Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network
The measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized b...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/7730 |
| _version_ | 1797577044473675776 |
|---|---|
| author | Zihao Liu Jingyi Hua Hongxiang Xue Haonan Tian Yang Chen Haowei Liu |
| author_facet | Zihao Liu Jingyi Hua Hongxiang Xue Haonan Tian Yang Chen Haowei Liu |
| author_sort | Zihao Liu |
| collection | DOAJ |
| description | The measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized by inefficiency and time consumption. On the other hand, it has the potential to induce heightened stress levels in pigs. This research introduces a hybrid 3D point cloud denoising approach for precise pig weight estimation. By integrating statistical filtering and DBSCAN clustering techniques, we mitigate weight estimation bias and overcome limitations in feature extraction. The convex hull technique refines the dataset to the pig’s back, while voxel down-sampling enhances real-time efficiency. Our model integrates pig back parameters with a convolutional neural network (CNN) for accurate weight estimation. Experimental analysis indicates that the mean absolute error (MAE), mean absolute percent error (MAPE), and root mean square error (RMSE) of the weight estimation model proposed in this research are 12.45 kg, 5.36%, and 12.91 kg, respectively. In contrast to the currently available weight estimation methods based on 2D and 3D techniques, the suggested approach offers the advantages of simplified equipment configuration and reduced data processing complexity. These benefits are achieved without compromising the accuracy of weight estimation. Consequently, the proposed method presents an effective monitoring solution for precise pig feeding management, leading to reduced human resource losses and improved welfare in pig breeding. |
| first_indexed | 2024-03-10T22:03:20Z |
| format | Article |
| id | doaj.art-668da9e7366f4e57bb1ae2a125cb9346 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:03:20Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-668da9e7366f4e57bb1ae2a125cb93462023-11-19T12:53:25ZengMDPI AGSensors1424-82202023-09-012318773010.3390/s23187730Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural NetworkZihao Liu0Jingyi Hua1Hongxiang Xue2Haonan Tian3Yang Chen4Haowei Liu5College of Engineering, Nanjing Agricultural University, Nanjing 210031, ChinaKey Laboratory of Breeding Equipment, Ministry of Agriculture and Rural Affairs, Nanjing 210031, ChinaCollege of Engineering, Nanjing Agricultural University, Nanjing 210031, ChinaKey Laboratory of Breeding Equipment, Ministry of Agriculture and Rural Affairs, Nanjing 210031, ChinaCollege of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, ChinaCollege of Engineering, Nanjing Agricultural University, Nanjing 210031, ChinaThe measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized by inefficiency and time consumption. On the other hand, it has the potential to induce heightened stress levels in pigs. This research introduces a hybrid 3D point cloud denoising approach for precise pig weight estimation. By integrating statistical filtering and DBSCAN clustering techniques, we mitigate weight estimation bias and overcome limitations in feature extraction. The convex hull technique refines the dataset to the pig’s back, while voxel down-sampling enhances real-time efficiency. Our model integrates pig back parameters with a convolutional neural network (CNN) for accurate weight estimation. Experimental analysis indicates that the mean absolute error (MAE), mean absolute percent error (MAPE), and root mean square error (RMSE) of the weight estimation model proposed in this research are 12.45 kg, 5.36%, and 12.91 kg, respectively. In contrast to the currently available weight estimation methods based on 2D and 3D techniques, the suggested approach offers the advantages of simplified equipment configuration and reduced data processing complexity. These benefits are achieved without compromising the accuracy of weight estimation. Consequently, the proposed method presents an effective monitoring solution for precise pig feeding management, leading to reduced human resource losses and improved welfare in pig breeding.https://www.mdpi.com/1424-8220/23/18/7730pig weight estimation3D sensorpoint cloud segmentationconvolutional neural network |
| spellingShingle | Zihao Liu Jingyi Hua Hongxiang Xue Haonan Tian Yang Chen Haowei Liu Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network Sensors pig weight estimation 3D sensor point cloud segmentation convolutional neural network |
| title | Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network |
| title_full | Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network |
| title_fullStr | Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network |
| title_full_unstemmed | Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network |
| title_short | Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network |
| title_sort | body weight estimation for pigs based on 3d hybrid filter and convolutional neural network |
| topic | pig weight estimation 3D sensor point cloud segmentation convolutional neural network |
| url | https://www.mdpi.com/1424-8220/23/18/7730 |
| work_keys_str_mv | AT zihaoliu bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork AT jingyihua bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork AT hongxiangxue bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork AT haonantian bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork AT yangchen bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork AT haoweiliu bodyweightestimationforpigsbasedon3dhybridfilterandconvolutionalneuralnetwork |