• 한국전자통신학회논문지
• /
• 제15권2호
• /
• pp.349-356
• /
• 2020

본 논문은 교통사고 방지를 위한 운전자의 눈 영상비를 이용한 상태 경고시스템의 설계에 대해 소개하고 있다. 제안하는 운전자 상태 경고 시스템은 눈 인식을 위한 카메라, 카메라를 통해 들어오는 정보를 처리하는 라즈베리파이, 그리고 그 정보를 통해 운전자에게 경고를 줄 때 필요한 부저와 진동기로 구성되어 있다. 운전자의 눈을 인식하기 위해서 기울기 방향성 히스토그램 기술과 딥러닝 기반의 얼굴 표지점 추정 기법을 사용하였다. 동작을 시작하면, 시스템은 눈 주변의 6개의 좌표를 통해 눈 영상비를 계산한다. 그리고 눈을 뜬 상태와 감은 상태의 눈 영상비를 각각 계산한 후 이 두 값으로부터 눈의 상태를 판단하는데 사용하는 문턱 값을 설정한다. 문턱 값이 운전자의 눈 크기에 적응하면서 설정되기 때문에 시스템은 최적의 문턱 값을 사용하여 운전자의 상태를 판단할 수 있다. 또한 낮은 조도에서도 눈을 인식할 수 있도록 회색조 변환 이미지와 LAB모델 이미지를 합성하여 사용하였다.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.44-49
• /
• 2022

The number of single-person households is increasing worldwide, and among them, the proportion of elderly single-person households is increasing. In the case of elderly single-person households, a significant portion of their leisure time is devoted to watching TV. However, if they fall asleep while watching TV without turning it off, it may be difficult to sleep well due to lights and sounds of TV, which can cause health problems such as depression and reduced immunity. Therefore, in this paper, we propose a system that automatically turns off the TV when a person watching TV falls asleep. Images are collected using the camera installed in front of the TV. Since the posture of a person watching TV varies from a sitting posture to a lying posture, the system is designed to determine whether or not to fall asleep regardless of the posture. In addition, since it becomes difficult to judge eye movements as a person moves away from the TV, a method for extending the judgmentable distance is proposed. The system model was implemented and tested using a Raspberry Pi, a monitor, an infrared sensor, and a camera. Eye movements were judged regardless of sitting or lying position, and the distance between a user and a TV was extended by about 200 cm.

• 전자공학회논문지SC
• /
• 제47권6호
• /
• pp.86-96
• /
• 2010

본 논문에서는 U-시차맵과 조감도를 이용한 스테레오 비전 기반의 장애물체 검출 및 차량 검증 방법을 제안한다. 먼저 최대 빈도 값을 이용하여 V-시차맵 상에서 도로 특징 정보를 추출하고, 추출된 도로 정보를 이용하여 대략적인 도로상의 장애물체 영역을 추출한다. 좀 더 정확한 장애물체 영역 추출을 위하여 U-시차맵을 생성하는데, 이때 시차값과 카메라 파라미터를 이용하여 계산된 문턱치를 이용하여 높이 제한된 U-시차맵을 생성함으로써, 일정한 높이의 장애물체만을 검출 할 수 있다. 그러나 검출된 장애물체 영역 내에는 여전히 다수의 장애물체와 배경이 존재하므로, 세그먼테이션 과정을 수행한다. 전 단계에서 추출된 장애물체 영역을 카메라 모델링과 파라미터를 이용하여 조감도 맵핑을 수행한다. 조감도는 시차맵과 카메라 정보를 기반으로 계산된 장애물체들의 위치를 평면상에 표시함으로써 장애물체들을 좀 더 쉽게 분리할 수 있다. 마지막으로 각각 분리된 장애물체들 별로 차량 특징 기반의 차량 검증 과정을 수행한다. 도로 접점 여부, 일정한 수평크기, 가로 세로 비율 및 텍스쳐 정보를 이용하여 최종적으로 도로상의 차량만을 검출한다. 그리고 실제 도로에서 획득한 영상에 제안한 알고리즘을 적용함으로써 장애물체 검출 및 차량 검증 성능을 검증한다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제14권4호
• /
• pp.525-534
• /
• 2001

A total of 120 pigs were used to investigate the effects of yucca extracts on the growth performance, nutrient digestibility, nutrient excretion and carcass characteristics of finishing pigs fed different levels of dietary protein. Pigs were allotted into $2{\times}3$ factorial design by the supplementation of yucca extracts (YE, 0 and 120 mg/kg) and 3 levels of dietary protein (14, 16, 18% for early finisher and 12, 14, 16% for late finisher for low, medium and high protein diet, respectively). During the early finishing period (51~76 kg BW), no significant difference was found in growth performance regardless of the YE supplementation or dietary protein levels. Growth performance of late finishing pigs (76~101 kg BW) was also not significantly different among treatments. However, ADG of pigs fed YE diet was significantly improved (p<0.05) regardless of the dietary protein levels. For the overall period (51~101 kg BW), although adding YE to the diet and elevating the protein level showed better ADG, there were no significant differences on growth performance among treatments. Early finishers showed significantly higher crude protein, crude ash and crude fat digestibilities when they were fed diets supplemented with YE. Digestibilities of amino acids were not affected by YE. Late finishers did not show any significant differences in proximate nutrient digestibilities regardless of YE supplementation or dietary protein levels. YE tended to slightly improve the CP digestibility, however no significant difference was found with increased dietary protein levels. There was no significant difference in amino acid digestibilities with YE supplementation or dietary CP levels during the late finishing period. Dry matter (DM) and nitrogen (N) excretion in feces did not show any significant difference among treatments. Early finishing pigs also did not respond to the inclusion of YE or dietary protein levels (p<0.05). Fecal N excretion of early finishing pigs seemed to be lowered in pigs fed YE. Pigs fed medium dietary protein diet tended to excrete a higher amount of N during the early finishing period, but not statistically different. A slight increase in fecal N excretion was found with the increased level of dietary protein during the late finishing period. For ammonia nitrogen excretion, although there was no significance, the NH3-N content tended to be increased by the increased dietary protein levels and with YE supplementation. The NH3-N content in manure increased by 24.5% with YE supplementation. There were no significant differences in carcass weight, backfat thickness, carcass grade and loin eye area among treatments. However, pigs fed non-YE with low protein diet showed a significantly (p<0.05) low carcass ratio among treatments and there was significant (p<0.05) difference between the YE-added treatment and non YE treatment in carcass ratio. As for the feed cost, the cost of feeding high level protein was higher than that of medium level protein by 5% and low level protein by 9% (p<0.05). Therefore, based on this study, it could be concluded that environmentally friendly agents might play a role to some extent in finishing pigs from the aspect of pollution control, and that more than 14 and 12% of dietary protein for early finishing and late finishing pigs respectively do not necessarily guarantee high growth performance.