• Journal of Biosystems Engineering
• /
• 제32권3호
• /
• pp.173-178
• /
• 2007

This research was conducted to develop and analyze a wireless monitoring system for judging if sick or dead layers (SDL) exist in multi-tier layers battery (MLB) by machine vision, and to evaluate the performance between a wired monitoring system and it. This study used the AP (Access Point), the RS-285 to RS-232 converter, RS-232 to Ethernet converter, PICBASIC board and upgraded lump image processing method to change wired monitoring system into wireless monitoring system. The system was tested at a pilot farm and farm layer house. Results showed that monitoring judgement success rate at a pilot farm on normal cage (without SDL) was 82.3% and that on abnormal cage (with SDL) was 87.5%, respectively. And communication performance test results showed at farm layer house was $700{\sim}900$ kbps while equipments operated. There were dropped slightly than performance of wired monitoring system, however, the quantity was too small to make a significant difference of performance of the controling system developed for wireless communication.

• Journal of Biosystems Engineering
• /
• 제31권5호
• /
• pp.436-442
• /
• 2006

This research was conducted to design and develop a wired monitoring system for judging if sick or dead layers (SDL) exist in multi-tier layers battery (MLB) by machine vision, and to analyze its performance. In this study, 20 Brown Leghorn (Hi-Brown) layers aged 37 weeks old, were used as the experimental animals. The intensity of concern paid by layers on feed was over 90% during 5 minutes and 30 seconds after providing feed, and normal layers (NL) had been standing to take feed for that period. Therefore, in this study, the optimal judging time was set by this test result. The wired monitoring system developed was consisted of a driving device for carrying machine vision systems, a control program, a RS232 to RS485 convertor, an automatic positioning system, and an image capture system. An image processing algorithm was developed to find SDL in MLB by the processes of binary processing, erosion, expansion, labeling, and reckoning central coordinate of the captured images. The optimal velocity for driving unit was set up as 0.13 m/s by the test results for wired monitoring system, and the proximity switch was controlled not to be operated for 1.0 second after first image captured. The wired monitoring system developed was tested to evaluate the remote monitoring performance at lab-scale laying hen house. Results showed that its judgement success.ate on normal cage (without SDL) was 87% and that on abnormal cage (with SDL) was 90%, respectively. Therefore, it would be concluded that the wired monitoring system developed in this study was well suited to the purpose of this study.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2005년도 하계 학술대회 논문집
• /
• pp.273-279
• /
• 2005

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2005년도 하계 학술대회 논문집
• /
• pp.280-288
• /
• 2005

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2006년도 하계 학술대회 논문집
• /
• pp.250-256
• /
• 2006

• 한국축산시설환경학회지
• /
• 제11권1호
• /
• pp.35-44
• /
• 2005

본 연구는 병계 및 폐사계의 자동 판정을 위한 알고리즘을 개발하는 것을 목적으로 수행되었다. 알고리즘을 개발하기 위하여 산란계의 질병증상 및 행동을 분석하였고 개발된 알고리즘으로 시스템을 구축하고 프로그램을 제작하여 성능을 분석하였다. 그 결과는 다음과 같이 요약된다. 1. 병$\cdot$폐사계의 판정을 위한 적정 촬영시간을 찾아내기 위해 산란계의 먹이에 대한 관심도를 조사한 결과 관심도가 $90\%$를 넘는 급이후 5분 30초 이내가 가장 적절한 것으로 판단되었다. 2. 외부의 빛을 차단하고 균일한 조도의 영상 얻기 위하여 illumination chamber를 설치하였으며 보조 조명장치를 부착하여 조도를 45 lx 로 균일하게 하였다. 3. 산란계의 영상을 추출하기 위한 RGB의 농도범위를 Red 0${\~}$140, Green 0${\~}$130, Blue 0${\~}$130 으로 하였을 때 가장 좋은 영상을 얻을 수 있었다. 4. 병계 및 폐사계의 판별을 위하여 CCD 카메라로부터 얻은 이미지를 2진화하고 수축 및 팽창 처리를 하여 Noise를 제거하였으며, Label-ing 작업 후 중심점을 계산하여 정상인 산란계의 이미지를 제거하였다. 5. 개발된 알고리즘을 LABWindows/CVI를 이용하여 프로그램을 작성하였다. 6. 개발된 감시시스템을 이용하여 실험 유형별로 4개의 케이지 산란계 20마리에 대하여 100회의 판별시험을 실시하였으며 그 결과 A형의 실험에서 $92\%$의 정확도를 나타냈고, B형의 실험에서 $96\%$의 정확도를 나타냈다. 7. 개발된 영상처리알고리즘을 영상처리시스템에 적용하여 실험산란계사내의 고단직립식산란계케이지에서 실험을 실시한 결과 높은 성공률을 보였으며 앞으로 개발될 고단직립식산란계케이지의 원격자동화감시시스템을 구성하는 데 있어서 적합한 영상처리알고리즘인 것으로 판단되었다.