Automated detection and quantification of contact behaviour in pigs using deep learning

Alameer, Ali; Buijs, Stephanie; O’Connell, Niamh; Dalton, Luke; Larsen, Mona Lilian Vestbjerg; Pedersen, Lene Juul; Kyriazakis, Ι.

doi:10.1016/j.biosystemseng.2022.10.002

Cited by 14 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies has been linked this damaging behavior to high stocking density, poor environmental conditions, nutrient deficiency, sex, and age [74][75][76][77][78]. With increasing concern, there are several efforts have been executing to develop an AI for automatic detection and monitoring of biting behavior using computer vision [18,[79][80][81]. The current study demonstrated a potential application of microphones to monitor tail and ear biting by monitoring screaming sounds of pigs.…”

Section: Discussionmentioning

confidence: 76%

“…This can be possible if farmers are able to monitor the pigs 24 hours throughout their cycle. With this necessity, there is an increasing effort to develop artificial intelligence (AI) for automatic and real-time monitoring of behavior and health conditions of pigs [18][19][20][21][22][23][24]. Previous studies used either cameras or microphones for the detection of abnormalities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Monitoring System for Health Status and Behavior of Pigs Under Different Environmental Conditions Using Vision and Audio Technologies

Lagua,

Mun,

Ampode

et al. 2023

Preprint

View full text Add to dashboard Cite

This study aimed to assess the feasibility of employing audio and vision technologies as an integrated monitoring system to monitor the health and behavior of pigs under different environmental conditions and to associate these factors. A total of 81 growing pigs ((Landrace x Largewhite) x Duroc) with distinct weight categories (10.47 ± 2.57 kg and 28.81 ± 5.03 kg) were distributed into two distinct housing conditions: Control (characterized by low NH3 levels and low stocking density) and Treatment (marked by elevated NH3 levels and varying stocking densities). Each house was installed with a SoundTalks monitor for automated daily evaluation of respiratory health status (ReHS), and a camera with a microphone to facilitate manual tracking of respiratory symptoms and behavioral patterns. Results showed that the Treatment group encountered significantly high room temperature, NH3 concentration, and carbon dioxide levels, resulting in compromised growth performance—a phenomenon further exacerbated in high stocking density conditions. Pigs within the treatment exhibited increases (p &lt; 0.05) in lateral and total lying behaviors, and incidences of ear and tail injuries, increases screaming frequency, conjunctivitis incidences, coughing frequency, elevated respiration rates, and a decrease in ReHS. The environmental conditions affect the behavior and health of the pigs. Moreover, the behavioral patterns of the pigs are associated with their health conditions. The SoundTalks system did not trigger any warnings during the experimental period. Nevertheless, trend analysis indicated a significant reduction in respiratory health in the treatment. In conclusion, this study underscores the efficacy of merging audio and visual technologies to holistically monitor pig health and behavior, enabling enhanced management strategies. Findings emphasize that monitoring the ReHS trend serves as a pivotal marker for identifying respiratory health problems, complementing the system's innate alarm functions.

show abstract

Section: Discussionmentioning

confidence: 76%

Section: Introductionmentioning

confidence: 99%

A Comprehensive Monitoring System for Health Status and Behavior of Pigs Under Different Environmental Conditions Using Vision and Audio Technologies

Lagua,

Mun,

Ampode

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, efforts should also be made to improve the stress susceptibility of pigs through breeding. While this has so far been hampered by low or zero heritability [18], the development of biomarkers [51] and automated phenotyping (e.g., [52]) could be successful in the future.…”

Section: Discussionmentioning

confidence: 99%

Phenotypic link between protein efficiency and pig welfare suggests no apparent trade-offs for mitigating nitrogen pollution

