• Title/Summary/Keyword: Pig Monitoring

Search Result 94, Processing Time 0.028 seconds

Development of Wearable Device for Monitoring Working Environment in Pig House (양돈장 작업환경 모니터링을 위한 웨어러블 장비개발)

  • Seo, Il-Hwan
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.62 no.1
    • /
    • pp.71-81
    • /
    • 2020
  • Enclosed pig house are creating an environment with high concentrations of gas and dust. Poor conditions in pig farms reduce pig weight and increase disease and accidents for livestock workers. In the pig house, the high concentration of harmful gas may cause asphyxiation accidents to workers and chronic respiratory disease by long-term exposure. As pig farm workers have been aging and feminized, the damage to the health of the harsh environment is getting serious, and real-time monitoring is needed to prevent the damage. However, most of the measuring devices related to humidity, harmful gas, and fine dust except temperature sensors are exposed to high concentrations of gas and dust inside pig house and are difficult to withstand for a long time. The purpose of this study is to develop an wearable based device to monitor the hazardous environment exposed to workers working in pig farms. Based on the field monitoring and previous researches, the measurement range and basic specifications of the equipment were selected, and wearable based device was designed in terms of utilization, economic efficiency, size and communication performance. Selected H2S and NH3 sensors showed the average error of 5.3% comparing to standard gas concentrations. The measured data can be used to manage the working environment according to the worker's location and to obtain basic data for work safety warning.

Accuracy Improvement of Pig Detection using Image Processing and Deep Learning Techniques on an Embedded Board (임베디드 보드에서 영상 처리 및 딥러닝 기법을 혼용한 돼지 탐지 정확도 개선)

  • Yu, Seunghyun;Son, Seungwook;Ahn, Hanse;Lee, Sejun;Baek, Hwapyeong;Chung, Yongwha;Park, Daihee
    • 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.

GAN-based Video Denoising for Robust Pig Detection System (GAN 기반의 영상 잡음에 강인한 돼지 탐지 시스템)

  • Bo, Zhao;Lee, Jonguk;Atif, Othmane;Park, Daihee;Chung, Yongwha
    • 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.

Individual Pig Detection using Fast Region-based Convolution Neural Network (고속 영역기반 컨볼루션 신경망을 이용한 개별 돼지의 탐지)

  • Choi, Jangmin;Lee, Jonguk;Chung, Yongwha;Park, Daihee
    • 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.

Real-Time Pig Segmentation for Individual Pig Monitoring in a Weaning Pig Room (이유자돈사에서 개별 돼지 모니터링을 위한 실시간 돼지 구분)

  • Ju, Miso;Baek, Hansol;Sa, Jaewon;Kim, Heegon;Chung, Yongwha;Park, Daihee
    • 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.

Accurate Pig Detection for Video Monitoring Environment (비디오 모니터링 환경에서 정확한 돼지 탐지)

  • Ahn, Hanse;Son, Seungwook;Yu, Seunghyun;Suh, Yooil;Son, Junhyung;Lee, Sejun;Chung, Yongwha;Park, Daihee
    • 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.

A study for implementation of monitoring system for genetic improvement of swine breeding stock (종돈개량 모니터링시스템에 대한 고찰)

  • Do, Chang-Hee;Yang, Chang-Beom;Choi, Jae-Gwan;Yang, Boh-Suk;Song, Hyung-Jun
    • Korean Journal of Agricultural Science
    • /
    • v.42 no.3
    • /
    • pp.215-222
    • /
    • 2015
  • This paper sketches the strategies and designs for monitoring system of swine genetic improvement. The system should reflect every side of pig production. The system leads us to assess the efficiency of pig production and the scope of the system includes not only nucleus, multiplying and commercial herds, but also packing and processing sectors. For more accurate statistics, data for this monitoring system must be collected from all above mentioned areas, but not by random sampling. Futhermore, data analysis results including seedstocks and distribution information of genetic trend should be included in the system. The schema of knowledge database system could be employed in the system. The monitoring system in the final destination would unify the systems derived from various sources and provide any solution in swine industry including pig breeding.

