Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields
Imaging sonar systems are widely used for monitoring fish behavior in turbid or low ambient light waters. For analyzing fish behavior in sonar images, fish segmentation is often required. In this paper, Mask R-CNN is adopted for segmenting fish in sonar images. Sonar images acquired from different s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7625 |
| _version_ | 1797508431998877696 |
|---|---|
| author | Chin-Chun Chang Yen-Po Wang Shyi-Chyi Cheng |
| author_facet | Chin-Chun Chang Yen-Po Wang Shyi-Chyi Cheng |
| author_sort | Chin-Chun Chang |
| collection | DOAJ |
| description | Imaging sonar systems are widely used for monitoring fish behavior in turbid or low ambient light waters. For analyzing fish behavior in sonar images, fish segmentation is often required. In this paper, Mask R-CNN is adopted for segmenting fish in sonar images. Sonar images acquired from different shallow waters can be quite different in the contrast between fish and the background. That difference can make Mask R-CNN trained on examples collected from one fish farm ineffective to fish segmentation for the other fish farms. In this paper, a preprocessing convolutional neural network (PreCNN) is proposed to provide “standardized” feature maps for Mask R-CNN and to ease applying Mask R-CNN trained for one fish farm to the others. PreCNN aims at decoupling learning of fish instances from learning of fish-cultured environments. PreCNN is a semantic segmentation network and integrated with conditional random fields. PreCNN can utilize successive sonar images and can be trained by semi-supervised learning to make use of unlabeled information. Experimental results have shown that Mask R-CNN on the output of PreCNN is more accurate than Mask R-CNN directly on sonar images. Applying Mask R-CNN plus PreCNN trained for one fish farm to new fish farms is also more effective. |
| first_indexed | 2024-03-10T05:04:55Z |
| format | Article |
| id | doaj.art-43df252520b94720909b503ebd6f787c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:04:55Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-43df252520b94720909b503ebd6f787c2023-11-23T01:26:54ZengMDPI AGSensors1424-82202021-11-012122762510.3390/s21227625Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random FieldsChin-Chun Chang0Yen-Po Wang1Shyi-Chyi Cheng2Department of Computer Science and Engineering, National Taiwan Ocean University, 2, Pei-Ning Rd., Keelung 202301, TaiwanDepartment of Computer Science and Engineering, National Taiwan Ocean University, 2, Pei-Ning Rd., Keelung 202301, TaiwanDepartment of Computer Science and Engineering, National Taiwan Ocean University, 2, Pei-Ning Rd., Keelung 202301, TaiwanImaging sonar systems are widely used for monitoring fish behavior in turbid or low ambient light waters. For analyzing fish behavior in sonar images, fish segmentation is often required. In this paper, Mask R-CNN is adopted for segmenting fish in sonar images. Sonar images acquired from different shallow waters can be quite different in the contrast between fish and the background. That difference can make Mask R-CNN trained on examples collected from one fish farm ineffective to fish segmentation for the other fish farms. In this paper, a preprocessing convolutional neural network (PreCNN) is proposed to provide “standardized” feature maps for Mask R-CNN and to ease applying Mask R-CNN trained for one fish farm to the others. PreCNN aims at decoupling learning of fish instances from learning of fish-cultured environments. PreCNN is a semantic segmentation network and integrated with conditional random fields. PreCNN can utilize successive sonar images and can be trained by semi-supervised learning to make use of unlabeled information. Experimental results have shown that Mask R-CNN on the output of PreCNN is more accurate than Mask R-CNN directly on sonar images. Applying Mask R-CNN plus PreCNN trained for one fish farm to new fish farms is also more effective.https://www.mdpi.com/1424-8220/21/22/7625fish segmentationsonar imagesconditional random fieldsmask R-CNN |
| spellingShingle | Chin-Chun Chang Yen-Po Wang Shyi-Chyi Cheng Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields Sensors fish segmentation sonar images conditional random fields mask R-CNN |
| title | Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields |
| title_full | Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields |
| title_fullStr | Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields |
| title_full_unstemmed | Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields |
| title_short | Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields |
| title_sort | fish segmentation in sonar images by mask r cnn on feature maps of conditional random fields |
| topic | fish segmentation sonar images conditional random fields mask R-CNN |
| url | https://www.mdpi.com/1424-8220/21/22/7625 |
| work_keys_str_mv | AT chinchunchang fishsegmentationinsonarimagesbymaskrcnnonfeaturemapsofconditionalrandomfields AT yenpowang fishsegmentationinsonarimagesbymaskrcnnonfeaturemapsofconditionalrandomfields AT shyichyicheng fishsegmentationinsonarimagesbymaskrcnnonfeaturemapsofconditionalrandomfields |