Fish counting through underwater fish detection using deep learning techniques
Aquaculture is the practice of reproducing, increasing and yielding aquatic organisms, such as aquatic animals and aquatic plants, in confined water bodies, like ponds, lakes, rivers, oceans, etc. Fishery represents one of the activities of aquaculture. The key function affecting fisheries managemen...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
ICI Publishing House
2023-12-01
|
| Series: | Revista Română de Informatică și Automatică |
| Subjects: | |
| Online Access: | https://rria.ici.ro/documents/446/art._6_India_VeerappanSundari-C1.pdf |
| _version_ | 1797355049810132992 |
|---|---|
| author | Sundari VEERAPPAN Jansi Rani SELLA VELUSWAMI |
| author_facet | Sundari VEERAPPAN Jansi Rani SELLA VELUSWAMI |
| author_sort | Sundari VEERAPPAN |
| collection | DOAJ |
| description | Aquaculture is the practice of reproducing, increasing and yielding aquatic organisms, such as aquatic animals and aquatic plants, in confined water bodies, like ponds, lakes, rivers, oceans, etc. Fishery represents one of the activities of aquaculture. The key function affecting fisheries management is the fishing activity. Operations like locating and counting fish are used to enhance this practice. There is a strong demand for underwater fish identification for multiple uses in sustainable fisheries. Real time monitoring helps to improve fishing activities. Deep Learning Techniques are used to train the computer with the available existing image data, faster GPUs, and algorithms employed to detect, locate and classify various objects within an underwater image or video with high accuracy. A well-liked object detection model, namely YOLO (You Only Look Once), is renowned for its quickness and precision. This paper presents a state-of-the-art version of the YOLO model for detecting and counting fish from underwater images or videos. The primary objective is to develop a system for automatic fish detection using an advanced convolutional neural network YOLOv8 and compare the results with the ones of the YOLOv7 model. It is proved that YOLOv8s performs better than YOLOv7, as YOLOv8s achieves a mAP@0.5 of 0.964, a precision of 0.929 and an IoU of 0.7. |
| first_indexed | 2024-03-08T13:58:38Z |
| format | Article |
| id | doaj.art-fe26e2b4cb6e4e9b9911fe12f5302304 |
| institution | Directory Open Access Journal |
| issn | 1220-1758 1841-4303 |
| language | English |
| last_indexed | 2024-03-08T13:58:38Z |
| publishDate | 2023-12-01 |
| publisher | ICI Publishing House |
| record_format | Article |
| series | Revista Română de Informatică și Automatică |
| spelling | doaj.art-fe26e2b4cb6e4e9b9911fe12f53023042024-01-15T08:22:51ZengICI Publishing HouseRevista Română de Informatică și Automatică1220-17581841-43032023-12-01334698010.33436/v33i4y202306Fish counting through underwater fish detection using deep learning techniquesSundari VEERAPPAN0Jansi Rani SELLA VELUSWAMI1Department of Computer Science and Engineering, Meenakshi Sundararajan Engineering College, Chennai, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, Tamil Nadu, IndiaAquaculture is the practice of reproducing, increasing and yielding aquatic organisms, such as aquatic animals and aquatic plants, in confined water bodies, like ponds, lakes, rivers, oceans, etc. Fishery represents one of the activities of aquaculture. The key function affecting fisheries management is the fishing activity. Operations like locating and counting fish are used to enhance this practice. There is a strong demand for underwater fish identification for multiple uses in sustainable fisheries. Real time monitoring helps to improve fishing activities. Deep Learning Techniques are used to train the computer with the available existing image data, faster GPUs, and algorithms employed to detect, locate and classify various objects within an underwater image or video with high accuracy. A well-liked object detection model, namely YOLO (You Only Look Once), is renowned for its quickness and precision. This paper presents a state-of-the-art version of the YOLO model for detecting and counting fish from underwater images or videos. The primary objective is to develop a system for automatic fish detection using an advanced convolutional neural network YOLOv8 and compare the results with the ones of the YOLOv7 model. It is proved that YOLOv8s performs better than YOLOv7, as YOLOv8s achieves a mAP@0.5 of 0.964, a precision of 0.929 and an IoU of 0.7.https://rria.ici.ro/documents/446/art._6_India_VeerappanSundari-C1.pdfaquaculturecomputer visionyolofish detection |
| spellingShingle | Sundari VEERAPPAN Jansi Rani SELLA VELUSWAMI Fish counting through underwater fish detection using deep learning techniques Revista Română de Informatică și Automatică aquaculture computer vision yolo fish detection |
| title | Fish counting through underwater fish detection using deep learning techniques |
| title_full | Fish counting through underwater fish detection using deep learning techniques |
| title_fullStr | Fish counting through underwater fish detection using deep learning techniques |
| title_full_unstemmed | Fish counting through underwater fish detection using deep learning techniques |
| title_short | Fish counting through underwater fish detection using deep learning techniques |
| title_sort | fish counting through underwater fish detection using deep learning techniques |
| topic | aquaculture computer vision yolo fish detection |
| url | https://rria.ici.ro/documents/446/art._6_India_VeerappanSundari-C1.pdf |
| work_keys_str_mv | AT sundariveerappan fishcountingthroughunderwaterfishdetectionusingdeeplearningtechniques AT jansiranisellaveluswami fishcountingthroughunderwaterfishdetectionusingdeeplearningtechniques |