A new approach for categorizing pig lying behaviour based on a Delaunay triangulation method

Nasirahmadi, Abozar; Hensel, Oliver; Edwards, Sandra A.; Sturm, Barbara

doi:10.1017/s1751731116001208

Cited by 59 publications

(40 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No differences were found when the data set included only morning and evening observations. A more frequent recording of the lying behavior in future studies, for example, with automatic image/video analysis, could give more detailed and dense information on the pig behavior and short-term changes [23].…”

Section: Discussionmentioning

confidence: 99%

Influence of Increased Light Intensity on the Acceptance of a Solid Lying Area and a Slatted Elimination Area in Fattening Pigs

Opderbeck

Keßler²,

Gordillo³

et al. 2020

Agriculture

View full text Add to dashboard Cite

Animal welfare labels have been introduced to improve housing conditions in conventional pig systems. Animal welfare should be increased by, e.g. offering a well-accepted and comfortable solid lying area. This study investigates the effect of bright light from an LED spotlight in the slatted area on lying and elimination behavior of fattening pigs. It was tested for two pen designs different in feeder and arrangement of the slatted area with 18 pigs per pen. The study took place in two different compartments (spatial repetition) with two pens of each pen design. The light intensity in the slatted area was increased by two spotlights within one pen of each design as case-control approach. A total of 648 fattening pigs were tested over four and five fattening periods respectively. The lying behavior was assessed by video scan sampling at three different weekdays at three times (morning, noon, evening) on each observation day. On average, the lying area was used by 60–63% of the pigs in the control pens and 67–69% in the spotlight pens. Additionally, a tendential effect of the deviation of the room temperature from the set temperature existed. The fouling of the animals and pen was not affected by the light intensity.

show abstract

Section: Discussionmentioning

confidence: 99%

Influence of Increased Light Intensity on the Acceptance of a Solid Lying Area and a Slatted Elimination Area in Fattening Pigs

Opderbeck

Keßler²,

Gordillo³

et al. 2020

Agriculture

View full text Add to dashboard Cite

show abstract

“…For previous research on identification, References [11,16-18, 20-22,24-26,29,31,38,44-48] for detection and References [10,19,37,39,45] for tracking exist. In addition, previous studies for early detection of abnormalities exist as various topics, including research on the movement of pigs [17,62], research on aggressive behavior of pigs [63,64], research on attitude change [16,22,23,31,32,34,35,40,46], research on mounting behavior [21], research on low-growth pig's behavior [49], research on pig weight [29,33,38] and research on the density of pigs [9,11].…”

Section: Introductionmentioning

confidence: 99%

EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations

et al. 2020

View full text Add to dashboard Cite

Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been reported. Since low-cost embedded boards have more limited computing power than typical PCs and have tradeoffs between execution speed and accuracy, achieving fast and accurate detection of individual pigs for “on-device” pig monitoring applications is very challenging. Therefore, in this paper, we propose a method for the fast detection of individual pigs by reducing the computational workload of 3 × 3 convolution in widely-used, deep learning-based object detectors. Then, in order to recover the accuracy of the “light-weight” deep learning-based object detector, we generate a three-channel composite image as its input image, through “simple” image preprocessing techniques. Our experimental results on an NVIDIA Jetson Nano embedded board show that the proposed method can improve the integrated performance of both execution speed and accuracy of widely-used, deep learning-based object detectors, by a factor of up to 8.7.

show abstract

“…Currently, various vision based algorithms have been developed to recognize various behaviors of pig. For analyzing lying behavior, ellipse fitting and Delaunay triangulation feature were utilized in the pig group [1]. The modified angle histogram was established according to the optical flow direction for detecting motoring behavior [2].…”

Section: Introductionmentioning

confidence: 99%

A Spatiotemporal Convolutional Network for Multi-Behavior Recognition of Pigs

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

The statistical data of different kinds of behaviors of pigs can reflect their health status. However, the traditional behavior statistics of pigs were obtained and then recorded from the videos through human eyes. In order to reduce labor and time consumption, this paper proposed a pig behavior recognition network with a spatiotemporal convolutional network based on the SlowFast network architecture for behavior classification of five categories. Firstly, a pig behavior recognition video dataset (PBVD-5) was built by cutting short clips from 3-month non-stop shooting videos, which was composed of five categories of pig's behavior: feeding, lying, motoring, scratching and mounting. Subsequently, a SlowFast network based spatiotemporal convolutional network for the pig's multi-behavior recognition (PMB-SCN) was proposed. The results of the networks with variant architectures of the PMB-SCN were implemented and the optimal architecture was compared with the state-of-the-art single stream 3D convolutional network in our dataset. Our 3D pig behavior recognition network showed a top-1 accuracy of 97.63% and a views accuracy of 96.35% on the test set of PBVD and a top-1 accuracy of 91.87% and a views accuracy of 84.47% on a new test set collected from a completely different pigsty. The experimental results showed that this network provided remarkable ability of generalization and possibility for the subsequent pig detection and behavior recognition simultaneously.

show abstract

A new approach for categorizing pig lying behaviour based on a Delaunay triangulation method

Cited by 59 publications

References 30 publications

Influence of Increased Light Intensity on the Acceptance of a Solid Lying Area and a Slatted Elimination Area in Fattening Pigs

Influence of Increased Light Intensity on the Acceptance of a Solid Lying Area and a Slatted Elimination Area in Fattening Pigs

EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations

A Spatiotemporal Convolutional Network for Multi-Behavior Recognition of Pigs

Contact Info

Product

Resources

About