• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.4
• /
• pp.185-193
• /
• 2024

Visual-inertial odometry (VIO) is a method that leverages sensor data from a camera and an inertial measurement unit (IMU) for state estimation. Whereas conventional VIO has limited capability to estimate scale of translation, the performance of recent approaches has been improved by utilizing depth maps obtained from RGB-D camera, especially in indoor environments. However, the depth map obtained from the RGB-D camera tends to rapidly lose accuracy as the distance increases, and therefore, it is required to develop alternative method to improve the VIO performance in wide environments. In this paper, we argue that leveraging depth map estimated from a deep neural network has benefits to state estimation. To improve the reliability of depth information utilized in VIO algorithm, we propose a kernel-based sampling strategy to filter out depth values with low confidence. The proposed method aims to improve the robustness and accuracy of VIO algorithms by selectively utilizing reliable values of estimated depth maps. Experiments were conducted on real-world custom dataset acquired from underground parking lot environments. Experimental results demonstrate that the proposed method is effective to improve the performance of VIO, exhibiting potential for the use of depth estimation network for state estimation.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.806-816
• /
• 2022

Purpose: In this study, the luminance measurement analysis results of the smoke generation state are considered for visual signal display light color for real-time escape guidance in the underground common area. Method: We will analyze the scattering characteristics of light in the atmosphere and optical technology based on the visibility theory, and try to classify the elemental technology as a guidance function through a prototype of a visual signal display device for evacuation guidance. Result: In the experiment conducted under the smoke-generating condition, the results were derived with low luminance ratio and good visibility in the order of red, green, and yellow. However, this result is different from general lighting in which color rendering is considered, and is limited to signals for signals and detection. Conclusion: A conclusions were drawn by reflecting both the luminance measurement results in the smoke generation situation and the preference survey results conducted in previous studies for the light color of the visual signal for signal and detection. When events such as smoke occur, it is better to use the escape guidance visual signal in red or green.

• Proceedings of the Optical Society of Korea Conference
• /
• 1998.08a
• /
• pp.122-123
• /
• 1998

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.10
• /
• pp.31-36
• /
• 2002

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.05a
• /
• pp.984-985
• /
• 2005

• Proceedings of the Optical Society of Korea Conference
• /
• 2006.07a
• /
• pp.157-158
• /
• 2006

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.1
• /
• pp.10-18
• /
• 2014

From the perspective of reducing the sampling cost of color images at high resolution, block-based compressive sensing (CS) has attracted considerable attention as a promising alternative to conventional Nyquist/Shannon sampling. On the other hand, for storing/transmitting applications, CS requires a very efficient way of representing the measurement data in terms of data volume. This paper addresses this problem by developing a measurement-coding method with the proposed customized Huffman coding. In addition, by noting the difference in visual importance between the luma and chroma channels, this paper proposes measurement coding in YCbCr space rather than in conventional RGB color space for better rate allocation. Furthermore, as the proper use of the image property in pursuing smoothness improves the CS recovery, this paper proposes the integration of a low pass filter to the CS recovery of color images, which is the block-based ${\ell}_{20}$-norm minimization. The proposed coding scheme shows considerable gain compared to conventional measurement coding.

• Journal of Korean Academy of Nursing
• /
• v.26 no.4
• /
• pp.868-877
• /
• 1996

This study was done to analyze research trends and to suggest future perspectives for nursing research on fatigue. The author reviewed 31 Korean and foreign research papers which have been published in the literature since 1970. An analysis of the study focused on the type of research subjects, type of study design. measurement instrument, and its correlated parameters. The results of the study are summarized as follows : First, within all of the studies analayzed, 14 studies were publised in Korea and 17 were published abroad. The number of studies done abroad have been increasing rapidly since 1991. Second, an analysis of the research design of the studies showed, eight studies each, Korean and foreign used survey design. Two Korean studies and seven foreign studies used a correlational design. Four comparative studies were done in Korea, but only two experimetal studies were performed abroad. Therefore, it was found that the trend of the study design used is survey design and there are more correlational studies done abroad than in Korea. Third, the type of the study subjects ; 11 Korean and three foreign studies dealt with healthy people. In addition, three Korean and 14 foreign studies investigated patients with various illnesses. It was found that patients with various illnesses were studied more frequently in foreign studies than in Korean studies. Fourth, the measurement tool used in the Korean studies ; 13 studies used a testible tool to assess patients' subjective symtoms or complaints of fatigue. The most commonly used tool used in 10 studies, was the Fatigue Self-Perception Scale, which was designed by the Labor and Health Institute of Japan. The Visual Analogue Scale was used in two studies, and Piper Fatigue Scale, addtional with physiologic parameters, was used in one study. In the foreign studies, subjective measurement tools were used in 16 studies. A combination of a subjective measurement tool with objective parameters was used in ten studies. For the subjective measurement tool used in the foreign studies, a specific measurement tool developed by the researcher which was used in seven studies. Either Rhoten Fatigue Scale or the Visual Analog Scale were used in three studies. Additionally, in order to identify the relationship between fatigue and psychological factors, The Profile of Mood State was used in three studies. Beck Depression Inventory was used in two studies. The Self Rated Depression Scale, developed by Zung, was used in one study and other measurement tools were used to measure various psychological parameters. Rhoten fatigue Checklist was also used to observe behavior patterns. Lastly, nine studies identified correlations between fatigue and other parameters. A significant correlation was found between fatigue and psychological factors such as depression, and pain. As a result of the above findings, it can be said that research trends on fatigue are increasing internationally. The selected study designs are survey studies both in Korea and abroad. There are more correlational studies abroad than in Korea. In addition, subjective measurement tools and objective parameters are used variously and combined with each other. had, there is a significant correlation between fatigue and psychological factors such as depression, and pain. More survey and correlational studies need to be done to identify the relationship of fatigue in patients with various condition or diagnoses and to suggest a scientific basis for nursing interventions with fatigue. Also, a tool to assess patient's subjective, objective, and behavioral aspects on fatigue needs to be developed.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.5
• /
• pp.135-143
• /
• 2000

The vision system is easy to use the exclusive use as a independent computer system but it is not much popularization by reason of expensive and difficult to adapt to the various fields, because it is easy to the existed computer system, the price is cheap and also it can use to the various measurement purpose which user wanted and programed. The measurement method of the vehicle axle casing nut welding part is that measure the value of the welding part to adapt the actual operation program from using the ratio between the actual length of the standard specimen and the length of image, to measure the ratio between the actual product and the camera image. A defect is found by the assembled visual inspection system. The inspection algorithm which estimates the quality of welded product is developed and also, the software program which processes the automatic test function of the inspection system. We make the foundation of the inspection automatic system and we will help to apply other welding machine.

• Journal of Biomedical Engineering Research
• /
• v.28 no.4
• /
• pp.477-483
• /
• 2007

We have measured EOG and fMRI simultaneously to investigate whether eye movement (blinking mechanism) might influence functional magnetic resonance imaging (fMRI) signal response in the primary visual cortex. $T2^*-weighted$ Echo-Planar Imaging (EPI) with concurrent electrooculogram (EOG) was acquired in four subjects while they viewed a fixation point and a checkerboard with a flickering rate of 8Hz. With the help of EOG information we divided the experimental blocks into two different conditions: fixation and moving eye. We have compared the fMRI data of these two conditions. Our results have shown that there is no difference between these two conditions. This might suggest that eye blinking does not affect BOLD signal changes in the primary visual cortex. This means further that eye blinking can be ignored in data processing.