height of the image are reduced after the image is sliced. According to analysis of a model complexity calculation formula, it can be known that the operation speed of the model can be directly increased when the image width and height are decreased. And meanwhile, the trained network model is trained and tested by using the test set, so that the identification and detection precision of the model can be ensured. According to the method, the target detection speed can be improved on the premise that the underwater target detection precision is ensured, and efficient real-time detection of the underwater target is achieved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an underwater target intelligent detection system, method and storage medium. Background technique [0002] Object detection is a very popular research field in the field of computer vision. Its technology is widely used in both military drones and consumer drones. The real-time target detection function is one of the very important functions of smart devices at present and in the future. However, due to hardware facilities such as memory and computing power However, the development of target detection technology is greatly restricted, so pruning and lightweight processing of target detection network has very important research value. The present invention adds a Slice-Concat structure before the backbone feature extraction network of the YOLOv3 network to reduce the calculation amount of the YOLOv3 network model and realize efficient real-time detection of underwater ta...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06F18/214
Inventor 吴珺刘欣王春枝朱天亮朱嘉辉李天意吴一帆王姝彤
Owner HUBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap