• 인터넷정보학회논문지
• /
• 제23권1호
• /
• pp.19-29
• /
• 2022

Natural user interface (NUI) is used for the natural motion interface without using a specific device or tool like a mouse, keyboards, and pens. Recently, as non-contact sensor-based interaction technologies for recognizing human motion, gestures, voice, and gaze have been actively studied, an environment has been prepared that can provide more diverse contents based on various interaction methods compared to existing methods. However, as the number of sensors device is rapidly increasing, the system using a lot of sensors can suffer from a lack of computational resources. To address this problem, we proposed a real-time multi-device control system for natural interactive platform. In the proposed system, we classified two types of devices as the HC devices such as high-end commercial sensor and the LC devices such astraditional monitoring sensor with low-cost. we adopt each device manager to control efficiently. we demonstrate a proposed system works properly with user behavior such as gestures, motions, gazes, and voices.

• 한국산업융합학회 논문집
• /
• 제19권1호
• /
• pp.1-9
• /
• 2016

In this paper, we propose a new learning control scheme for various walk motion control of biped robot with same learning-base by neural network. We show that learning control algorithm based on the neural network is significantly more attractive intelligent controller design than previous traditional forms of control systems. A multi layer back propagation neural network identification is simulated to obtain a dynamic model of biped robot. Once the neural network has learned, the other neural network control is designed for various trajectory tracking control with same learning-base. The biped robots have been received increased attention due to several properties such as its human like mobility and the high-order dynamic equation. These properties enable the biped robots to perform the dangerous works instead of human beings. Thus, the stable walking control of the biped robots is a fundamentally hot issue and has been studied by many researchers. However, legged locomotion, it is difficult to control the biped robots. Besides, unlike the robot manipulator, the biped robot has an uncontrollable degree of freedom playing a dominant role for the stability of their locomotion in the biped robot dynamics. From the simulation and experiments the reliability of iterative learning control was illustrated.

• 한국컴퓨터정보학회논문지
• /
• 제25권1호
• /
• pp.55-61
• /
• 2020

딥 러닝 기술의 발전과 컴퓨팅 파워 등의 개선으로 인해 비디오 기반 연구는 최근 많은 관심을 얻고 있다. 비디오 데이터가 이미지 데이터와 비교하여 가장 큰 차이는 비디오 데이터에는 많은 양의 시간적, 공간적 정보가 포함되어 있다는 점이다. 이처럼 비디오에 포함된 많은 양의 데이터로 인해 컴퓨터 비전 연구에 있어서 행동 인식은 중요한 연구 과제 중 하나이지만, 비디오와 같이 움직임이 있는 환경에서 인간의 행동 인식은 매우 복잡하고 도전적인 과제이다. 인간에 대한 여러 연구를 바탕으로 인공지능에서는 인간과 유사한 주의(attention)메커니즘이 효율적인 인식 모델이라는 것을 알게 되었다. 이 효율적인 모델은 이미지 정보와 복잡한 연속 비디오 정보를 처리하는 데 이상적이다. 본 논문에서는 이러한 연구배경을 기반으로, 비디오에서 인간의 행동을 효율적으로 인식하기 위해 먼저 인간의 행동에 주목한 후 비디오 행동 인식에 주의메커니즘을 도입하고자 한다. 논문의 주요내용은 두 가지 주의 메카니즘을 기반으로 컨볼루션 신경망을 이용한 새로운 3D 잔류 주의 네트워크를 제안함으로써 비디오에서 인간의 행동을 식별하고자 한다. 제안 모델의 평가 결과 최대 90.7%정도의 정확도를 보였다.

