• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.31-56
• /
• 2024

Pig farming, a vital industry, necessitates proactive measures for early disease detection and crush symptom monitoring to ensure optimum pig health and safety. This review explores advanced thermal sensing technologies and computer vision-based thermal imaging techniques employed for pig disease and piglet crush symptom monitoring on pig farms. Infrared thermography (IRT) is a non-invasive and efficient technology for measuring pig body temperature, providing advantages such as non-destructive, long-distance, and high-sensitivity measurements. Unlike traditional methods, IRT offers a quick and labor-saving approach to acquiring physiological data impacted by environmental temperature, crucial for understanding pig body physiology and metabolism. IRT aids in early disease detection, respiratory health monitoring, and evaluating vaccination effectiveness. Challenges include body surface emissivity variations affecting measurement accuracy. Thermal imaging and deep learning algorithms are used for pig behavior recognition, with the dorsal plane effective for stress detection. Remote health monitoring through thermal imaging, deep learning, and wearable devices facilitates non-invasive assessment of pig health, minimizing medication use. Integration of advanced sensors, thermal imaging, and deep learning shows potential for disease detection and improvement in pig farming, but challenges and ethical considerations must be addressed for successful implementation. This review summarizes the state-of-the-art technologies used in the pig farming industry, including computer vision algorithms such as object detection, image segmentation, and deep learning techniques. It also discusses the benefits and limitations of IRT technology, providing an overview of the current research field. This study provides valuable insights for researchers and farmers regarding IRT application in pig production, highlighting notable approaches and the latest research findings in this field.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.215-223
• /
• 2016

To reduce huge losses in pig farms, weaning pigs with weak immune systems are required to be carefully supervised. Even if various researches have been performed for livestock monitoring environment, segmenting each pig from touching pigs is still entrenched as a difficult problem. In this paper, we propose a real-time segmentation method for moving pigs by using motion information in a 24-h video surveillance system. The experimental results with the videos obtained from a domestic pig farm illustrated the possibility for segmenting by using our proposed method in real-time.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.1
• /
• pp.6-9
• /
• 2000

The purpose of this study was to evaluate the effect of lower numbers of sperm $(3{\times}10^9)$ per dose liquid semen and type of semen used in artificial insemination (AI) on sow reproductive performance in subtropical area. Semen was supplied by two commercial AI centers. A total of 671 female pigs from seven farms were inseminated with either $3{\times}10^9$ or $5{\times}10^9$ sperm per dose. Two types of semen were used: heterospermic semen from two boars of the same breed and homospermic semen from a single boar. After insemination, conception rate, farrowing rate, total litter size, and number of dead piglets were recorded. The analysis of variance indicated that there was no significant effect of interactions between pig farm, type of semen, or number of sperm on any of the traits measured. There were significant differences in conception rate, farrowing rate, and total litter size among pig farms (p<0.05). The effect of number of sperm per dose liquid semen ($3{\times}10^9$ or $5{\times}10^9$) was not significant. Sows inseminated with homospermic semen showed significantly higher conception and farrowing rates but significantly lower total litter size (p<0.05). In conclusion, the number of sperm per dose liquid semen for AI could be lowered to $3{\times}10^9 $ without affecting reproductive performance in subtropical areas like Taiwan.

• Journal of Animal Environmental Science
• /
• v.20 no.1
• /
• pp.9-14
• /
• 2014

This survey was conducted to give the basic information for ventilation systems of weaned pig house to establish the acceptable ventilation system in Korea. A total of 11 farms were surveyed in this study and 1 more farm in each province was regionally selected. The general information, inlet and outlet ventilation system, alley in house, space allowance of weaned pigs and manure management were surveyed. Space allowance of weaned pig in 82% of surveyed farms met the legal standard. Side wall inlet and outlet ventilation system were 82% and 73% of surveyed farms, respectively. Moreover, 73% farms have alley in the pig house to control temperature of inlet air. In this survey, both planar slot and circular duct inlet system and side wall fan outlet system could be a favorable ventilation system in weaned pig house.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Journal of Wellbeing Management and Applied Psychology
• /
• v.6 no.2
• /
• pp.9-13
• /
• 2023

Purpose: In this study, we would like to make a technical proposal to solve the odor problem in pig houses. Through this, we would like to suggest an effective way to reduce the odor generated in the pig house as a solution to civil complaints. Research design, data and methodology: Conduct direct visits to pig farms where many civil complaints about bad odor occur, and identify the problems of each farm. Identify elements related to odor control, such as structure, facility, equipment, odor management method, and ventilation type. Through this, the technology to be applied to reduce odor and the solution to the odor problem are presented. Results: The results of major improvements are as follows: 1. Improvement of the structure of the barn or composting shed to an airtight type 2. Improvement of the pig manure treatment structure using the slope inside the barn 3. Establishment of ventilation and cooling systems 4. Automation of the mist spray system. Conclusions: As a result, as practical measures, sealing of facilities using winch curtains, construction of air conditioning systems using negative pressure ventilation, and management systems using AIoT systems were presented. It is judged that this study can be helpful in determining the grievances caused by civil complaints of tenant livestock farms and the direction of facility improvement in the future.

