OCEANS 2018 MTS/IEEE Charleston 2018
DOI: 10.1109/oceans.2018.8604658
|View full text |Cite
|
Sign up to set email alerts
|

Embedded Online Fish Detection and Tracking System via YOLOv3 and Parallel Correlation Filter

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0
1

Year Published

2020
2020
2022
2022

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 33 publications
(10 citation statements)
references
References 8 publications
0
9
0
1
Order By: Relevance
“…Then, there comes one-stage detection algorithms with high detection speed. R-CNN and YOLO are currently the most widely utilised one-stage object detection methods (You Only Look Once) [7] [8][9] [10].…”
Section: Object Detectionmentioning
confidence: 99%
“…Then, there comes one-stage detection algorithms with high detection speed. R-CNN and YOLO are currently the most widely utilised one-stage object detection methods (You Only Look Once) [7] [8][9] [10].…”
Section: Object Detectionmentioning
confidence: 99%
“…Sung et al [45] used YOLO for fish detection and achieved 16.7 fps object detection speed in GPU. In work [46], YOLOv3 was implemented on NVIDIA Jetson TX2 and the experimental results showed that it can achieve real-time object detection. However, the above research does not take any effective approaches to enhance the quality of underwater images before performing object detection.…”
Section: Related Workmentioning
confidence: 99%
“…In previous work on fish detection, Liu et al [18] have presented an online fish tracking system using YOLO and parallel correlation filters, and included detection and categorization in an end-to-end approach. Similar work is carried out by Xu et al [19] who trained a YOLO architecture aimed at detecting a variety of fish species with three very different datasets, obtaining a mean average precision score of 0.5392.…”
Section: Introductionmentioning
confidence: 99%