Roch

Ewaoluwagbemiga

Kasper

2023

Preprint

View full text Add to dashboard Cite

Pig manure is a significant contributor to environmental pollution due to nitrogen compounds. While limiting protein in feed can mitigate this issue, this may result in damaging behaviors if the pigs’ nutritional needs are unmet. One long-term strategy to reduce nitrogen pollution is to breed pigs for higher protein efficiency (PE), but concerns were raised that this may negatively affect pig welfare. To investigate whether PE is related to impaired pig welfare, this study observed 95 non-tail-docked fattening pigs around 100 days old with a 20% protein restriction. Only three pigs were observed engaging in tail biting and manipulation of regions that are particularly vulnerable to injury, and none of these behaviors were associated with PE. Pigs with higher PE tended to initiate and win more confrontations than those with lower PE. We cannot confirm or exclude the influence of PE on the manipulation of pen mates’ less vulnerable regions. Such behaviors are normal and non-damaging per se, but can stress and injure pen mates if carried out excessively due to boredom or stress. Interestingly, increased engagement with straw was not associated with a reduction in potentially harmful behaviors, but we found a significant positive correlation. In conclusion, the study found no major behavioral abnormalities in pigs with higher PE. However, it highlights the importance of considering the potential trade-off between sustainability and welfare, reducing stress and providing adequate environmental enrichment to ensure the welfare of the pigs, especially if they are to become more efficient through breeding.

show abstract

“…Timeliness in detection is crucial for preventing further losses due to disease. Therefore, there is a growing effort to develop artificial intelligence (AI) systems for automatic health monitoring based on pig behavior, physiology, or vocalization (Alameer et al 2022;Matthews et al 2017;Shen et al 2022). Infected pigs exhibit elevated temperatures, heart rates, and respiration rates, which can be automatically detected using thermal infrared and RGB cameras (Jorquera-Chavez et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Monitoring using artificial intelligence reveals critical links between housing conditions and respiratory health in pigs

Lagua,

Mun,

Ampode

et al. 2024

J. Anim. Behav. Biometeorol.

View full text Add to dashboard Cite

Respiratory disease is the most significant issue in the pig industry and leads to high mortality and reduced growth rates. Housing conditions are crucial for maintaining the health and welfare of animals to optimize growth rates. This study aimed to evaluate the respiratory health status of pigs raised in different housing conditions using artificial intelligence (AI) technology and to determine the relationships between respiratory health and environmental factors. Eighty growing pigs (Largewhite × Landrace) × Duroc) were randomly distributed into two housing conditions: the control group, which had normal housing conditions, and the treatment group, which had poor housing conditions. A two-sample t test was performed to compare the groups, and a cross-correlation analysis was conducted to determine associations between respiratory health and days of exposure to environmental factors. The results show significant (p < 0.001) lower incidence of respiratory health status along with a significant (p < 0.001) greater frequency of coughing in pigs raised under poor housing conditions. Respiratory health is negatively associated with high exposure to temperature, relative humidity, and CO2 at lags 0 (R = -0.873, -0.887, and -0.869, respectively), -1 (R = -0.708, -0.742, and -0.705, respectively), and -2 (R = -0.545, -0.590, and -0.599, respectively). Furthermore, respiratory health was negatively associated with high exposure to NH3 (R = -0.420) at lag 0. In conclusion, AI technology is an effective tool for monitoring respiratory health. However, further evaluation and calibration of the alarm system threshold are recommended. These findings suggest that maintaining proper control of environmental factors can help prevent respiratory diseases in pigs.

show abstract

Automated detection and quantification of contact behaviour in pigs using deep learning

Cited by 14 publications

References 36 publications

A Comprehensive Monitoring System for Health Status and Behavior of Pigs Under Different Environmental Conditions Using Vision and Audio Technologies

A Comprehensive Monitoring System for Health Status and Behavior of Pigs Under Different Environmental Conditions Using Vision and Audio Technologies

Phenotypic link between protein efficiency and pig welfare suggests no apparent trade-offs for mitigating nitrogen pollution

Monitoring using artificial intelligence reveals critical links between housing conditions and respiratory health in pigs

Contact Info

Product

Resources

About