Pressure Monitoring System in Gastro-Intestinal Track (소화기관내의 압력 모니터링 시스템)

  • 김용인;박석호;김병규;박종오
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.10 no.11
    • /
    • pp.1089-1094
    • /
    • 2004
  • Diseases in the gastro-intestinal track are on an increasing trend. In order to diagnose a patient, the various signals of the digestive organ, such as temperature, pH, and pressure, can offer the helpful information. Among the above mentioned signals, we choose the pressure variation as a monitoring signal. The variation of a pressure signal of the gastro-intestinal track can offer the information of a digestive trouble or some clues of the diseases. In this paper, a pressure monitoring system for the digestive organs of a living pig is presented. This system concept is to transmit the measured biomedical signals from a transmitter in a living pig to wireless receiver that is positioned out of body. The integrated solution includes the following parts: (1) the swallow type pressure capsule, (2) the receiving set consisting of a receiver, decoder box, and PC. The merit of the proposed system if that the monitoring system can supply the precise and repeatable pressure in the gastro-intestinal track. In addition, the design of low power consumption enables it to keep sending reliable signals while the pressure capsule is working in the digestive organ. The subject of the study for the pressure monitoring system is in-vivo experiments for a living pig. We achieved the pressure tracings in digestive organs and verified the validity of system after several in-vivo tests using pressure monitoring system. As a result, we found each organ has its own characterized pressure fluctuation.

Development of an Early Diagnostic Device for African Swine Fever through Real-time Temperature Monitoring Ear-tags (RTMEs)

  • Taehyeun Kim;Minjong Hong;JungHwal Shin
    • Journal of Sensor Science and Technology
    • /
    • v.32 no.5
    • /
    • pp.275-279
    • /
    • 2023
  • Throughout the 20th century, the transition of pig farms from extensive to intensive commercial operations amplified the risk of disease transmission, particularly involving African swine fever (ASF). Real-time temperature monitoring systems have emerged as essential tools for early ASF diagnosis. In this paper, we introduce new real-time temperature monitoring ear tags (RTMEs) modeled after existing ear tag designs. Our crafted Pig-Temp platforms have three primary advantages. First, they can be effortlessly attached to pig ears, ensuring superior compatibility. Second, they enable real-time temperature detection, and the data can be displayed on a personal computer or smartphone application. Furthermore, they demonstrate excellent measurement accuracy, ranging from 98.9% to 99.8% at temperatures between 2.2 and 360℃. A linear regression approach enables fever symptoms associated with ASF to be identified within 3 min using RTMEs. The communication range extends to approximately 12 m (452 m2), enabling measurements from an estimated 75 to 2,260 pigs per gateway. These newly developed Pig-Temp platforms offer singifcant enhancement of early ASF detection.

Pressure Monitoring System in Gastro-Intestinal Tract

  • Kim, Byung-Kyu;Kim, Yong-In;Park, Suk-Ho;Jo, Jin-Ho;Park, Gwi-Tae
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2005.06a
    • /
    • pp.196-201
    • /
    • 2005
  • Diseases in the gastro-intestinal tract are on an increasing trend. In order to diagnose a patient, various signals of the digestive organ, such as temperature, pH, and pressure, can offer the helpful information. Among the above mentioned signals, we choose the pressure variation as a monitoring signal. The variation of a pressure signal of the gastro-intestinal tract can offer the information of a digestive trouble or some clues of the diseases. In this paper, a pressure monitoring system for the digestive organs of a living pig is presented. This is why a pig's gastro-intestinal tract is very similar as human's. This system concept is to transmit the measured biomedical signals from a transmitter in a living pig to a wireless receiver that is positioned out of body. The integrated solution includes the swallow type pressure capsule and the receiving set consisting of a receiver, decoder circuit. The merit of the proposed system is that the monitoring system can supply the precise and a durable characteristic to measure and to transmit a signal in the gastro-intestinal tract. We achieved the pressure tracings in digestive organs and verified the validity of system after several in-vivo tests using the pressure monitoring system. Through various experiments, we found each organ has its own characterized pressure fluctuation.

  • PDF