Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN
The normal growth of fishes is closely relevant to the density of mariculture. It is of great significance to accurately calculate the breeding area of specific sea area from satellite remote sensing images. However, there are no reports about cage segmentation and density detection based on remote...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Information Processing in Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214317321000378 |
| _version_ | 1797757906789072896 |
|---|---|
| author | Chuang Yu Zhuhua Hu Ruoqing Li Xin Xia Yaochi Zhao Xiang Fan Yong Bai |
| author_facet | Chuang Yu Zhuhua Hu Ruoqing Li Xin Xia Yaochi Zhao Xiang Fan Yong Bai |
| author_sort | Chuang Yu |
| collection | DOAJ |
| description | The normal growth of fishes is closely relevant to the density of mariculture. It is of great significance to accurately calculate the breeding area of specific sea area from satellite remote sensing images. However, there are no reports about cage segmentation and density detection based on remote sensing images so far. And the accurate segmentation of cages faces challenges from very large high-resolution images. Firstly, a new public mariculture cage data set is built. Secondly, the training set is augmented via sample variations to improve the robustness of the model. Then, for cage segmentation and density statistics, a new methodology based on Mask R-CNN is proposed. Using dividing and stitching technologies, the entire remote sensing test images of the cage can be accurately segmented. Finally, using the trained model, the object detection features and segmentation characteristics can be obtained at the same time. Considering only the area within the target detection frame, the proposed method can count the pixels in the segmented area, which can obtain accurate area and density while reducing time-consuming. Experimental results demonstrate that, compared with traditional contour extraction method and U-Net based scheme, the proposed scheme can significantly improve segmentation precision and model’s robustness. The relative error of the actual area is only 1.3%. |
| first_indexed | 2024-03-12T18:21:22Z |
| format | Article |
| id | doaj.art-a02277a9068b489ab022991d5271a694 |
| institution | Directory Open Access Journal |
| issn | 2214-3173 |
| language | English |
| last_indexed | 2024-03-12T18:21:22Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Information Processing in Agriculture |
| spelling | doaj.art-a02277a9068b489ab022991d5271a6942023-08-02T08:51:03ZengElsevierInformation Processing in Agriculture2214-31732022-09-0193417430Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNNChuang Yu0Zhuhua Hu1Ruoqing Li2Xin Xia3Yaochi Zhao4Xiang Fan5Yong Bai6School of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR China; Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, PR ChinaSchool of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR China; Corresponding authorsat: School of Information and Communication Engineering, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR China.School of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR ChinaSchool of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR ChinaSchool of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR China; Corresponding authorsat: School of Information and Communication Engineering, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR China.School of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR ChinaSchool of Information and Communication Engineering, School of Computer Science & Cyberspace Security, Hainan University, No. 58, Renmin Avenue, Haikou 570228, PR ChinaThe normal growth of fishes is closely relevant to the density of mariculture. It is of great significance to accurately calculate the breeding area of specific sea area from satellite remote sensing images. However, there are no reports about cage segmentation and density detection based on remote sensing images so far. And the accurate segmentation of cages faces challenges from very large high-resolution images. Firstly, a new public mariculture cage data set is built. Secondly, the training set is augmented via sample variations to improve the robustness of the model. Then, for cage segmentation and density statistics, a new methodology based on Mask R-CNN is proposed. Using dividing and stitching technologies, the entire remote sensing test images of the cage can be accurately segmented. Finally, using the trained model, the object detection features and segmentation characteristics can be obtained at the same time. Considering only the area within the target detection frame, the proposed method can count the pixels in the segmented area, which can obtain accurate area and density while reducing time-consuming. Experimental results demonstrate that, compared with traditional contour extraction method and U-Net based scheme, the proposed scheme can significantly improve segmentation precision and model’s robustness. The relative error of the actual area is only 1.3%.http://www.sciencedirect.com/science/article/pii/S2214317321000378Deep learningMask R-CNNImage segmentationRemote sensing |
| spellingShingle | Chuang Yu Zhuhua Hu Ruoqing Li Xin Xia Yaochi Zhao Xiang Fan Yong Bai Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN Information Processing in Agriculture Deep learning Mask R-CNN Image segmentation Remote sensing |
| title | Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN |
| title_full | Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN |
| title_fullStr | Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN |
| title_full_unstemmed | Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN |
| title_short | Segmentation and density statistics of mariculture cages from remote sensing images using mask R-CNN |
| title_sort | segmentation and density statistics of mariculture cages from remote sensing images using mask r cnn |
| topic | Deep learning Mask R-CNN Image segmentation Remote sensing |
| url | http://www.sciencedirect.com/science/article/pii/S2214317321000378 |
| work_keys_str_mv | AT chuangyu segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT zhuhuahu segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT ruoqingli segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT xinxia segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT yaochizhao segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT xiangfan segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn AT yongbai segmentationanddensitystatisticsofmariculturecagesfromremotesensingimagesusingmaskrcnn |