• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• 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.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 Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.216-224
• /
• 2017

Abnormal situation caused by aggressive behavior of pigs adversely affects the growth of pigs, and comes with an economic loss in intensive pigsties. Therefore, IT-based video surveillance system is needed to monitor the abnormal situations in pigsty continuously in order to minimize the economic demage. Recently, some advances have been made in pig monitoring; however, detecting each pig is still challenging problem. In this paper, we propose a new color image-based monitoring system for the detection of the individual pig using a fast region-based convolution neural network with consideration of detecting touching pigs in a crowed pigsty. The experimental results with the color images obtained from a pig farm located in Sejong city illustrate the efficiency of the proposed method.

• Journal of Veterinary Science
• /
• v.19 no.6
• /
• pp.855-857
• /
• 2018

Porcine parvovirus 7 (PPV7) was first detected in Korean pig farms in 2017. The detection rate of PPV7 DNA was 24.0% (30/125) in aborted pig fetuses and 74.9% (262/350) in finishing pigs, suggesting that PPV7 has circulated among Korean domestic pig farms. Phylogenetic analysis based on capsid protein amino acid sequences demonstrated that the nine isolated Korean strains (PPV-KA1-3 and PPV-KF1-6) were closely related to the previously reported USA and Chinese PPV7 strains. In addition, the Korean strains exhibit genetic diversity with both insertion and deletion mutations. This study contributes to the understanding of the molecular epidemiology of PPV7 in Korea.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.700-703
• /
• 2021

Infrared cameras are widely used in recent research for automatic monitoring the abnormal behaviors of the pig. However, when deployed in real pig farms, infrared cameras always get polluted due to the harsh environment of pig farms which negatively affects the performance of pig monitoring. In this paper, we propose a real-time noise-robust infrared camera-based pig automatic monitoring system to improve the robustness of pigs' automatic monitoring in real pig farms. The proposed system first uses a preprocessor with a U-Net architecture that was trained as a GAN generator to transform the noisy images into clean images, then uses a YOLOv5-based detector to detect pigs. The experimental results show that with adding the preprocessing step, the average pig detection precision improved greatly from 0.639 to 0.759.

• International Journal of Oral Biology
• /
• v.36 no.2
• /
• pp.79-82
• /
• 2011

The aim of this study was to develop Prevotella intermedia ATCC 49046-specific PCR primers designed based on the nucleotide sequence of a DNA probe Pig28. The strainspecificity of the PCR primers, Pig28-F1/Pig28-R1, was confirmed with 9 strains of P. intermedia and 25 strains (15 species) of Prevotella species. The detection limit of the PCR primers was 2 pg of the purified genomic DNA of P. intermedia ATCC 49046. These PCR primers were found to be useful for identifying P. intermedia ATCC 49046, particularly for determining the authenticity of the strain.

• Korean Journal of Veterinary Service
• /
• v.22 no.4
• /
• pp.371-375
• /
• 1999

Total 1,434 sera collected from 72 pig farms were tested for the detection of porcine reproductive and respiratory syndrome (PRRS) virus antibodies. The overall seroprevalence of PRRS virus antibodies was 49.3% (707/727). Of 72 farms tested 59 (81.9%) farms had at least one or more than one pigs with PRRS virus antibodies. The seroprevalence of PRRS virus antibody varied with age. Seroprevalence of PRRS virus antibody in 1 to 30-day-old, 31 to 40-day-old, 41 to 50-day-old, 51 to 60-day-old, and over 61-day-old pig were 27.4%, 52.3%, 57.9%, 52.7%, and 68.2%, respectively. Gilt showed relatively higher seroprevalence (61.2%) than sow (29.2%) and boar (38.3%). In most farms, the infection of PRRS virus was chronic and confined to grower or finisher. This pattern of infection suggests that partial depopulation of the infected herds appears be one of the measures to eradicate the PRRS virus infection. High seroprevalence of the PRRS virus antibody in gilts and boars indicates that the infected gilts and boars in the breeding farms are the major source of the PRRS virus infection, and also play an important role in spreading the PRRS virus between fan mates or herds.

