Citation: Ge, H.; Dai, Y.; Zhu, Z.; Liu,
R. A Deep Learning Model Applied
to Optical Image Target Detection
and Recognition for the Identification
of Underwater Biostructures.
Machines 2022, 10, 809. https://
doi.org/10.3390/machines10090809
Academic Editors: Kelvin K.L. Wong,
Dhanjoo N. Ghista, Andrew W.H. Ip
and W.J. (Chris) Zhang
Received: 25 July 2022
Accepted: 29 August 2022
Published: 15 September 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Deep Learning Model Applied to Optical Image Target
Detection and Recognition for the Identification of
Underwater Biostructures
Huilin Ge , Yuewei Dai *, Zhiyu Zhu and Runbang Liu
School of Electronic Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China
* Correspondence: dyw@nuist.edu.cn
Abstract:
Objective: We propose a deep-learning-based underwater target detection system that
can effectively solve the problem of underwater optical image target detection and recognition.
Methods: In this paper, based on the depth of the underwater optical image target detection and
recognition and using a learning model, we put forward corresponding solutions using the concept
of style migration solutions, such as training samples. A lack of variability and poor generalization of
practical applications presents a challenge for underwater object identification. The UW_YOLOv3
lightweight model was proposed to solve the problems of calculating energy consumption and
storage resource limitations in underwater application scenarios. The detection and recognition
module, based on deep learning, can deal with the degradation process of underwater imaging by
embedding an image enhancement module into the detection and recognition module for the joint
tuning and transferring of knowledge. Results: The detection accuracy of the UW_YOLOv3 model
designed in this paper outperformed the lightweight algorithm YOLOV3-TINY by 7.9% at the same
image scale input. Compared with other large algorithms, the detection accuracy was lower, but
the detection speed was much higher. Compared with the SSD algorithm, the detection accuracy
was only 4.7 lower; the speed was 40.9 FPS higher; and the rate was nearly 16 times higher than
Faster R-CNN. When the input scale was 224, although part of the accuracy was lost, the detection
speed doubled, reaching 156.9 FPS. Conclusion: Based on our framework, the problem of underwater
optical image target detection and recognition can be effectively solved. Relevant studies have not
only enriched the theory of target detection and glory, but have also provided optical glasses with a
clear vision for appropriate underwater application systems.
Keywords:
underwater imaging; deep learning; object detection; image enhancement; UW_YOLOv3
1. Introduction
Underwater target detection tasks can be divided into two categories according to the
different signals of the target to be detected [
1
]. The first category uses acoustic images
collected by sonar to detect underwater targets, which is only suitable for the long-distance
detection and tracking of large targets [
2
]. The second type is underwater target detection
based on the optical image of a machine-vision system.
Visual images have advantages in short-range underwater target detection, with a
high resolution and rich information. Therefore, target detection based on light vision
has gradually become the leading research direction of underwater short-range target
recognition and detection [
3
]. To accurately identify a target, the key is to determine the
category and location of the underwater target. The most direct method is to collect images
through underwater cameras and implement detection through a deployed underwater
target-detection algorithm. However, shallow aquatic environments are complex and often
lead to problems such as color shifts, uneven illumination, blurring, and distortion in the
imaging process. These scenarios are very unfavorable for the results of the detection
Machines 2022, 10, 809. https://doi.org/10.3390/machines10090809 https://www.mdpi.com/journal/machines
