Usage of computer vision analysis for automatic detection of activity changes in sows during final gestation

Küster, Steffen; Kardel, Matthias; Ammer, Stefanie; Brünger, Johannes; Koch, Reinhard; Traulsen, Imke

doi:10.1016/j.compag.2019.105177

Cited by 19 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The example for diurnal evaluation of an individual sow suites the results of established studies well and shows great potential to identify the onset of farrowing or possible diseases, which can affect individual diurnal act out of behavior/postures. Like in previous work, a sow individual diurnal pattern needs to be taken into account to detect diseases or the onset of farrowing (Cornou and Lundbye-Christensen, 2012;Küster et al, 2020).…”

Section: Discussionmentioning

confidence: 99%

“…Approaches for single pigs can be found in the farrowing sector. E.g., the monitoring of the prenatal behavior of sows for the estimation of the onset of farrowing using natural given behavior deviations like nest-building and the varying amount of position changes before farrowing using 3D accelerometer or 2D pixel-movement (Pastell et al, 2016;Traulsen et al, 2018;Küster et al, 2020). More detailed approaches focused on inter birth interval and prevention of asphyxia as well as counting of piglets or the postpartum lying behavior of sows in regard to prevent piglet crushing and gathering information of nursing behavior from 2D-images (Yang et al, 2018) and 3D-depth images (Okinda et al, 2018;Zheng et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Behavior and Posture Detection of Sows in Loose Farrowing Pens Based on 2D-Video Images

Küster¹,

Nolte²,

Meckbach³

et al. 2021

Front. Anim. Sci.

Self Cite

View full text Add to dashboard Cite

The monitoring of farm animals and the automatic recognition of deviant behavior have recently become increasingly important in farm animal science research and in practical agriculture. The aim of this study was to develop an approach to automatically predict behavior and posture of sows by using a 2D image-based deep neural network (DNN) for the detection and localization of relevant sow and pen features, followed by a hierarchical conditional statement based on human expert knowledge for behavior/posture classification. The automatic detection of sow body parts and pen equipment was trained using an object detection algorithm (YOLO V3). The algorithm achieved an Average Precision (AP) of 0.97 (straw rack), 0.97 (head), 0.95 (feeding trough), 0.86 (jute bag), 0.78 (tail), 0.75 (legs) and 0.66 (teats). The conditional statement, which classifies and automatically generates a posture or behavior of the sow under consideration of context, temporal and geometric values of the detected features, classified 59.6% of the postures (lying lateral, lying ventral, standing, sitting) and behaviors (interaction with pen equipment) correctly. In conclusion, the results indicate the potential of DNN toward automatic behavior classification from 2D videos as potential basis for an automatic farrowing monitoring system.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Behavior and Posture Detection of Sows in Loose Farrowing Pens Based on 2D-Video Images

Küster¹,

Nolte²,

Meckbach³

et al. 2021

Front. Anim. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hence, the activity level of animals can be monitored from the frame-to-frame changes in the sum of the foreground pixels. This approach has been applied to detect activity changes in sows during final gestation [ 4 ]. However, it has never been used for estrus detection in cows.…”

Section: Introductionmentioning

confidence: 99%

Estrus Detection Using Background Image Subtraction Technique in Tie-Stalled Cows

Higaki

Horihata

Suzuki

et al. 2021

Animals

View full text Add to dashboard Cite

In this study, we determined the applicability of the background image subtraction technique to detect estrus in tie-stalled cows. To investigate the impact of the camera shooting direction, webcams were set up to capture the front, top, and rear views of a cow simultaneously. Video recording was performed for a total of ten estrous cycles in six cows. Standing estrus was confirmed by testing at 6 h intervals. From the end of estrus, transrectal ultrasonography was performed every 2 h to confirm ovulation time. Foreground objects (moving objects) were extracted in the videos using the background subtraction technique, and the pixels were counted at each frame of five frames-per-second sequences. After calculating the hourly averaged pixel counts, the change in values was expressed as the pixel ratio (total value during the last 24 h/total value during the last 24 to 48 h). The mean pixel ratio gradually increased at approximately 48 h before ovulation, and the highest value was observed at estrus, regardless of the camera shooting direction. When using front-view videos with an appropriate threshold, estrus was detected with 90% sensitivity and 50% precision. The present method in particular has the potential to be a non-contact estrus detection method for tie-stalled cows.

show abstract

“…Cang [11] and YOLO was applied by Sa et al for pig detection under various illumination conditions [12]. However, bounding boxes are not able to capture the contours of objects, which is why valuable information could be lost when only using bounding boxes [13]. For some PLF related use cases like the prediction of tail biting in grouped house pigs, this information could be insufficient.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Deep Learning Instance Segmentation Models for Pig Precision Livestock Farming

et al. 2021

View full text Add to dashboard Cite

In this paper, the deep learning instance segmentation architectures DetectoRS, SOLOv2, DETR and Mask R-CNN were applied to data from the field of Pig Precision Livestock Farming to investigate whether these models can address the specific challenges of this domain. For this purpose, we created a custom dataset consisting of 731 images with high heterogeneity and high-quality segmentation masks. For evaluation, the standard metric for benchmarking instance segmentation models in computer vision, the mean average precision, was used. The results show that all tested models can be applied to the considered domain in terms of prediction accuracy. With a mAP of 0.848, DetectoRS achieves the best results on the test set, but is also the largest model with the greatest hardware requirements. It turns out that increasing model complexity and size does not have a large impact on prediction accuracy for instance segmentation of pigs. DETR, SOLOv2, and Mask R-CNN achieve similar results to DetectoRS with a parameter count almost three times smaller. Visual evaluation of predictions shows quality differences in terms of accuracy of segmentation masks. DetectoRS generates the best masks overall, while DETR has advantages in correctly segmenting the tail region. However, it can be observed that each of the tested models has problems in assigning segmentation masks correctly once a pig is overlapped. The results demonstrate the potential of deep learning instance segmentation models in Pig Precision Livestock Farming and lay the foundation for future research in this area.

show abstract

Usage of computer vision analysis for automatic detection of activity changes in sows during final gestation

Cited by 19 publications

References 20 publications

Automatic Behavior and Posture Detection of Sows in Loose Farrowing Pens Based on 2D-Video Images

Automatic Behavior and Posture Detection of Sows in Loose Farrowing Pens Based on 2D-Video Images

Estrus Detection Using Background Image Subtraction Technique in Tie-Stalled Cows

Evaluation of Deep Learning Instance Segmentation Models for Pig Precision Livestock Farming

Contact Info

Product

Resources

About