Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset

Bergamini, Luca; Pini, Stefano; Simoni, Alessandro; Vezzani, Roberto; Calderara, Simone; D’Eath, Richard B.; Fisher, Robert B.

doi:10.5220/0010288405240533

Cited by 18 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of detection failures made by an anchor‐based detector as shown by Bergamini et al. [11]. Orange arrows indicate failures…”

Section: Resultsmentioning

confidence: 99%

“…Bergamini et al. [11] used an anchor‐based detector in their study. Their dataset comprises twelve videos of a single pen with eight animals.…”

Section: Methodsmentioning

confidence: 99%

“…The experiments are conducted on two publicly available pig detection datasets: Bergamini et al. [11] and Psota et al [6]. Thus, we compare our proposed approach to an anchor‐based framework and an anchor‐free keypoint‐based framework.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An efficient anchor‐free method for pig detection

Mattina

Benzinou

Nasreddine

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Given the rapid growth of commercial pig farms, the need to automatically monitor pig behaviour becomes more important in order to assist farmers. Recent advances in convolutional neural networks may pave the way for new solutions. However, the primary task of individual pig detection under real‐world conditions is still a challenging task. Previous studies used anchor‐based frameworks that are unsuitable for such crowded scenarios with extreme overlapping. Furthermore, most applications focus on specific levels of brightness, farm facilities, or pig species without considering generalization. To tackle these problems, an anchor‐free pig detection method based on pig centre localization is first proposed. Then, a novel negative training data augmentation technique is introduced using examples from outside the training distribution. Furthermore, using the test time augmentation technique is proposed to improve the model performance. Experiments are conducted on two online pig detection datasets; the network surpasses state‐of‐the‐art results for both datasets. It is also found that the proposed method outperforms the latest anchor‐free techniques commonly used in crowded scenarios. The method can detect pigs individually, even if their bounding boxes overlap strongly or occlude each other. Moreover, the real‐time system achieves an improvement of 10% in Fmeasure$F_{\text{measure}}$ when testing in unconstrained real‐world conditions.

show abstract

“…Examples of detection failures made by an anchor‐based detector as shown by Bergamini et al. [11]. Orange arrows indicate failures…”

Section: Resultsmentioning

confidence: 99%

“…Bergamini et al. [11] used an anchor‐based detector in their study. Their dataset comprises twelve videos of a single pen with eight animals.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An efficient anchor‐free method for pig detection

Mattina

Benzinou

Nasreddine

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…This technological advancement allows farmers to measure and estimate stock density and behavioural patterns on an individual basis [44]. Deep and shallow vision technologies could also be implemented in the near future to help assess behavioural pattern changes, such as pecking, over time [45][46][47].…”

Section: Tracking and Stocking Density Estimationmentioning

confidence: 99%

Automated Tracking Systems for the Assessment of Farmed Poultry

Neethirajan¹

2022

Animals

View full text Add to dashboard Cite

The world’s growing population is highly dependent on animal agriculture. Animal products provide nutrient-packed meals that help to sustain individuals of all ages in communities across the globe. As the human demand for animal proteins grows, the agricultural industry must continue to advance its efficiency and quality of production. One of the most commonly farmed livestock is poultry and their significance is felt on a global scale. Current poultry farming practices result in the premature death and rejection of billions of chickens on an annual basis before they are processed for meat. This loss of life is concerning regarding animal welfare, agricultural efficiency, and economic impacts. The best way to prevent these losses is through the individualistic and/or group level assessment of animals on a continuous basis. On large-scale farms, such attention to detail was generally considered to be inaccurate and inefficient, but with the integration of artificial intelligence (AI)-assisted technology individualised, and per-herd assessments of livestock became possible and accurate. Various studies have shown that cameras linked with specialised systems of AI can properly analyse flocks for health concerns, thus improving the survival rate and product quality of farmed poultry. Building on recent advancements, this review explores the aspects of AI in the detection, counting, and tracking of poultry in commercial and research-based applications.

show abstract

“…This technological advancement allows farmers to measure and estimate stock density and behavioral patterns on an individual basis (Zhang et al, 2019). Deep and shallow vision technologies can also be implemented in near future to help assess behavioral pattern changes such as pecking over time (Bergamini et al, 2021).…”

Section: Tracking and Stocking Density Estimationmentioning

confidence: 99%

Automated Tracking Systems for the Assessment of Farmed Poultry

Neethirajan¹

2021

Preprint

View full text Add to dashboard Cite

The world's growing population is highly dependent on animal agriculture. Animal products provide nutrient-packed meals that help to sustain individuals of all ages in communities across the globe. As the human demand for animal proteins grows, the agricultural industry must continue to advance its efficiency and quality of production. One of the most commonly farmed livestock is poultry and their significance is felt on a global scale. Current poultry farming practices result in the premature death and rejection of billions of chickens on an annual basis before they are processed for meat. This loss of life is concerning regarding animal welfare, agricultural efficiency, and economic impacts. The best way to prevent these losses is through the individualistic and/or group level assessment of animal on a continuous basis. On large-scale farms, such attention to detail was generally considered to be inaccurate and inefficient, but with the integration of Artificial Intelligence (AI) assisted technology individualized and per-herd assessments of livestock are possible and accurate. Various studies have shown cameras linked with specialized systems of AI can properly analyze flocks for health concerns, thus improving the survival rate and product quality of farmed poultry. Building on the recent advancements, this review explores the aspects of AI in the detection, counting and tracking of the poultry in commercial and research-based applications.

show abstract

Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset

Cited by 18 publications

References 35 publications

An efficient anchor‐free method for pig detection

An efficient anchor‐free method for pig detection

Automated Tracking Systems for the Assessment of Farmed Poultry

Automated Tracking Systems for the Assessment of Farmed Poultry

Contact Info

Product

Resources

About