Investigation of Pig Activity Based on Video Data and Semi-Supervised Neural Networks

Abstract

The activity level of pigs is an important stress indicator which can be associated to tail-biting, a major issue for animal welfare of domestic pigs in conventional housing systems. Although the consideration of the animal activity could be essential to detect tail-biting before an outbreak occurs, it is often manually assessed and therefore labor intense, cost intensive and impracticable on a commercial scale. Recent advances of semi- and unsupervised convolutional neural networks (CNNs) have made them to the state of art technology for detecting anomalous behavior patterns in a variety of complex scene environments. In this study we apply such a CNN for anomaly detection to identify varying levels of activity in a multi-pen problem setup. By applying a two-stage approach we first trained the CNN to detect anomalies in the form of extreme activity behavior. Second, we trained a classifier to categorize the detected anomaly scores by learning the potential activity range of each pen. We evaluated our framework by analyzing 82 manually rated videos and achieved a success rate of 91%. Furthermore, we compared our model with a motion history image (MHI) approach and a binary image approach using two benchmark data sets, i.e., the well established pedestrian data sets published by the University of California, San Diego (UCSD) and our pig data set. The results show the effectiveness of our framework, which can be applied without the need of a labor intense manual annotation process and can be utilized for the assessment of the pig activity in a variety of applications like early warning systems to detect changes in the state of health.

AI in Sustainable Pig Farming: IoT Insights into Stress and Gait

“…Stress in pigs can be evaluated by detecting physiological changes such as those recorded by the 3-in-1 sensor and alterations in behaviors inferred from accelerometer data. Some potential stress indicators include heart rate (HR), heart rate variability (HRV), breathing rate (BR), and changes in activity and posture [25][26][27][28]. Furthermore, parameters such as ECG amplitude, ECG noise, and galvanic skin response (GSR) can also signify increased stress levels.…”

Inovações no Reconhecimento e Detecção de Animais: Uma Análise da Literatura com Ênfase em Redes Neurais e Aprendizado de Máquina

“…Título do Artigo 1 [Hansen et al 2018] Towards on-farm pig face recognition using convolutional neural networks 2 [Taheri and Toygar 2018] Animal classification using images with score level fusion. 3 [Nasirahmadi et al 2019] Deep learning and machine vision approaches to individual pig posture detection 4 [Barbedo et al 2019] A Study on the Detection of Cattle in UAV Images Using Deep Learning 5 [Li et al 2019] Mounting Behaviour Recognition for Pigs Based on Deep Learning 6 [Shah et al 2019] Fish-Pak: Fish species dataset from Pakistan for visual features based classification 7 [Achour et al 2020] Image analysis for individual identification and feeding behaviour monitoring of dairy cows based on Convolutional Neural Networks (CNN) 8 [Chen et al 2020] Recognition of aggressive episodes of pigs based on convolutional neural network and long short-term memory 9 [Geffen et al 2020] A machine vision system to detect and count laying hens in battery cages 10 [Salau and Krieter 2020] Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting 11 [Wutke et al 2020] Investigation of Pig Activity Based on Video Data and Semi-Supervised Neural Networks 12 [Andersen et al 2021] Towards Machine Recognition of Facial Expressions of Pain in Horses 13 [Hansen et al 2021] Towards Facial Expression Recognition for On-Farm Welfare Assessment in Pigs 14 [de Silva et al 2022] Feasibility of using convolutional neural networks for individual identifcation of wild Asian elephants 15 [Teoh et al 2022] Deep learning for behaviour classification in a preclinical brain injury model…”

The Application of Cameras in Precision Pig Farming: An Overview for Swine-Keeping Professionals

“…An automatic monitoring system for identifying locomotion was proposed in earlier studies [ 27 , 91 ]. A new approach was introduced to monitor the pigs’ motions; object marking was conducted by an ellipse fitting method, whereas objects were extracted using Otsu’s threshold for further processing.…”