• Korean Journal of Veterinary Research
• /
• v.29 no.4
• /
• pp.567-575
• /
• 1989

This study was conducted to evaluate the possibility of application of a microenzyme-linked immunosorbent assay(micro-ELISA) for the serodiagnosis of specific toxoplasma antibodies in swine sera and this test was performed as a microplate system by coating the polystyrene plates with toxoplasma soluble antigen, incubated serially diluted sera, then added horse radish peroxidase labelled goat anti-swine IgG(r) conjugate followed by o-phenylenediamine as substrate. The color development by enzyme-substrate reaction was determined by the photometric reading [ELISA reader at 490nm (OD)] and visual reading. The soluble antigen was prepared from the tachyzoites in mouse peritoneal cavity. A total of 1,200 swine sera from pig slaughter-house and a total of 116 swine sera from pig breeding station (S-C farm) were tested for the detection of antibodies to Toxoplasma gondii. The results obtained were summarized as follows: 1. The optimal reactions of indirect ELISA for the test sera were determined by the dilution of antigen 1:256 and 1:3,200 of horse radish peroxidase conjugate [anti-swine IgG(r)]. 2. The specific togoplasma antibody(IgG) in pigs infected with Tp artificially were detected as the serum titers of 1:64 or 1:128 at one week postinfection. 3. Of a total of 1,200 swine sera from pig slaughter-house 505 samples of sera were detected as positive (42.1%) and of a total of 116 swine sera from S-C pig breeding station 68 samples of sera as positive (58.6%). 4. The specific antibody(IgG) detection rates against a total of 1,200 test sera from pig slaughter-house were not significant between male (43.1%) and female (40.7%). 5. The indirect ELISA was proved to be a sensitive and specific procedure for the serodiagnosis of swine toxoplasmosis and also evaluated as an effective screening test for the large scale of test samples in laboratory.

• Korean Journal of Veterinary Service
• /
• v.45 no.2
• /
• pp.87-99
• /
• 2022

A novel porcine circovirus 4 (PCV4) was recently emerged in Chinese and Korean pig herds, which provided epidemiological situation where three pathogenic PCVs, PCV2, PCV3, and newly emerged PCV4, could co-infect pig herds in these countries. In this study, a new triplex quantitative real-time polymerase chain reaction (tqPCR) method was developed for the rapid and differential detection of these viruses. The assay specifically amplified each viral capsid gene, whereas no other porcine pathogenic genes were detected. The detection limit of the assay was below 10 copies/µL and the assay showed high repeatability and reproducibility. In the clinical evaluation using 1476 clinical samples from 198 Korean pig farms, the detection rates of PCV2, PCV3 and PCV4 by the tqPCR assay were 13.8%, 25.4%, and 3.8%, respectively, which were 100% agreement with those of previously reported monoplex qPCR assays for PCV2, PCV3, and PCV4, with a κ value (95% CI) of 1 (1.00~1.00). The prevalence of PCV2, PCV3, and PCV4 at the farm levels were 46.5%, 63.6%, and 19.7%, respectively. The co-infection analysis for tested pig farms showed that single infection rates for PCV2, PCV3, and PCV4 were 28.8%, 44.4%, and 9.6%, respectively, the dual infection rates of PCV2 and PCV3, PCV2 and PCV4, and PCV3 and PCV4 were 12.6%, 3.5%, and 5.1%, respectively, and the triple infection rate for PCV2, PCV3, and PCV4 was 1.5%. These results demonstrate that three pathogenic PCVs are widely spread, and their co-infections are common in Korean pig herds, and the newly developed tqPCR assay will be useful for etiological and epidemiological studies of these pathogenic PCVs.