• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.411-417
• /
• 2009

We proposed a robust body part tracking system for intelligent environment that will not limit freedom of users. Unlike any previous gesture recognizer, we upgraded the generality of the system by creating the ability the ability to recognize details, such as, the ability to detect the difference between long sleeves and short sleeves. For the precise each body part tracking, we obtained the image of hands, head, and feet separately from a single camera, and when detecting each body part, we separately chose the appropriate feature for certain parts. Using a calibrated camera, we transferred 2D detected body parts into the 3D posture. In the experimentation, this system showed advanced hand tracking performance in real time(50fps).

• Journal of the Korean Society of Industry Convergence
• /
• v.17 no.2
• /
• pp.42-53
• /
• 2014

Robust voice recognition (RVR) is essential for a robot to communicate with people. One of the main problems with RVR for robots is that robots inevitably real environment noises. The noise is captured with strong power by the microphones, because the noise sources are closed to the microphones. The signal-to-noise ratio of input voice becomes quite low. However, it is possible to estimate the noise by using information on the robot's own motions and postures, because a type of motion/gesture produces almost the same pattern of noise every time it is performed. In this paper, we propose an RVR system which can robustly recognize voice by adults and children in noisy environments. We evaluate the RVR system in a communication robot placed in a real noisy environment. Voice is captured using a wireless microphone. Navigation Strategy is shown Obstacle detection and local map, Design of Goal-seeking Behavior and Avoidance Behavior, Fuzzy Decision Maker and Lower level controller. The final hypothesis is selected based on posterior probability. We then select the task in the motion task library. In the motion control, we also integrate the obstacle avoidance control using ultrasonic sensors. Those are powerful for detecting obstacle with simple algorithm.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.60-63
• /
• 2008

The sony Eytoy is developed on Playstation 2 using webcam for detecting human. A user see his appearance in television and become real gamer in the game. It is very different interface compared with ordinary video game which uses joystick. Although Eyetoy already was made for commercial products but the interface method still is interesting and can be added with many techniques like gesture recognition. In this paper, we have developed game interface with image processing for human hand and face detection and with game graphic module. And we realize one example game for busting balloons and demonstrated the game interface abilities. We will open this project for other developers and will be developed very much.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.73-76
• /
• 2013

This paper proposes a tongue and its direction recognition algorithm which compares and estimates pixel distribution in the mouth area. As the size of smart phones grows, facial gesture control technology for a smart phone is required. Firstly, the nose area is detected and the mouth area is detected based on the ratio of the nose to mouth. After detecting the mouth area, it is divided by a pattern of grid and the distribution of pixels having the similar color to the tongue is tested for each segment. The recognition rate was nearly 80% in the experiments performed with five researchers among our laboratory members.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.1-12
• /
• 2011

Large-sized multi-touch screen is usually made using infrared rays. That is because it has technical constraints or cost problems to make the screen with the other ways using such as existing resistive overlays, capacitive overlay, or acoustic wave. Using infrared rays to make multi-touch screen is easy, but is likely to have technical limits to be implemented. To make up for these technical problems, two other methods were suggested through Surface project, which is a next generation user-interface concept of Microsoft. One is Frustrated Total Internal Reflection (FTIR) which uses infrared cameras, the other is Diffuse Illumination (DI). FTIR and DI are easy to be implemented in large screens and are not influenced by the number of touch points. Although FTIR method has an advantage in detecting touch-points, it also has lots of disadvantages such as screen size limit, quality of the materials, the module for infrared LED arrays, and high consuming power. On the other hand, DI method has difficulty in detecting touch-points because of it's structural problems but makes it possible to solve the problem of FTIR. In this thesis, we study the algorithms for effectively correcting the distort phenomenon of optical lens, and image processing algorithms in order to solve the touch detecting problem of the original DI method. Moreover, we suggest calibration algorithms for improving the accuracy of multi-touch, and a new tracking technique for accurate movement and gesture of the touch device. To verify our approaches, we implemented a table-based multi touch screen.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.685-691
• /
• 2020

In this study, an algorithm that recognizes numbers from 0 to 9 was developed using the data obtained after tracking hand movements using the echo signal of a millimeter-wave radar sensor at 77 GHz. The echo signals obtained from the radar sensor by detecting the motion of a hand gesture revealed a cluster of irregular dots due to the difference in scattering cross-sectional area. A valid center point was obtained from them by applying a K-Means algorithm using 3D coordinate values. In addition, the obtained center points were connected to produce a numeric image. The recognition rate was compared by inputting the obtained image and an image similar to human handwriting by applying the smoothing technique to a CNN (Convolutional Neural Network) model trained with MNIST (Modified National Institute of Standards and Technology database). The experiment was conducted in two ways. First, in the recognition experiments using images with and without smoothing, average recognition rates of 77.0% and 81.0% were obtained, respectively. In the experiment of the CNN model with augmentation of learning data, a recognition rate of 97.5% and 99.0% on average was obtained in the recognition experiment using the image with and without smoothing technique, respectively. This study can be applied to various non-contact recognition technologies using radar sensors.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• 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.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.82-91
• /
• 2009

Sign language spotting is the task of detecting and recognizing the signs in a signed utterance. The difficulty of sign language spotting is that the occurrences of signs vary in both motion and shape. Moreover, the signs appear within a continuous gesture stream, interspersed with transitional movements between signs in a vocabulary and non-sign patterns(which include out-of-vocabulary signs, epentheses, and other movements that do not correspond to signs). In this paper, a novel method for designing a threshold model in a conditional random field(CRF) model is proposed. The proposed model performs an adaptive threshold for distinguishing between signs in the vocabulary and non-sign patterns. A hand appearance-based sign verification method, a short-sign detector, and a subsign reasoning method are included to further improve sign language spotting accuracy. Experimental results show that the proposed method can detect signs from continuous data with an 88% spotting rate and can recognize signs from isolated data with a 94% recognition rate, versus 74% and 90% respectively for CRFs without a threshold model, short-sign detector, subsign reasoning, and hand appearance-based sign verification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2727-2732
• /
• 2014

Recently, the researches of object tracking and recognition using Microsoft's Kinect are being actively studied. In this environment human hand detection and tracking is the most basic technique for human computer interaction. This paper proposes a method of improving the accuracy of the detected hand region's boundary in the cluttered background. To do this, we combine the hand detection results using the skin color with the extracted depth image from Kinect. From the experimental results, we show that the proposed method increase the accuracy of the hand region detection than the method of detecting a hand region with a depth image only. If the proposed method is applied to the sign language or gesture recognition system it is expected to contribute much to accuracy improvement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.389-392
• /
• 2010

In this paper, it presents to detect location using structural information of hand from the input color images on Webcam and to recognize hand gestures. In this system, based on the skin color, the image changes a binary number and labels. Within each labeled area, we can find the Maximum Inscribed Circle using Voronoi Diagram. This circle can find the center of hand. And the circle extracts hand region from analyzing the ellipse elements to relate Maximum Inscribed Circle. We use the Maximum Inscribed Circle and the ellipse elements as characteristic of hand gesture recognition. In various environments, we cannot recognize the object that have similar colors like the background colors. But the proposed algorithm has the advantage that can be effectively eliminated about it.