High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3
To better detect fish in an aquaculture environment, a high-accuracy real-time detection model is proposed. An experimental dataset was collected for fish detection in laboratory aquaculture environments using remotely operated vehicles. To overcome the inaccuracy of the You Only Look Once v3 (YOLOv...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/4761670 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554112922681344 |
|---|---|
| author | Wenkai Wang Bingwei He Liwei Zhang |
| author_facet | Wenkai Wang Bingwei He Liwei Zhang |
| author_sort | Wenkai Wang |
| collection | DOAJ |
| description | To better detect fish in an aquaculture environment, a high-accuracy real-time detection model is proposed. An experimental dataset was collected for fish detection in laboratory aquaculture environments using remotely operated vehicles. To overcome the inaccuracy of the You Only Look Once v3 (YOLOv3) algorithm in underwater farming environment, a suitable set of hyperparameters was obtained through multiple sets of experiments. Then, a real-time image recovery algorithm is applied before YOLOv3 to reduce the effects of both noise and light on images whilst keeping the real-time capability, leading to a mean average precision of 0.85 and frame rate of 17.6 fps, respectively. Finally, compared with the base detection model using only the YOLOv3 algorithm, the enhanced detection model presented results in a reduction of miss detection rate from 23% to only 9% across different environments and with the detection accuracy of the target in different environments being improved from 8% to 37%. |
| format | Article |
| id | doaj-art-c02c1fc624354184bd7a9a53a5557078 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-c02c1fc624354184bd7a9a53a55570782025-02-03T05:52:26ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/47616704761670High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3Wenkai Wang0Bingwei He1Liwei Zhang2School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350000, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350000, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350000, ChinaTo better detect fish in an aquaculture environment, a high-accuracy real-time detection model is proposed. An experimental dataset was collected for fish detection in laboratory aquaculture environments using remotely operated vehicles. To overcome the inaccuracy of the You Only Look Once v3 (YOLOv3) algorithm in underwater farming environment, a suitable set of hyperparameters was obtained through multiple sets of experiments. Then, a real-time image recovery algorithm is applied before YOLOv3 to reduce the effects of both noise and light on images whilst keeping the real-time capability, leading to a mean average precision of 0.85 and frame rate of 17.6 fps, respectively. Finally, compared with the base detection model using only the YOLOv3 algorithm, the enhanced detection model presented results in a reduction of miss detection rate from 23% to only 9% across different environments and with the detection accuracy of the target in different environments being improved from 8% to 37%.http://dx.doi.org/10.1155/2021/4761670 |
| spellingShingle | Wenkai Wang Bingwei He Liwei Zhang High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 Complexity |
| title | High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 |
| title_full | High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 |
| title_fullStr | High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 |
| title_full_unstemmed | High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 |
| title_short | High-Accuracy Real-Time Fish Detection Based on Self-Build Dataset and RIRD-YOLOv3 |
| title_sort | high accuracy real time fish detection based on self build dataset and rird yolov3 |
| url | http://dx.doi.org/10.1155/2021/4761670 |
| work_keys_str_mv | AT wenkaiwang highaccuracyrealtimefishdetectionbasedonselfbuilddatasetandrirdyolov3 AT bingweihe highaccuracyrealtimefishdetectionbasedonselfbuilddatasetandrirdyolov3 AT liweizhang highaccuracyrealtimefishdetectionbasedonselfbuilddatasetandrirdyolov3 |