Underwater target identification method based on improved YOLOv8 algorithm

By improving the YOLOv8n model, a deep separation convolution and inverted residual attention mechanism was introduced, a small target detection head was added, and a multi-level detection head system was built, which solved the detection accuracy and efficiency of underwater target recognition in a turbid environment of water bodies, and achieved higher mAP, accuracy and recall.

CN120356084AActive Publication Date: 2025-07-22WILD SC NINGBO INTELLIGENT TECH +1
View PDF 5 Cites 5 Cited by

Patent Information

Application Number
CN202510841459.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-23
Publication Date
2025-07-22
Estimated Expiration
2045-06-23

Smart Images

  • Figure CN120356084A_ABST
    Figure CN120356084A_ABST
Patent Text Reader

Abstract

The invention discloses an underwater target recognition method based on an improved YOLOv8 algorithm, and the method comprises the steps: inputting an underwater image into an improved YOLOv8n model for underwater target detection, and obtaining an output underwater target recognition result. The method has the advantages that the convolution blocks of the P5 layer of the backbone network and the last layer of the neck network adopt DSConv, so that the network complexity is reduced, and the reasoning speed is increased; a fourth C2f module of the backbone network adopts a C2f DiRMB module in which an inverted residual attention mechanism and dual-channel convolution are introduced, so that the capability of capturing key global information of the network is enhanced, training parameters are reduced, and the understanding of a complex scene is improved; and finally, a small target detection head for improving the small target detection capability is additionally arranged in the head network. According to the underwater target identification method, the mAP (at) is 0.5%, the mAP (at) is 0.5-0.95%, and the accuracy and the recall rate are respectively improved by 0.5%, 0.8%, 0.5% and 1.0%.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Small target detection method for images acquired by unmanned aerial vehicle based on improved YOLOv8 algorithm

    CN118628939A

  • Lightweight network target detection method based on structure optimization and feature fusion

    CN118710883A

  • PCB small target defect detection method based on improved YOLOv8x

    CN119722669A

  • Power transformation equipment defect detection method based on improved YOLOv8n model

    CN120047714A

  • Method and system for multi-source algae image target detection

    US20240087310A1

Cited By

  • Small target visual detection method in geological exploration scene

    CN120612561A

  • A small target visual detection method in geological exploration scenarios

    CN120612561B

  • Underwater target detection method, system, equipment and medium

    CN120808131A

  • Deep-sea biological image processing method based on neural network

    CN121236572A

  • Bubble detection, tracking and parameter quantification method and device based on improved YOLOv8

    CN121884078A