SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation
As a highly productive rice, ratoon rice is widely planted worldwide, but the rolling of rice stubble in mechanical harvesting severely limits its total yield; based on this, some scholars have proposed rolled rice stubble righting machines. However, limited by the uncertainty of the field environme...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/16/9136 |
| _version_ | 1797585660879568896 |
|---|---|
| author | Yuanrui Li Liping Xiao Zhaopeng Liu Muhua Liu Peng Fang Xiongfei Chen Jiajia Yu Junan Liu Jinping Cai |
| author_facet | Yuanrui Li Liping Xiao Zhaopeng Liu Muhua Liu Peng Fang Xiongfei Chen Jiajia Yu Junan Liu Jinping Cai |
| author_sort | Yuanrui Li |
| collection | DOAJ |
| description | As a highly productive rice, ratoon rice is widely planted worldwide, but the rolling of rice stubble in mechanical harvesting severely limits its total yield; based on this, some scholars have proposed rolled rice stubble righting machines. However, limited by the uncertainty of the field environment, the machine’s localization accuracy of the target needs to be improved. To address this problem, real-time detection of rolled rice stubble rows is a prerequisite. Therefore, this paper introduces a deep learning method for the first time to achieve this. To this end, we presented a novel approach to improve a model that is used for the simplification of Mask R-CNN, which does not require any modules to be added or replaced on the original model. Firstly, two branches in the second stage were deleted, and the region proposals output from the stage was used directly as the mask generation region, and segmentation performance was substantially improved after a simple optimization of the region proposals. Further, the contribution of the feature map was counted, and the backbone network was simplified accordingly. The resulting SMR-RS model was still able to perform instance segmentation and has better segmentation performance than Mask R-CNN and other state-of-the-art models while significantly reducing the average image processing time and hardware consumption. |
| first_indexed | 2024-03-11T00:09:17Z |
| format | Article |
| id | doaj.art-1b836a7331a84bada5b59953c6fd7b7b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T00:09:17Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1b836a7331a84bada5b59953c6fd7b7b2023-11-19T00:04:58ZengMDPI AGApplied Sciences2076-34172023-08-011316913610.3390/app13169136SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row SegmentationYuanrui Li0Liping Xiao1Zhaopeng Liu2Muhua Liu3Peng Fang4Xiongfei Chen5Jiajia Yu6Junan Liu7Jinping Cai8College of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaCollege of Engineering, Jiangxi Agricultural University, Nanchang 330045, ChinaAs a highly productive rice, ratoon rice is widely planted worldwide, but the rolling of rice stubble in mechanical harvesting severely limits its total yield; based on this, some scholars have proposed rolled rice stubble righting machines. However, limited by the uncertainty of the field environment, the machine’s localization accuracy of the target needs to be improved. To address this problem, real-time detection of rolled rice stubble rows is a prerequisite. Therefore, this paper introduces a deep learning method for the first time to achieve this. To this end, we presented a novel approach to improve a model that is used for the simplification of Mask R-CNN, which does not require any modules to be added or replaced on the original model. Firstly, two branches in the second stage were deleted, and the region proposals output from the stage was used directly as the mask generation region, and segmentation performance was substantially improved after a simple optimization of the region proposals. Further, the contribution of the feature map was counted, and the backbone network was simplified accordingly. The resulting SMR-RS model was still able to perform instance segmentation and has better segmentation performance than Mask R-CNN and other state-of-the-art models while significantly reducing the average image processing time and hardware consumption.https://www.mdpi.com/2076-3417/13/16/9136ratoon riceconvolutional neural networkinstance segmentationmodel simplificationMask R-CNN |
| spellingShingle | Yuanrui Li Liping Xiao Zhaopeng Liu Muhua Liu Peng Fang Xiongfei Chen Jiajia Yu Junan Liu Jinping Cai SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation Applied Sciences ratoon rice convolutional neural network instance segmentation model simplification Mask R-CNN |
| title | SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation |
| title_full | SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation |
| title_fullStr | SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation |
| title_full_unstemmed | SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation |
| title_short | SMR-RS: An Improved Mask R-CNN Specialized for Rolled Rice Stubble Row Segmentation |
| title_sort | smr rs an improved mask r cnn specialized for rolled rice stubble row segmentation |
| topic | ratoon rice convolutional neural network instance segmentation model simplification Mask R-CNN |
| url | https://www.mdpi.com/2076-3417/13/16/9136 |
| work_keys_str_mv | AT yuanruili smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT lipingxiao smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT zhaopengliu smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT muhualiu smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT pengfang smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT xiongfeichen smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT jiajiayu smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT junanliu smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation AT jinpingcai smrrsanimprovedmaskrcnnspecializedforrolledricestubblerowsegmentation |