Instrumented pig gait analysis: State-of-the-art

Neťuková, Slávka; Duspivová, Tereza; Tesar, Jan; Bejtic, Martin; Baxa, Monika; Ellederová, Zdeňka; Szabó, Zoltán; Krupička, Radim

doi:10.1016/j.jveb.2021.06.006

Cited by 8 publications

(11 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Except for the last (crucial) step, all of this can be fully automated, and the whole workflow is readily available for precision livestock farming. Monitoring can happen automatically (as in Litten et al, 2003;Netukova et al, 2021), which reduces delay in identifying individuals in need of intervention. Multiple models can be tested in parallel: in the present test case, the “weight” and “size” models found LBW locomotion indistinguishable from the “normal” reference group, whereas the “age” model specifically identified those animals which likely experience a delay in locomotor development.…”

Section: Discussionmentioning

confidence: 99%

“…The workflow herein involved handling of the animals as a consequence of the research setting. However, note that the procedure could easily be automated for continuous data collection by a suitable pen arrangement (Meijer et al, 2014; Netukova et al, 2021; Stavrakakis et al,2014).…”

Section: Methodsmentioning

confidence: 99%

“…These animals have been subject to a variety of locomotor studies, including paradigms to test the effects of breed (Mirkiani et al, 2021), birth weight (Vanden Hole et al, 2018a, 2021, 2017), surface friction (von Wachenfelt et al, 2008), welfare (Guesgen and Bench, 2017), various pathologies (Abell et al, 2014; Benasson et al, 2020; LaVallee et al, 2020), and more ( cf . Netukova et al, 2021). Of particular interest has been the occurrence of a subset of individuals which are born with lower weight (LBW, low birth weight) than their “normal” (NBW) littermates.…”

Section: Introductionmentioning

confidence: 99%

“…These methods are high precision tools, but low through-put or expensive, some potentially invasive, and therefore not generally suitable for broad monitoring of farm animals. On the other hand, computational techniques are increasingly available to mine extensive data sets collected with sensors or cameras for diagnostically relevant signals (Gómez et al, 2021; Neethirajan, 2020; Netukova et al, 2021; Piñeiro et al, 2019; Wurtz et al, 2019). “Precision Lifestock Farming”, an application of integrated management systems, might be the desired economic model.…”

Section: Introductionmentioning

confidence: 99%

“…Kinematic measurements have enabled the inference of many aspects of the locomotion of domestic animals (e.g. Netukova et al, 2021; Qiao et al,2021; Schlageter-Tello et al, 2014; Serra Bragança et al, 2018); even individual recognition is possible in well-studied domestic species (e.g. Figueiredo et al, 2018; Patua et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Workflow for High Through-Put, High Precision Livestock Diagnostic Screening of Locomotor Kinematics

Mielke

Ginneken

Aerts

2022

Preprint

View full text Add to dashboard Cite

In the study of vertebrate locomotion, kinematic measures of gait, dynamic posture, and coordination often change when comparing subjects of different body mass, size, and age. Is it, conversely, possible to infer subject characteristics from the kinematic measures? For this study, piglets (Sus domesticus) were filmed from lateral perspective during their first ten hours of life, an age at which body mass and size have major consequences for survival. We then apply deep learning methods for point digitization (DeepLabCut), calculate joint angle profiles, and apply an information-preserving transfromation (Fourier series) to retrieve a multivariate kinematic data set. We train a probabilistic model to predict subject characteristics from kinematics. The model infers subject characteristics accurately for strides from piglets of normal birth weight (i.e. the category it was trained on), but surprisingly predicts the body mass and size of low birth weight piglets (which were left out of training, out-of-sample prediction) to be "normal". The discrepancies between prediction and observation confirm that dynamic posture and coordination are unaffected by lower birth weight and lower size, which is evidence that low birth weight does not imply locomotor deficits. However, the age of some (but not all) low birth weight individuals is underestimated, supporting the hypothesis that these piglets experience a delay in locomotor maturation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Workflow for High Through-Put, High Precision Livestock Diagnostic Screening of Locomotor Kinematics

Mielke

Ginneken

Aerts

2022

Preprint

View full text Add to dashboard Cite

show abstract

GANPose: Pose estimation of grouped pigs using a generative adversarial network

Wang¹,

Zhou²,

Yin³

et al. 2023

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Deep learning pose detection model for sow locomotion

de Paula,

de Sousa,

Sarmiento

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Lameness affects animal mobility, causing pain and discomfort. Lameness in early stages often goes undetected due to a lack of observation, precision, and reliability. Automated and non-invasive systems offer precision and detection ease and may improve animal welfare. This study was conducted to create a repository of images and videos of sows with different locomotion scores. Our goal is to develop a computer vision model for automatically identifying specific points on the sow's body. The automatic identification and ability to track specific body areas, will allow us to conduct kinematic studies with the aim of facilitating the detection of lameness using deep learning. The video database was collected on a pig farm with a scenario built to allow filming of sows in locomotion with different lameness scores. Two stereo cameras were used to record 2D videos images. Thirteen locomotion experts assessed the videos using the Locomotion Score System developed by Zinpro Corporation. From this annotated repository, computational models were trained and tested using the open-source deep learning-based animal pose tracking framework SLEAP (Social LEAP Estimates Animal Poses). The top-performing models were constructed using the LEAP architecture to accurately track 6 (lateral view) and 10 (dorsal view) skeleton keypoints. The architecture achieved average precisions values of 0.90 and 0.72, average distances of 6.83 and 11.37 in pixel, and similarities of 0.94 and 0.86 for the lateral and dorsal views, respectively. These computational models are proposed as a Precision Livestock Farming tool and method for identifying and estimating postures in pigs automatically and objectively. The 2D video image repository with different pig locomotion scores can be used as a tool for teaching and research. Based on our skeleton keypoint classification results, an automatic system could be developed. This could contribute to the objective assessment of locomotion scores in sows, improving their welfare.

show abstract

Instrumented pig gait analysis: State-of-the-art

Cited by 8 publications

References 60 publications

A Workflow for High Through-Put, High Precision Livestock Diagnostic Screening of Locomotor Kinematics

A Workflow for High Through-Put, High Precision Livestock Diagnostic Screening of Locomotor Kinematics

GANPose: Pose estimation of grouped pigs using a generative adversarial network

Deep learning pose detection model for sow locomotion

Contact Info

Product

Resources

About