Jin Zhang

Dr. Jin Zhang

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 March 2023 in Journal of Fish Biology
Verified
Journal Article
Closed access
WSWei Shen
Wei Shen
ZPZhanfei Peng
Zhanfei Peng
JZJin Zhang
Jin Zhang

21 June 2018 in Sensors
Verified
Journal Article
Open access
PDF file
JDJing Danxiang
Jing Danxiang
JHJun Han
Jun Han
JZJin Zhang
Jin Zhang
This paper introduces a methodology applying an imaging sonar for three-dimensional (3D) target tracking underwater. The key process in this work involves obtaining the target’s position in space using two images of the same scene, acquired by an adaptive resolution imaging sonar (ARIS) at different positions. A data association algorithm was designed to connect the same target in image sequences. The goal of this work was to track multiple targets in 3D space. The ARIS provides sequences of bi-dimensional images from the backscattered energy according to the range and azimuth. The challenge involved determining the missing elevation information for the observed object within the sonar detection range. By computing the geometrical transformation between the acquisition planar images and the cubical space, using only the sonar information that included the posture and moving speed of the ARIS, the target’s elevation information was obtained. To evaluate the performance of the proposed method, an indoor experiment was conducted using the ARIS. On the basis of the experimental results, we confirmed that the proposed method effectively obtained the target’s position in 3D space. A moving target simulation was also conducted, and the results showed that this method was effective for moving targets. Finally, a field experiment was performed to obtain the vertical distribution and track the 3D trajectories of fish.

31 August 2024 in Fishes
Verified
Journal Article
Open access
PDF file
WSWei Shen
Wei Shen
LMLiu Mengqi
Liu Mengqi
QLQuanshui Lu
Quanshui Lu
ZYZhaowei Yin
Zhaowei Yin
JZJin Zhang
Jin Zhang
In order to more accurately and quickly identify and count underwater fish targets, and to address the issues of excessive reliance on manual processes and low processing efficiency in the identification and counting of fish targets using sonar data, a method based on DIDSON and YOLOv5 for fish target identification and counting is proposed. This study is based on YOLOv5, which trains a recognition model by identifying fish targets in each frame of DIDSON images and uses the DeepSort algorithm to track and count fish targets. Field data collection was conducted at Chenhang Reservoir in Shanghai, and this method was used to process and verify the results. The accuracy of random sampling was 83.56%, and the average accuracy of survey line detection was 84.28%. Compared with the traditional method of using Echoview to process sonar data, the YOLOv5 based method replaces the step that requires manual participation, significantly reducing the time required for data processing while maintaining the same accuracy, providing faster and more effective technical support for monitoring and managing fish populations.