Abstract
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−1) 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−1) 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−1); 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.
Highlights
The US egg industry is transitioning to alternative hen housing systems due to subpar bird welfare conditions in conventional cage housing systems
The objectives of this study were to (1) develop vision-based floor-egg detectors based on three Convolutional Neural Networks (CNNs), i.e. single shot detector (SSD), faster R-CNN, and region-based fully convolutional network (R-fully-convolutional network (FCN)); (2) compare the performance of the three CNN floor-egg detectors to detect floor eggs under a range of simulated CF environments and system settings; (3) evaluate performance of the optimal CNN floor-egg detector under different settings; and (4) assess the generalizability of the optimal CNN floor-egg detector under random settings
Three CNN floor-egg detectors were developed in this study and evaluated for their performance on floor egg detection based on a five-fold cross-validation strategy
Summary
The US egg industry is transitioning to alternative hen housing systems due to subpar bird welfare conditions in conventional cage housing systems. Cage-free (CF) housing systems are among the alternative systems that provide hens with larger living spaces and welfare enrichments, such as perches, nestboxes, and litter floor [1]. Floor eggs represent approximately 0.2–2% of daily egg production, even with proper animal training and management [4]. In some extreme cases (e.g., lack of training for nesting, accidental nestbox access restriction, etc.), floor eggs could exceed 5% of total egg production [3,4], translating to over 2500 daily floor eggs in a typical 50,000-hen CF house. Because floor eggs are directly contacted with litter/manure and exposed to hens, they may be contaminated and/or pecked by birds if not collected in a timely manner [5]. Floor eggs may induce egg Sensors 2020, 20, 332; doi:10.3390/s20020332 www.mdpi.com/journal/sensors
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.