Multi-object extraction from topview group-housed pig images based on adaptive partitioning and multilevel thresholding segmentation

Guo, Yizheng; Zhu, Weixing; Jiao, Pengpeng; Ma, Chenguang; Yang, Jianjun

doi:10.1016/j.biosystemseng.2015.05.001

Cited by 56 publications

(29 citation statements)

References 25 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, computer algorithms able to analyse RGB (red, green and blue) imagery to assess animal behaviour and liveweight among others [16,17] are being investigated as tools to assess health and welfare in pigs. Processing of RGB imagery has also been used for human monitoring, which has shown promising results when evaluating physiological parameters in people [18,19].…”

Section: Introductionmentioning

confidence: 99%

Remotely Sensed Imagery for Early Detection of Respiratory Disease in Pigs: A Pilot Study

Jorquera-Chavez

Fuentes

Dunshea

et al. 2020

Animals

View full text Add to dashboard Cite

Simple Summary: Respiratory disease in pigs causes suffering in infected animals and economic losses to producers. One of the most appropriate approaches to minimising these negative effects is by the early detection of infected animals. This pilot study aimed to use computer-based techniques to measure changes in temperature (eye and ear-base temperature), heart rate and respiration rate of pigs from thermal-infrared and conventional images. These measures, together with clinical observations, were obtained from pigs that were infected with Actinobacillus pleuropneumoniae (APP) and from pigs that were healthy. Infected pigs showed higher temperature and heart rate than healthy pigs across the period analysed. Respiration rate showed less difference between infected and healthy pigs. In addition, the biggest changes in these measures were recorded from six hours before the clinical observations identified sick animals. Results have highlighted that computer vision techniques can provide important and useable data regarding physiological changes that can indicate early signs of respiratory infection in pigs. This could aid the management of the disease, increasing the success of the treatment and decreasing the rate of severe cases and death.Abstract: Respiratory diseases are a major problem in the pig industry worldwide. Due to the impact of these diseases, the early identification of infected herds is essential. Computer vision technology, using RGB (red, green and blue) and thermal infrared imagery, can assist the early detection of changes in animal physiology related to these and other diseases. This pilot study aimed to identify whether these techniques are a useful tool to detect early changes of eye and ear-base temperature, heart rate and respiration rate in pigs that were challenged with Actinobacillus pleuropneumoniae. Clinical observations and imagery were analysed, comparing data obtained from animals that showed some signs of illness with data from animals that showed no signs of ill health. Highly significant differences (p < 0.05) were observed between sick and healthy pigs in heart rate, eye and ear temperature, with higher heart rate and higher temperatures in sick pigs. The largest change in temperature and heart rate remotely measured was observed around 4-6 h before signs of clinical illness were observed by the skilled technicians. These data suggest that computer vision techniques could be a useful tool to detect indicators of disease before the symptoms can be observed by stock people, assisting the early detection and control of respiratory diseases in pigs, promoting further research to study the capability and possible uses of this technology for on farm monitoring and management.

show abstract

Section: Introductionmentioning

confidence: 99%

Remotely Sensed Imagery for Early Detection of Respiratory Disease in Pigs: A Pilot Study

Jorquera-Chavez

Fuentes

Dunshea

et al. 2020

Animals

View full text Add to dashboard Cite

show abstract

“…Figure 5c shows the final result of boundaries detection. We also implemented the method proposed by Guo et al (2015), as shown in Figures 6 and 7…”

Section: Resultsmentioning

confidence: 99%

“…In the second step, we enhance the image using histogram equalization. This method is simple and effective for enhancing images with a large dynamic range (Guo et al, 2015). Afterwards, we segment the images with adaptive thresholding using an integral image (Bradley and Roth, 2007) with a window size of 250 x 250 pixels.…”

Section: Methodsmentioning

confidence: 99%

“…Several studies (Shao and Xin, 2008;Wang et al, 2008;Tu et al, 2013Tu et al, , 2014Guo et al, 2014Guo et al, , 2015Kashiha et al, 2014;Khoramshahi et al, 2014) have investigated boundary detection, identification, and behavior analysis of pigs from above (top-view) the pen. Research on the efficiency of methods for boundary detection of pigs is primarily to improve subsequent tasks, such as identifying pigs.…”

Section: Introductionmentioning

confidence: 99%

“…However, this method is computationally intensive (Tu et al, 2013;Guo et al, 2014). Guo et al (2015) developed a computationally less intensive method that uses only a single frame image; their method could detect pigs based on adaptive partitioning and multilevel thresholding segmentation (Guo et al, 2014). Yet, detecting pigs in images of a complex scene with high pen density remains a challenge (Kashiha et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Boundary Detection of Pigs in Pens Based on Adaptive Thresholding Using an Integral Image and Adaptive Partitioning

Buayai¹,

Kantanukul²,

Leung³

et al. 2017

CMUJNS

View full text Add to dashboard Cite

The seed of rice (Oryza sativa L.) from the highlands of northern Thailand, which is located within the species' centre of diversity, constitutes some of the world's last local rice germplasm still retained on-farm, provides local farmers and communities with a readily accessible resource, and is a source of value-adding traits for rice breeding. This paper reports on the germplasm represented by 281 seed samples collected in 2013 from an area of the highlands between latitudes 17.76°N to 20.18°N and longitudes 97.76°E to 100.48°E. The samples were provided by farmers belonging to 10 ethnicities, in number that closely correlated with the groups' share of the highland population (r = 0.84; P < 0.01). Compared with the slender grain rice of the lowlands, the highland germplasm was distinctive in its grain shape, and classed as large grain type in the husk, and medium grain type as de-husked, brown rice. The rice, which was predominantly of non-glutinous grain type and grown mainly as upland rice, had generally higher iron concentrations than rice in the lowlands; thus demonstrating how an on-farm rice germplasm may directly benefit local farmers and communities who consume the rice they grow. In addition, potential value-adding traits were identified in varieties and seed samples with the highest zinc density and novel rice with pigmented pericarp and high anti-oxidative capacity.

show abstract

Cow Behavior Recognition Using Motion History Image Feature

Ahn

Choi

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Multi-object extraction from topview group-housed pig images based on adaptive partitioning and multilevel thresholding segmentation

Cited by 56 publications

References 25 publications

Remotely Sensed Imagery for Early Detection of Respiratory Disease in Pigs: A Pilot Study

Remotely Sensed Imagery for Early Detection of Respiratory Disease in Pigs: A Pilot Study

Boundary Detection of Pigs in Pens Based on Adaptive Thresholding Using an Integral Image and Adaptive Partitioning

Cow Behavior Recognition Using Motion History Image Feature

Contact Info

Product

Resources

About