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.1160-1165
• /
• 2004

The purpose of this study was to calculate three dimensional angular displacements, moments and joint reaction forces of the ankle joint during the waist pulling, and to assess the ankle joint reaction forces according to different perturbation modes and different levels of perturbation magnitude. Ankle joint model was assumed 3-D ball and socket joint which is capable of three rotational movements. We used 6 cameras, force plate and waist pulling system. Two different waist pulling systems were adopted for forward sway with three magnitudes each. From motion data and ground reaction forces, we could calculate 3-D angular displacements, moments and joint reaction forces during the recovery of postural balance control. From the experiment using falling mass perturbation, joint moments were larger than those from the experiment using air cylinder pulling system with milder perturbation. However, JRF were similar nevertheless the difference in joint moment. From this finding, we could conjecture that the human body employs different strategies to protect joints by decreasing joint reaction forces, like using the joint movement of flexion or extension or compensating joint reaction force with surrounding soft tissues. Therefore, biomechanical analysis of human ankle joint presented in this study is considered useful for understanding balance control and ankle injury mechanism.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• 한국정밀공학회지
• /
• 제28권6호
• /
• pp.687-693
• /
• 2011

Spring-mass models have been widely accepted to explain the basic dynamics of human gait. Researchers found that the leg stiffness increased with gait speed to increase energy efficiency. However, the difference of leg stiffness change with gait speed between the young and the elderly has not been verified yet. In this study, we calculated the lower limb stiffness of the elderly using walking model with an axial spring. Vertical stiffness was defined as the ratio of the vertical force change to the vertical displacement change. Seven young and eight elderly subjects participated to the test. The subjects walked on a 12 meter long, 1 meter wide walkway at four different gait speeds, ranging from their self-selected speed to maximum speed randomly. Kinetic and kinematic data were collected using three force plates and motion capture cameras, respectively. The vertical stiffness of the two groups increased as a function of walking speed. Maximum walking speed of the elderly was slower than that of the young, yet the walking speed correlated well with the optimal stiffness that maximizes propulsion energy in both groups. The results may imply that human may use apparent limb stiffness to optimize energy based on spring-like leg mechanics.

• 한국자동차공학회논문집
• /
• 제21권1호
• /
• pp.1-8
• /
• 2013

Recently, the automotive technology has developed with electronics and information technology as convergence technology while vehicles had been regarded as machines. Moreover, vehicles are becoming more intelligent and safer devices, assembly of advanced technologies by customers' demand. Even though all of installations of vehicle have attracted as diverting devices, it cause drivers' mistakes like delay of response on traffic condition. Here, we proposed the Field Operational Test (FOT) environment which could be used as driving and road conditions collector(Vehicle motion, Traffic condition, Driver input, Driver state, etc.) for researches about Driver Friendly Intelligent System(SCC, LDWS, etc.), Human Vehicle Interface(Driving Workload, etc.) and Economic Drive Model. Furthermore driving patten and fuel consumption patten of drivers were analyzed by measured data and direction of future research was suggested.

• 디지털콘텐츠학회 논문지
• /
• 제18권3호
• /
• pp.559-565
• /
• 2017

스마트폰에 내장된 가속도 센서를 이용하여 사용자의 동작 상태나 행동을 인식하기 위한 연구가 다양하게 진행되어 왔다. 본 논문에서는 스마트폰의 3D 가속도 정보에 신경회로망을 적용하여 사람의 행동을 인식하는 연구를 진행하였다. 시계열 데이터를 신경회로망에 그대로 적용하면 성능상의 문제가 발생한다. 따라서 여러 시구간에 대해 특징을 추출하여 각 시구간에 대해 신경회로망을 학습시키고, 이 신경회로망들의 출력들을 입력으로 하여 학습하여 구성하는 다중 시구간 신경회로망을 제안하였다. 제안하는 방법을 실제 가속도 데이터에 적용한 결과 SVM, AdaBoost, IBk 등 다른 분류기보다 우수한 성능을 보였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제36권5호
• /
• pp.674-682
• /
• 2012

A new intelligent stereo vision sensor system was studied for the motion and depth control of unmanned vehicles. A new bottom-up saliency map model for the human-like active stereo vision system based on biological visual process was developed to select a target object. If the left and right cameras successfully find the same target object, the implemented active vision system with two cameras focuses on a landmark and can detect the depth and the direction information. By using this information, the unmanned vehicle can approach to the target autonomously. A number of tests for the proposed bottom-up saliency map were performed, and their results were presented.