YOLOv7-Based Land and Underwater Target Detection and Recognition

Jieren Li; Liwei Shi; Shuxiang Guo

doi:10.1109/ICMA57826.2023.10215671

YOLOv7-Based Land and Underwater Target Detection and Recognition

Jieren Li
, Liwei Shi^*
, Shuxiang Guo

^*Corresponding author for this work

School of Medical Science and Engineering

Beijing Institute of Technology
Southern University of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

There is a growing demand for marine resource development. Bionic amphibious robots can replace humans to conduct land and underwater exploration, which has important research significance. Deep learning has developed rapidly in recent years, and many kinds of target detection algorithms have emerged. We select one two-stage target detection algorithm Faster R-CNN, three single-stage target detection algorithms SSD, Centernet, and YOLOv7. We use each of these four algorithms to train the VOC2007 dataset in a deep learning environment. After the training is completed, these four models are evaluated and predicted separately. We find an algorithm that is most suitable for the amphibious robot applicationYOLOv7. Finally, we use the YOLOv7 model to detect the underwater dataset, and the results prove that the model is promising for detecting small underwater targets.

Original language	English
Title of host publication	2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1437-1442
Number of pages	6
ISBN (Electronic)	9798350320831
DOIs	https://doi.org/10.1109/ICMA57826.2023.10215671
Publication status	Published - 2023
Event	20th IEEE International Conference on Mechatronics and Automation, ICMA 2023 - Harbin, Heilongjiang, China Duration: 6 Aug 2023 → 9 Aug 2023

Publication series

Name	2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023

Conference

Conference	20th IEEE International Conference on Mechatronics and Automation, ICMA 2023
Country/Territory	China
City	Harbin, Heilongjiang
Period	6/08/23 → 9/08/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

Amphibious robots
Centernet
Faster R-CNN
SSD
YOLOv7

Access to Document

10.1109/ICMA57826.2023.10215671

Cite this

Li, J., Shi, L., & Guo, S. (2023). YOLOv7-Based Land and Underwater Target Detection and Recognition. In 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023 (pp. 1437-1442). (2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMA57826.2023.10215671

@inproceedings{3ca9a6fe76604c1c9fad2f927f9859f1,

title = "YOLOv7-Based Land and Underwater Target Detection and Recognition",

abstract = "There is a growing demand for marine resource development. Bionic amphibious robots can replace humans to conduct land and underwater exploration, which has important research significance. Deep learning has developed rapidly in recent years, and many kinds of target detection algorithms have emerged. We select one two-stage target detection algorithm Faster R-CNN, three single-stage target detection algorithms SSD, Centernet, and YOLOv7. We use each of these four algorithms to train the VOC2007 dataset in a deep learning environment. After the training is completed, these four models are evaluated and predicted separately. We find an algorithm that is most suitable for the amphibious robot applicationYOLOv7. Finally, we use the YOLOv7 model to detect the underwater dataset, and the results prove that the model is promising for detecting small underwater targets.",

keywords = "Amphibious robots, Centernet, Faster R-CNN, SSD, YOLOv7",

author = "Jieren Li and Liwei Shi and Shuxiang Guo",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th IEEE International Conference on Mechatronics and Automation, ICMA 2023 ; Conference date: 06-08-2023 Through 09-08-2023",

year = "2023",

doi = "10.1109/ICMA57826.2023.10215671",

language = "English",

series = "2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1437--1442",

booktitle = "2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023",

address = "United States",

}

Li, J, Shi, L & Guo, S 2023, YOLOv7-Based Land and Underwater Target Detection and Recognition. in 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023. 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1437-1442, 20th IEEE International Conference on Mechatronics and Automation, ICMA 2023, Harbin, Heilongjiang, China, 6/08/23. https://doi.org/10.1109/ICMA57826.2023.10215671

YOLOv7-Based Land and Underwater Target Detection and Recognition. / Li, Jieren; Shi, Liwei; Guo, Shuxiang.
2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1437-1442 (2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - YOLOv7-Based Land and Underwater Target Detection and Recognition

AU - Li, Jieren

AU - Shi, Liwei

AU - Guo, Shuxiang

PY - 2023

Y1 - 2023

N2 - There is a growing demand for marine resource development. Bionic amphibious robots can replace humans to conduct land and underwater exploration, which has important research significance. Deep learning has developed rapidly in recent years, and many kinds of target detection algorithms have emerged. We select one two-stage target detection algorithm Faster R-CNN, three single-stage target detection algorithms SSD, Centernet, and YOLOv7. We use each of these four algorithms to train the VOC2007 dataset in a deep learning environment. After the training is completed, these four models are evaluated and predicted separately. We find an algorithm that is most suitable for the amphibious robot applicationYOLOv7. Finally, we use the YOLOv7 model to detect the underwater dataset, and the results prove that the model is promising for detecting small underwater targets.

AB - There is a growing demand for marine resource development. Bionic amphibious robots can replace humans to conduct land and underwater exploration, which has important research significance. Deep learning has developed rapidly in recent years, and many kinds of target detection algorithms have emerged. We select one two-stage target detection algorithm Faster R-CNN, three single-stage target detection algorithms SSD, Centernet, and YOLOv7. We use each of these four algorithms to train the VOC2007 dataset in a deep learning environment. After the training is completed, these four models are evaluated and predicted separately. We find an algorithm that is most suitable for the amphibious robot applicationYOLOv7. Finally, we use the YOLOv7 model to detect the underwater dataset, and the results prove that the model is promising for detecting small underwater targets.

KW - Amphibious robots

KW - Centernet

KW - Faster R-CNN

KW - SSD

KW - YOLOv7

UR - https://www.scopus.com/pages/publications/85170824824

U2 - 10.1109/ICMA57826.2023.10215671

DO - 10.1109/ICMA57826.2023.10215671

M3 - Conference contribution

AN - SCOPUS:85170824824

T3 - 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023

SP - 1437

EP - 1442

BT - 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

Y2 - 6 August 2023 through 9 August 2023

ER -

YOLOv7-Based Land and Underwater Target Detection and Recognition

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this