In search of the behavioural correlates of optical flow patterns in the automated assessment of broiler chicken welfare

Group level measures of welfare flocks have been criticized on the grounds that they give only average measures and overlook the welfare of individual animals. However, we here show that the group-level optical flow patterns made by broiler flocks can be used to deliver information not just about the flock averages but also about the proportion of individuals in different movement categories. Mean optical flow provides information about the average movement of the whole flock while the variance, skew and kurtosis quantify the variation between individuals. We correlated flock optical flow patterns with the behavior and welfare of a sample of 16 birds per flock in two runway tests and a water (latency-to-lie) test. In the runway tests, there was a positive correlation between the average time taken to complete the runway and the skew and kurtosis of optical flow on day 28 of flock life (on average slow individuals came from flocks with a high skew and kurtosis). In the water test, there was a positive correlation between the average length of time the birds remained standing and the mean and variance of flock optical flow (on average, the most mobile individuals came from flocks with the highest mean). Patterns at the flock level thus contain valuable information about the activity of different proportions of the individuals within a flock.

Download Full-text

Welfare at group and individual level: optical flow patterns of broiler chicken flocks are correlated with the behaviour of individual birds

10.1101/2021.01.19.427267 ◽

2021 ◽

Author(s):

Sabine Gebhardt-Henrich ◽

Ariane Stratmann ◽

Marian Stamp Dawkins

Keyword(s):

Optical Flow ◽

Broiler Chicken ◽

Animal Health ◽

Flow Patterns ◽

Broiler Meat ◽

Positive Correlation ◽

Individual Level ◽

Water Test ◽

The Mean ◽

To Come

AbstractGroup level measures of welfare such as the optical flow patterns made by broiler chicken flocks have been criticized on the grounds that they give only average measures and overlook the welfare of individual animals. However, we here show that by using the skew and kurtosis in addition to the mean, optical flow patterns can be used to deliver information not just about the flock average but also about the proportion of individuals in different movement categories. We correlated flock optical flow patterns with the behaviour of a sample of 16 birds per flock in two runway tests and a water (latency-to-lie) test. In the runway tests, there was a positive correlation between the time taken to complete the runway and the skew and kurtosis of optical flow on day 28 of flock life (slow individuals came from flocks with a high skew and kurtosis). In the water test, there was a positive correlation between the length of time the birds remained standing and the mean and variance of flock optical flow (the most mobile individuals came from flocks with the highest mean). Patterns at flock level thus contain valuable information about the welfare of the individuals that compose the flock.Simple SummaryTechnology on farms potentially brings benefits of improved animal health, welfare and productivity as well as reduction in disease, waste and environmental impact. However, it also raises public concern about the welfare of individual animals, particularly when applied to large groups such as broiler (meat) chickens. We here address this issue by showing that camera technology can both provide life-long continuous monitoring of the welfare of whole flocks and also give crucial information about the individuals making up the flock. The cameras detect variation between individuals and are also sensitive to birds moving abnormally. By testing birds individually, we show that slow-moving birds tended to come from flocks that moved slowly overall and showed large variation between individuals whereas fast-moving birds were more likely to come from more active flocks that moved more uniformly. Properly used, camera technology can thus monitor the welfare of flocks continuously throughout their lives while reflecting the behaviour of individual birds.

Download Full-text

Optical flow patterns in broiler chicken flocks as automated measures of behaviour and gait

Applied Animal Behaviour Science ◽

10.1016/j.applanim.2009.04.009 ◽

2009 ◽

Vol 119 (3-4) ◽

pp. 203-209 ◽

Cited By ~ 50

Author(s):

Marian Stamp Dawkins ◽

Hyoung-joo Lee ◽

Corri D. Waitt ◽

Stephen J. Roberts

Keyword(s):

Optical Flow ◽

Broiler Chicken ◽

Flow Patterns

Download Full-text

Detection of unusual optical flow patterns by multilevel hidden Markov models

Optical Engineering ◽

10.1117/1.3280284 ◽

2010 ◽

Vol 49 (1) ◽

pp. 017201 ◽

Cited By ~ 12

Author(s):

László Czúni

Keyword(s):

Optical Flow ◽

Hidden Markov Models ◽

Markov Models ◽

Hidden Markov ◽

Flow Patterns

Download Full-text

Relationships between Head-Shoulder Divergences and Sickness in a Virtual Environment

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/154193129804202102 ◽

1998 ◽

Vol 42 (21) ◽

pp. 1471-1475 ◽

Cited By ~ 3

Author(s):

Jennifer A. Ehrlich ◽

Michael J. Singer ◽

Robert C. Allen

Keyword(s):

Optical Flow ◽

Virtual Environments ◽

Virtual Environment ◽

Flow Patterns ◽

Time On Task ◽

The Relationship

Sickness is often experienced during exposure to virtual environments (VEs). Optical flow patterns may influence this VE sickness. We investigated the relationship between VE sickness and head-shoulder divergence angles while moving through a VE. The VE experience induced some level of VE sickness in all participants. Those not completing the study evidenced significantly more severe VE sickness symptoms than those completing it did. No relationships between head-shoulder divergence and sickness were revealed for experimental dropouts. However, significant correlations were found between several sickness measures and head-shoulder divergences for those completing the study. An interaction between head-shoulder divergence and time on task may exist.

Download Full-text

Early warning of footpad dermatitis and hockburn in broiler chicken flocks using optical flow, bodyweight and water consumption

Veterinary Record ◽

10.1136/vr.104066 ◽

2017 ◽

Vol 180 (20) ◽

pp. 499-499 ◽

Cited By ~ 14

Author(s):

M. S. Dawkins ◽

S. J. Roberts ◽

R. J. Cain ◽

T. Nickson ◽

C. A. Donnelly

Keyword(s):

Optical Flow ◽

Water Consumption ◽

Early Warning ◽

Broiler Chicken

Download Full-text

Topological Sparse Learning of Dynamic Form Patterns

Neural Computation ◽

10.1162/neco_a_00670 ◽

2015 ◽

Vol 27 (1) ◽

pp. 42-73 ◽

Cited By ~ 3

Author(s):

T. Guthier ◽

V. Willert ◽

J. Eggert

Keyword(s):

Optical Flow ◽

Spatial Configuration ◽

Learning Algorithm ◽

Human Action ◽

Flow Patterns ◽

Classification Performance ◽

Sparse Learning ◽

Expression Recognition ◽

Data Set ◽

Face Expression

Motion is a crucial source of information for a variety of tasks in social interactions. The process of how humans recognize complex articulated movements such as gestures or face expressions remains largely unclear. There is an ongoing discussion if and how explicit low-level motion information, such as optical flow, is involved in the recognition process. Motivated by this discussion, we introduce a computational model that classifies the spatial configuration of gradient and optical flow patterns. The patterns are learned with an unsupervised learning algorithm based on translation-invariant nonnegative sparse coding called VNMF that extracts prototypical optical flow patterns shaped, for example, as moving heads or limb parts. A key element of the proposed system is a lateral inhibition term that suppresses activations of competing patterns in the learning process, leading to a low number of dominant and topological sparse activations. We analyze the classification performance of the gradient and optical flow patterns on three real-world human action recognition and one face expression recognition data set. The results indicate that the recognition of human actions can be achieved by gradient patterns alone, but adding optical flow patterns increases the classification performance. The combined patterns outperform other biological-inspired models and are competitive with current computer vision approaches.

Download Full-text