• 로봇학회논문지
• /
• 제4권4호
• /
• pp.257-264
• /
• 2009

This paper proposes a novel face detection method that finds tiny faces located at a long range even with low-resolution input images captured by a mobile robot. The proposed approach can locate extremely small-sized face regions of $12{\times}12$ pixels. We solve a tiny face detection problem by organizing a system that consists of multiple detectors including a mean-shift color tracker, short- and long-rage face detectors, and an omega shape detector. The proposed method adopts the long-range face detector that is well trained enough to detect tiny faces at a long range, and limiting its operation to only within a search region that is automatically determined by the mean-shift color tracker and the omega shape detector. By focusing on limiting the face search region as much as possible, the proposed method can accurately detect tiny faces at a long distance even with a low-resolution image, and decrease false positives sharply. According to the experimental results on realistic databases, the performance of the proposed approach is at a sufficiently practical level for various robot applications such as face recognition of non-cooperative users, human-following, and gesture recognition for long-range interaction.

• 로봇학회논문지
• /
• 제5권2호
• /
• pp.152-159
• /
• 2010

Finding a head of a person in a scene is very important for taking a well composed picture by a robot photographer because it depends on the position of the head. So in this paper, we propose a robust head tracking algorithm using a hybrid of an omega shape tracker and local binary pattern (LBP) AdaBoost face detector for the robot photographer to take a fine picture automatically. Face detection algorithms have good performance in terms of finding frontal faces, but it is not the same for rotated faces. In addition, when the face is occluded by a hat or hands, it has a hard time finding the face. In order to solve this problem, the omega shape tracker based on active shape model (ASM) is presented. The omega shape tracker is robust to occlusion and illuminationchange. However, whenthe environment is dynamic,such as when people move fast and when there is a complex background, its performance is unsatisfactory. Therefore, a method combining the face detection algorithm and the omega shape tracker by probabilistic method using histograms of oriented gradient (HOG) descriptor is proposed in this paper, in order to robustly find human head. A robot photographer was also implemented to abide by the 'rule of thirds' and to take photos when people smile.

• 로봇학회논문지
• /
• 제5권1호
• /
• pp.7-13
• /
• 2010

This paper presents the sound-based emotion estimation method and the growing HRI (human-robot interaction) system for a Mon-E robot. The method of emotion estimation uses the musical element based on the law of harmony and counterpoint. The emotion is estimated from sound using the information of musical elements which include chord, tempo, volume, harmonic and compass. In this paper, the estimated emotions display the standard 12 emotions including Eckman's 6 emotions (anger, disgust, fear, happiness, sadness, surprise) and the opposite 6 emotions (calmness, love, confidence, unhappiness, gladness, comfortableness) of those. The growing HRI system analyzes sensing information, estimated emotion and service log in an edutainment robot. So, it commands the behavior of the robot. The growing HRI system consists of the emotion client and the emotion server. The emotion client estimates the emotion from sound. This client not only transmits the estimated emotion and sensing information to the emotion server but also delivers response coming from the emotion server to the main program of the robot. The emotion server not only updates the rule table of HRI using information transmitted from the emotion client and but also transmits the response of the HRI to the emotion client. The proposed system was applied to a Mon-E robot and can supply friendly HRI service to users.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.119-128
• /
• 2014

본 논문에서는 이전 연구 방법에서의 UV-histogram을 확장하여 적응적 UV-histogram을 제시함으로써, 복잡한 구성의 장면에서 사람의 검출율을 높이는 방법을 제시한다. 제안 방법은 먼저 U-histogram에서 사람 영역을 1차 추출하고, 각각의 레이블링된 U에서 V-histogram을 생성함으로써, 이전 방법에서 구분할 수 없었던 사람 후보 영역을 정확하게 추출한다. 또한 제안 방법은 사람 판정시, 초점거리와 거리에 따라 적응적인 크기를 가지는 오메가 모양의 템플릿을 이용하여 검출의 정확도를 높였으며, 누적 영상을 이용하여 오검출을 템플릿 재매칭 함으로써, occlusion에도 강인한 특성을 가진다. 실험 결과는 Bae의 연구방법에 비하여 복잡한 환경에서 약 15%의 정확도 향상, 80%의 재현율 향상을 보이며, Xia의 연구방법에 비하여 20배 빠른 수행속도를 보여, 제안 방법의 성능이 우수함을 입증한다.

• 전기학회논문지
• /
• 제67권3호
• /
• pp.413-418
• /
• 2018

In this paper, we describe the development of a non-enzymatic glucose sensor based on copper nanocubes(Cu NCs) electroplated laser induced graphene(LIG) electrodes which can detect a certain range of glucose concentrations. $CO_2$ laser equipment was used to form LIG electrodes on the PI film. This fabrication method allows easy control of the LIG electrode size and shape. The Cu NCs were electrochemically deposited on the LIG electrodes to improve electron transfer rates and thus enhancing electrocatalytic reaction with glucose. The average sheet resistances before and after electroplating were $15.6{\Omega}/{\Box}$ and $19.6{\Omega}/{\Box}$, respectively, which confirmed that copper nanocubes were formed on the laser induced graphene electrodes. The prepared electrode was used to measure the current according to glucose concentration using an electrochemical method. The LIG electrodes with Cu NCs demonstrated a high degree of sensitivity ($1643.31{\mu}A/mM{\cdot}cm^2$), good stability with a linear response to glucose ranging from 0.05 mM to 1 mM concentration, and a limit of detection of 0.05 mM. In order to verify that these electrodes can be used as flexible devices, the electrodes were bent to $30^{\circ}$, $90^{\circ}$, and $180^{\circ}$ and cyclic voltammetry measurements were taken while the electrodes were bent. The measured data showed that the peak voltage was almost constant at 0.42 V and the signal was stable even in the flexed condition. Therefore, it is concluded that these electrodes can be used in flexible sensors for detecting glucose in the physiological sample like saliva, tear or sweat.