A method and system for underwater image target detection

An underwater image and target detection technology, applied in the field of image processing, can solve the problems of long time, low recognition accuracy, time-consuming and labor-intensive engineering, etc., and achieve the effect of high accuracy and short time-consuming.

CN109214319AInactive Publication Date: 2019-01-15CHINA AGRI UNIV
2 Cites 15 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2019-01-15
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The embodiment of the invention provides an underwater image target detection method and system, comprising the following steps: obtaining an underwater image to be detected, and utilizing MS-CNN denoise algorithm and dark channel prior denoising algorithm preprocess that underwater image to be detected to obtain a first image; inputting the first image into the trained preset feature pyramid network FPN, and outputting a target detection result; wherein the convolution layer of the preset FPN is a PVA network and a C. ReLU structure is added. As the underwater image to be detected is preprocessed, the improved FPN is used to detect the target from the preprocessed underwater image and output the target detection results without manual feature design. The detection process is time-consuming and the detection results have high accuracy. It can be well adapted to the practical application requirements such as automatic detection and automatic fishing.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] Embodiments of the present invention relate to the technical field of image processing, and more specifically, to a method and system for detecting an underwater image target. Background technique

[0002] As one of the important technologies for perceiving the underwater world, underwater machine vision has been widely used in ocean engineering, underwater exploration, target detection, biological monitoring, etc., providing rich resources for oceanographic and fishery scientific research. The information laid the foundation for the development of smart ocean and smart fishery. As a branch of underwater image target detection technology, it is mounted on underwater robots, applying image and video analysis, biomass detection, and biometric identification to the underwater environment, which promotes the development of ocean detection and fishery automation.

[0003] However, the underwater environment usually has insufficient light, obvious noise, lo...

Examples

Embodiment Construction

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the Some, but not all, embodiments are invented. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0021] figure 1 A flow chart of an underwater image target detection method provided by an embodiment of the present invention, such as figure 1 shown, including:

[0022] S101. Acquire the underwater image to be detected, and use the MS-CNN denoising algorithm and the dark channel prior denoising algorithm to preprocess the underwater image to be detected to obtain a...