We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree.
- Authors
Li, Ximing; Wu, Jingyi; Zhao, Zeyong; Zhuang, Yitao; Sun, Shikai; Xie, Huanlong; Gao, Yuefang; Xiao, Deqin
- Abstract
Simple Summary: In the broiler farming industry, accurately weighing broilers is essential. Camera-based weighing systems offer a solution without requiring expensive platform weighers. However, existing computer vision methods for estimating broiler weight are limited to young broilers and become less accurate as broilers age due to increased density and weight imbalance. To tackle this, a new approach is introduced in this paper. It uses a segmentation network (Mask R-CNN) with depth images captured by a 3D camera to isolate broilers. Artificial and learned features are combined using a feature fusion module, and these features are used to estimate broiler weight through gradient boosting decision trees (GBDT). The method excels in accurately estimating the weight of individual broilers within complex scenes and holds promise for enhancing broiler weight estimation methods. 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 R2 of 0.707 in a test set of 240 63-day-old bantam chicken images, it outperforms other methods.
- Subjects
DECISION trees; COMPUTER vision; VISUAL fields; THREE-dimensional imaging; CHICKENS; POULTRY growth; PERIMETRY; POULTRY farming
- Publication
Animals (2076-2615), 2023, Vol 13, Issue 23, p3721
- ISSN
2076-2615
- Publication type
Article
- DOI
10.3390/ani13233721