Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection
The manual collection of eggs laid on the floor (or ‘floor eggs’) in cage-free (CF) laying hen housing is strenuous and time-consuming. Using robots for automatic floor egg collection offers a novel solution to reduce labor yet relies on robust egg detection systems. This study s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/2/332 |
| _version_ | 1818016004667604992 |
|---|---|
| author | Guoming Li Yan Xu Yang Zhao Qian Du Yanbo Huang |
| author_facet | Guoming Li Yan Xu Yang Zhao Qian Du Yanbo Huang |
| author_sort | Guoming Li |
| collection | DOAJ |
| description | The manual collection of eggs laid on the floor (or ‘floor eggs’) in cage-free (CF) laying hen housing is strenuous and time-consuming. Using robots for automatic floor egg collection offers a novel solution to reduce labor yet relies on robust egg detection systems. This study sought to develop vision-based floor-egg detectors using three Convolutional Neural Networks (CNNs), i.e., single shot detector (SSD), faster region-based CNN (faster R-CNN), and region-based fully convolutional network (R-FCN), and evaluate their performance on floor egg detection under simulated CF environments. The results show that the SSD detector had the highest precision (99.9 ± 0.1%) and fastest processing speed (125.1 ± 2.7 ms·image<sup>−1</sup>) but the lowest recall (72.1 ± 7.2%) and accuracy (72.0 ± 7.2%) among the three floor-egg detectors. The R-FCN detector had the slowest processing speed (243.2 ± 1.0 ms·image<sup>−1</sup>) and the lowest precision (93.3 ± 2.4%). The faster R-CNN detector had the best performance in floor egg detection with the highest recall (98.4 ± 0.4%) and accuracy (98.1 ± 0.3%), and a medium prevision (99.7 ± 0.2%) and image processing speed (201.5 ± 2.3 ms·image<sup>−1</sup>); thus, the faster R-CNN detector was selected as the optimal model. The faster R-CNN detector performed almost perfectly for floor egg detection under a wide range of simulated CF environments and system settings, except for brown egg detection at 1 lux light intensity. When tested under random settings, the faster R-CNN detector had 91.9−94.7% precision, 99.8−100.0% recall, and 91.9−94.5% accuracy for floor egg detection. It is concluded that a properly-trained CNN floor-egg detector may accurately detect floor eggs under CF housing environments and has the potential to serve as a crucial vision-based component for robotic floor egg collection systems. |
| first_indexed | 2024-04-14T07:05:50Z |
| format | Article |
| id | doaj.art-80c444e1e8594f6db513242f6a9838fc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T07:05:50Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-80c444e1e8594f6db513242f6a9838fc2022-12-22T02:06:33ZengMDPI AGSensors1424-82202020-01-0120233210.3390/s20020332s20020332Evaluating Convolutional Neural Networks for Cage-Free Floor Egg DetectionGuoming Li0Yan Xu1Yang Zhao2Qian Du3Yanbo Huang4Department of Agricultural and Biological Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Agricultural and Biological Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762, USAAgricultural Research Service, Crop Production Systems Research Unit, United States Department of Agriculture, Stoneville, MS 38776, USAThe manual collection of eggs laid on the floor (or ‘floor eggs’) in cage-free (CF) laying hen housing is strenuous and time-consuming. Using robots for automatic floor egg collection offers a novel solution to reduce labor yet relies on robust egg detection systems. This study sought to develop vision-based floor-egg detectors using three Convolutional Neural Networks (CNNs), i.e., single shot detector (SSD), faster region-based CNN (faster R-CNN), and region-based fully convolutional network (R-FCN), and evaluate their performance on floor egg detection under simulated CF environments. The results show that the SSD detector had the highest precision (99.9 ± 0.1%) and fastest processing speed (125.1 ± 2.7 ms·image<sup>−1</sup>) but the lowest recall (72.1 ± 7.2%) and accuracy (72.0 ± 7.2%) among the three floor-egg detectors. The R-FCN detector had the slowest processing speed (243.2 ± 1.0 ms·image<sup>−1</sup>) and the lowest precision (93.3 ± 2.4%). The faster R-CNN detector had the best performance in floor egg detection with the highest recall (98.4 ± 0.4%) and accuracy (98.1 ± 0.3%), and a medium prevision (99.7 ± 0.2%) and image processing speed (201.5 ± 2.3 ms·image<sup>−1</sup>); thus, the faster R-CNN detector was selected as the optimal model. The faster R-CNN detector performed almost perfectly for floor egg detection under a wide range of simulated CF environments and system settings, except for brown egg detection at 1 lux light intensity. When tested under random settings, the faster R-CNN detector had 91.9−94.7% precision, 99.8−100.0% recall, and 91.9−94.5% accuracy for floor egg detection. It is concluded that a properly-trained CNN floor-egg detector may accurately detect floor eggs under CF housing environments and has the potential to serve as a crucial vision-based component for robotic floor egg collection systems.https://www.mdpi.com/1424-8220/20/2/332floor eggconvolutional neural networktensorflowcage-freeevaluation |
| spellingShingle | Guoming Li Yan Xu Yang Zhao Qian Du Yanbo Huang Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection Sensors floor egg convolutional neural network tensorflow cage-free evaluation |
| title | Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection |
| title_full | Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection |
| title_fullStr | Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection |
| title_full_unstemmed | Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection |
| title_short | Evaluating Convolutional Neural Networks for Cage-Free Floor Egg Detection |
| title_sort | evaluating convolutional neural networks for cage free floor egg detection |
| topic | floor egg convolutional neural network tensorflow cage-free evaluation |
| url | https://www.mdpi.com/1424-8220/20/2/332 |
| work_keys_str_mv | AT guomingli evaluatingconvolutionalneuralnetworksforcagefreeflooreggdetection AT yanxu evaluatingconvolutionalneuralnetworksforcagefreeflooreggdetection AT yangzhao evaluatingconvolutionalneuralnetworksforcagefreeflooreggdetection AT qiandu evaluatingconvolutionalneuralnetworksforcagefreeflooreggdetection AT yanbohuang evaluatingconvolutionalneuralnetworksforcagefreeflooreggdetection |