No abstract

Manual observation and classification of animal behaviors is laborious, time-consuming, and of limited ability to process large amount of data. A computer vision-based system was developed that automatically recognizes sow behaviors (lying, sitting, standing, kneeling, feeding, drinking, and shifting) in farrowing crate. The system consisted of a low-cost 3D camera that simultaneously acquires digital and depth images and a software program that detects and identifies the sow's behaviors. This paper describes the computational algorithm for the analysis of depth images and presents its performance in recognizing the sow's behaviors as compared to manual recognition. The images were acquired at 6 s intervals on three days of a 21-day lactation period. Based on analysis of the 6 s interval images, the algorithm had the following accuracy of behavioral classification: 99.9% in lying, 96.4% in sitting, 99.2% in standing, 78.1% in kneeling, 97.4% in feeding, 92.7% in drinking, and 63.9% in transitioning between behaviors. The lower classification accuracy for the transitioning category presumably stemmed from insufficient frequency of the image acquisition which can be readily improved. Hence the reported system provides an effective way to automatically process and classify the sow's behavioral images. This tool is conducive to investigating behavioral responses and time budget of lactating sows and their litters to farrowing crate designs and management practices. RightsWorks produced by employees of the U.S. Government as part of their official duties are not copyrighted within the U.S. The content of this document is not copyrighted. b s t r a c tManual observation and classification of animal behaviors is laborious, time-consuming, and of limited ability to process large amount of data. A computer vision-based system was developed that automatically recognizes sow behaviors (lying, sitting, standing, kneeling, feeding, drinking, and shifting) in farrowing crate. The system consisted of a low-cost 3D camera that simultaneously acquires digital and depth images and a software program that detects and identifies the sow's behaviors. This paper describes the computational algorithm for the analysis of depth images and presents its performance in recognizing the sow's behaviors as compared to manual recognition. The images were acquired at 6 s intervals on three days of a 21-day lactation period. Based on analysis of the 6 s interval images, the algorithm had the following accuracy of behavioral classification: 99.9% in lying, 96.4% in sitting, 99.2% in standing, 78.1% in kneeling, 97.4% in feeding, 92.7% in drinking, and 63.9% in transitioning between behaviors. The lower classification accuracy for the transitioning category presumably stemmed from insufficient frequency of the image acquisition which can be readily improved. Hence the reported system provides an effective way to automatically process and classify the sow's behavioral images. This tool is conducive to investigating behavioral responses an...

No abstract

No abstract

Enriched colony housing (ECH) is a relatively new egg production system. As such, information is lacking on design parameters to ensure the well-being of the hens and optimal utilization of housing resources. A new system has been developed at Iowa State University that enables automated monitoring and quantification of feeding and nesting behaviors of individual hens in ECH. Ultra-high-frequency radio frequency identification (UHF RFID) is employed to track individual animals. The UHF RFID system consists of four components: antennas, tags, readers, and a data acquisition system. The antennas for monitoring feeding behavior are placed inside the two feed troughs and covered with plastic boards. Each feed trough has six antennas aligned in series covering the length of the feeder. Four additional antennas are placed inside the nest boxes to monitor the nesting behaviors. All 16 antennas are connected to five 4-channel readers, two per feed trough and one for the nest boxes, that are further connected to the hosting computer via Ethernet. Feed and water consumption and egg production are continuously monitored using load cells. This article describes the development and testing of the RFID system for monitoring feeding and nesting behaviors and provides sample data. The system has proven to be able to characterize benchmark feeding and nesting behaviors of individual hens in ECH, such as daily time spent at the feeder and in the nest box, daily frequency of visiting the feeder and the nest box, number of hens feeding and nesting simultaneously, and variability in these behaviors among individual hens. Future applications of the system include assessing the impact of resource allocation and management practices on feeding and nesting behaviors and on the well-being of the hens. This information will provide a scientific basis for optimal design and management of alternative hen housing systems.