An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree
Broiler weighing is essential in the broiler farming industry. Camera-based systems can economically weigh various broiler types without expensive platforms. However, existing computer vision methods for weight estimation are less mature, as they focus on young broilers. In effect, the estimation er...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/13/23/3721 |
| _version_ | 1797400505361629184 |
|---|---|
| author | Ximing Li Jingyi Wu Zeyong Zhao Yitao Zhuang Shikai Sun Huanlong Xie Yuefang Gao Deqin Xiao |
| author_facet | Ximing Li Jingyi Wu Zeyong Zhao Yitao Zhuang Shikai Sun Huanlong Xie Yuefang Gao Deqin Xiao |
| author_sort | Ximing Li |
| collection | DOAJ |
| description | Broiler weighing is essential in the broiler farming industry. Camera-based systems can economically weigh various broiler types without expensive platforms. However, existing computer vision methods for weight estimation are less mature, as they focus on young broilers. In effect, the estimation error increases with the age of the broiler. To tackle this, this paper presents a novel framework. First, it employs Mask R-CNN for instance segmentation of depth images captured by 3D cameras. Next, once the images of either a single broiler or multiple broilers are segmented, the extended artificial features and the learned features extracted by Customized Resnet50 (C-Resnet50) are fused by a feature fusion module. Finally, the fused features are adopted to estimate the body weight of each broiler employing gradient boosting decision tree (GBDT). By integrating diverse features with GBTD, the proposed framework can effectively obtain the broiler instance among many depth images of multiple broilers in the visual field despite the complex background. Experimental results show that this framework significantly boosts accuracy and robustness. With an MAE of 0.093 kg and an R<sup>2</sup> of 0.707 in a test set of 240 63-day-old bantam chicken images, it outperforms other methods. |
| first_indexed | 2024-03-09T01:55:29Z |
| format | Article |
| id | doaj.art-28e2d4d2d05e4bd689dbdba9a027ea7b |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-09T01:55:29Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-28e2d4d2d05e4bd689dbdba9a027ea7b2023-12-08T15:10:49ZengMDPI AGAnimals2076-26152023-12-011323372110.3390/ani13233721An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision TreeXiming Li0Jingyi Wu1Zeyong Zhao2Yitao Zhuang3Shikai Sun4Huanlong Xie5Yuefang Gao6Deqin Xiao7College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaWens Foodstuff Group Co., Ltd., Yunfu 527400, ChinaWens Foodstuff Group Co., Ltd., Yunfu 527400, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaBroiler weighing is essential in the broiler farming industry. Camera-based systems can economically weigh various broiler types without expensive platforms. However, existing computer vision methods for weight estimation are less mature, as they focus on young broilers. In effect, the estimation error increases with the age of the broiler. To tackle this, this paper presents a novel framework. First, it employs Mask R-CNN for instance segmentation of depth images captured by 3D cameras. Next, once the images of either a single broiler or multiple broilers are segmented, the extended artificial features and the learned features extracted by Customized Resnet50 (C-Resnet50) are fused by a feature fusion module. Finally, the fused features are adopted to estimate the body weight of each broiler employing gradient boosting decision tree (GBDT). By integrating diverse features with GBTD, the proposed framework can effectively obtain the broiler instance among many depth images of multiple broilers in the visual field despite the complex background. Experimental results show that this framework significantly boosts accuracy and robustness. With an MAE of 0.093 kg and an R<sup>2</sup> of 0.707 in a test set of 240 63-day-old bantam chicken images, it outperforms other methods.https://www.mdpi.com/2076-2615/13/23/3721broilerdepth imageinstance segmentationweight estimationgradient boosting decision tree |
| spellingShingle | Ximing Li Jingyi Wu Zeyong Zhao Yitao Zhuang Shikai Sun Huanlong Xie Yuefang Gao Deqin Xiao An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree Animals broiler depth image instance segmentation weight estimation gradient boosting decision tree |
| title | An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree |
| title_full | An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree |
| title_fullStr | An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree |
| title_full_unstemmed | An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree |
| title_short | An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree |
| title_sort | improved method for broiler weight estimation integrating multi feature with gradient boosting decision tree |
| topic | broiler depth image instance segmentation weight estimation gradient boosting decision tree |
| url | https://www.mdpi.com/2076-2615/13/23/3721 |
| work_keys_str_mv | AT ximingli animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT jingyiwu animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT zeyongzhao animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT yitaozhuang animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT shikaisun animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT huanlongxie animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT yuefanggao animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT deqinxiao animprovedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT ximingli improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT jingyiwu improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT zeyongzhao improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT yitaozhuang improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT shikaisun improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT huanlongxie improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT yuefanggao improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree AT deqinxiao improvedmethodforbroilerweightestimationintegratingmultifeaturewithgradientboostingdecisiontree |