• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.2
• /
• pp.349-356
• /
• 2020

This paper introduces the implementation of a driver's condition warning system using eye aspect ratio to prevent a car accident. The proposed driver's condition warning system using eye aspect ratio consists of a camera, that is required to detect eyes, the Raspberrypie that processes information on eyes from the camera, buzzer and vibrator, that are required to warn the driver. In order to detect and recognize driver's eyes, the histogram of oriented gradients and face landmark estimation based on deep-learning are used. Initially the system calculates the eye aspect ratio of the driver from 6 coordinates around the eye and then gets each eye aspect ratio values when the eyes are opened and closed. These two different eye aspect ratio values are used to calculate the threshold value that is necessary to determine the eye state. Because the threshold value is adaptively determined according to the driver's eye aspect ratio, the system can use the optimal threshold value to determine the driver's condition. In addition, the system synthesizes an input image from the gray-scaled and LAB model images to operate in low lighting conditions.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.86-96
• /
• 2010

In this paper, we propose stereo vision-based obstacle detection and vehicle verification methods using U-disparity map and bird's-eye view mapping. First, we extract a road feature using maximum frequent values in each row and column. And we extract obstacle areas on the road using the extracted road feature. To extract obstacle areas exactly we utilize U-disparity map. We can extract obstacle areas exactly on the U-disparity map using threshold value which consists of disparity value and camera parameter. But there are still multiple obstacles in the extracted obstacle areas. Thus, we perform another processing, namely segmentation. We convert the extracted obstacle areas into a bird's-eye view using camera modeling and parameters. We can segment obstacle areas on the bird's-eye view robustly because obstacles are represented on it according to ranges. Finally, we verify the obstacles whether those are vehicles or not using various vehicle features, namely road contacting, constant horizontal length, aspect ratio and texture information. We conduct experiments to prove the performance of our proposed algorithms in real traffic situations.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.4
• /
• 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.