• Korean Journal of Veterinary Service
• /
• v.39 no.4
• /
• pp.211-219
• /
• 2016

For determining the prevalence of major enteric pathogens, clinical examination and etiological diagnosis were carried out on 75 Korean pig farms. Enteric disease-suspected signs were observed in 90.7% of the farms and the incidence and severity were higher in younger age groups of the pigs. Five of seven pathogens were detected in 375 fecal samples collected from the 75 farms, and the farm-level prevalence of porcine rotavirus group A (PoRVA), pathogenic Escherichia (E.) coli, Lawsonia (L.) intracelluraris, Salmonella spp., and Brachyspira (B.) hyodysenteriae was 54.7%, 54.7%, 16.0%, 10.7% and 2.7%, respectively. PoRVA was extensively infected in suckling and weaning pig groups. The prevalence of pathogenic E. coli was highest in suckling period, and after the period, it exhibited a tendency to decrease. Salmonella spp. and L. intracelluraris were detected in all feeding groups of pigs in a ratio of 1.3~6.7%. B. hyodysenteriae was detected in 1.3~2.7% of growing and fattening pig groups but not detected in suckling and weaning pig groups. At least one or more pathogens were detected in 30.1% of 375 fecal samples. Among these, 25.0% or 5.1% of cases were single or mixed infection. Enteric disease signs of the pigs were significantly co-related with the detection of PoRVA, pathogenic E. coli or Salmonella spp. (P<0.01) but not with L. intracelluraris or B. hyodysenteriae (P>0.05). Conclusively, it will be expected that these data obtained in this study are very useful for subsequent studies and prevention strategies for swine enteric disease in Korean pig farms.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.6
• /
• pp.898-906
• /
• 2014

The objective of this study was to investigate differences in the faecal microbial composition among Lantang, Bama, Erhualian, Meishan, Xiaomeishan, Duroc, Landrace, and Yorkshire sows and to explore the possible link of the pig breed with the gut microbial community. Among the sows, the Meishan, Landrace, Duroc, and Yorkshire sows were from the same breeding farm with the same feed. Fresh faeces were collected from three sows of each purebred breed for microbiota analysis and volatile fatty acid (VFA) determination. Denaturing gradient gel electrophoresis (DGGE) analysis revealed that samples from Bama, Erhualian, and Xiaomeishan sows, which from different farms, were generally grouped in one cluster, with similarity higher than 67.2%, and those from Duroc, Landrace, and Yorkshire sows were grouped in another cluster. Principal component analysis of the DGGE profile showed that samples from the foreign breeds and the samples from the Chinese indigenous breeds were scattered in two different groups, irrespective of the farm origin. Faecal VFA concentrations were significantly affected by the pig breed. The proportion of acetate was higher in the Bama sows than in the other breeds. The real-time PCR analysis showed that 16S rRNA gene copies of total bacteria, Firmicutes and Bacteroidetes were significantly higher in the Bama sows compared to Xiaomeishan and Duroc sows. Both Meishan and Erhualian sows had higher numbers of total bacteria, Firmicutes, Bacteroidetes and sulphate-reducing bacteria as compared to Duroc sows. The results suggest that the pig breed affects the composition of gut microbiota. The microbial composition is different with different breeds, especially between overseas breeds (lean type) and Chinese breeds (relatively obese type).

• Journal of Veterinary Clinics
• /
• v.33 no.2
• /
• pp.107-112
• /
• 2016

The objective of this study was to determine potential contributing factors associated with biosecurity level of farrow-to-finish pig farms and to develop a classification tree model to explore how these factors related to each other based on prediction model. To this end, the author analyzed data (n = 193) extracted from a cross-sectional study of 344 farrow-to-finish farms which was conducted between March and September 2014 aimed to explore swine disease status at farm level. Standardized questionnaires with information about basic demographical data and management practices were collected in each farm by on-site visit of trained veterinarians. For the classification of the data sets regarding biosecurity level as a dependent variable and predictor variables, Chi-squared Automatic Interaction Detection (CHAID) algorithm was applied for modeling classification tree. The statistics of misclassification risk was used to evaluate the fitness of the model in terms of prediction results. Categorical multivariate input data (40 variables) was used to construct a classification tree, and the target variable was biosecurity level dichotomized into low versus high. In general, the level of biosecurity was lower in the majority of farms studied, mainly due to the limited implementation of on-farm basic biosecurity measures aimed at controlling the potential introduction and transmission of swine diseases. The CHAID model illustrated the relative importance of significant predictors in explaining the level of biosecurity; maintenance of medical records of treatment and vaccination, use of dedicated clothing to enter the farm, installing fence surrounding the farm perimeter, and periodic monitoring of the herd using written biosecurity plan in place. The misclassification risk estimate of the prediction model was 0.145 with the standard error of 0.025, indicating that 85.5% of the cases could be classified correctly by using the decision rule based on the current tree. Although CHAID approach could provide detailed information and insight about interactions among factors associated with biosecurity level, further evaluation of potential bias intervened in the course of data collection should be included in future studies. In addition, there is still need to validate findings through the external dataset with larger sample size to improve the external validity of the current model.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1361-1370
• /
• 2016

To reduce huge losses in pig farms, weaning pigs with weak immune systems are required to be carefully supervised. Even if various researches have been performed for pig monitoring environment, segmenting each pig from touching-pigs is still entrenched as a difficult problem. In this paper, we propose a segmentation method for touching-pigs by using concave-points and edge information in a video surveillance system. Especially, we interpret the segmentation problem as a time-series analysis problem in order to identify the concave-points generated by touching-pigs. Based on the experimental results with the videos obtained from a domestic pig farm, we believe that the proposed method can accurately segment the touching-pigs.