Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration
Posture changes in pigs during growth are often precursors of disease. Monitoring pigs’ behavioral activities can allow us to detect pathological changes in pigs earlier and identify the factors threatening the health of pigs in advance. Pigs tend to be farmed on a large scale, and manual observatio...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Animals |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-2615/11/5/1295 |
id |
doaj-1c7478fd323046c1a18021a5308a0f16 |
---|---|
record_format |
Article |
spelling |
doaj-1c7478fd323046c1a18021a5308a0f162021-04-30T23:05:21ZengMDPI AGAnimals2076-26152021-04-01111295129510.3390/ani11051295Pig-Posture Recognition Based on Computer Vision: Dataset and ExplorationHongmin Shao0Jingyu Pu1Jiong Mu2College of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaPosture changes in pigs during growth are often precursors of disease. Monitoring pigs’ behavioral activities can allow us to detect pathological changes in pigs earlier and identify the factors threatening the health of pigs in advance. Pigs tend to be farmed on a large scale, and manual observation by keepers is time consuming and laborious. Therefore, the use of computers to monitor the growth processes of pigs in real time, and to recognize the duration and frequency of pigs’ postural changes over time, can prevent outbreaks of porcine diseases. The contributions of this article are as follows: (1) The first human-annotated pig-posture-identification dataset in the world was established, including 800 pictures of each of the four pig postures: standing, lying on the stomach, lying on the side, and exploring. (2) When using a deep separable convolutional network to classify pig postures, the accuracy was 92.45%. The results show that the method proposed in this paper achieves adequate pig-posture recognition in a piggery environment and may be suitable for livestock farm applications.https://www.mdpi.com/2076-2615/11/5/1295computer visionposture recognitionpig postureagricultural automationautomated breeding |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hongmin Shao Jingyu Pu Jiong Mu |
spellingShingle |
Hongmin Shao Jingyu Pu Jiong Mu Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration Animals computer vision posture recognition pig posture agricultural automation automated breeding |
author_facet |
Hongmin Shao Jingyu Pu Jiong Mu |
author_sort |
Hongmin Shao |
title |
Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration |
title_short |
Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration |
title_full |
Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration |
title_fullStr |
Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration |
title_full_unstemmed |
Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration |
title_sort |
pig-posture recognition based on computer vision: dataset and exploration |
publisher |
MDPI AG |
series |
Animals |
issn |
2076-2615 |
publishDate |
2021-04-01 |
description |
Posture changes in pigs during growth are often precursors of disease. Monitoring pigs’ behavioral activities can allow us to detect pathological changes in pigs earlier and identify the factors threatening the health of pigs in advance. Pigs tend to be farmed on a large scale, and manual observation by keepers is time consuming and laborious. Therefore, the use of computers to monitor the growth processes of pigs in real time, and to recognize the duration and frequency of pigs’ postural changes over time, can prevent outbreaks of porcine diseases. The contributions of this article are as follows: (1) The first human-annotated pig-posture-identification dataset in the world was established, including 800 pictures of each of the four pig postures: standing, lying on the stomach, lying on the side, and exploring. (2) When using a deep separable convolutional network to classify pig postures, the accuracy was 92.45%. The results show that the method proposed in this paper achieves adequate pig-posture recognition in a piggery environment and may be suitable for livestock farm applications. |
topic |
computer vision posture recognition pig posture agricultural automation automated breeding |
url |
https://www.mdpi.com/2076-2615/11/5/1295 |
work_keys_str_mv |
AT hongminshao pigposturerecognitionbasedoncomputervisiondatasetandexploration AT jingyupu pigposturerecognitionbasedoncomputervisiondatasetandexploration AT jiongmu pigposturerecognitionbasedoncomputervisiondatasetandexploration |
_version_ |
1721497117165355008 |