• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.321-327
• /
• 2015

In this paper, we propose an algorithm for achieving robust Visual Voice Activity Detection (VVAD) for enhanced speech recognition. In conventional VVAD algorithms, the motion of lip region is found by applying an optical flow or Chaos inspired measures for detecting visual speech frames. The optical flow-based VVAD is difficult to be adopted to driving scenarios due to its computational complexity. While invariant to illumination changes, Chaos theory based VVAD method is sensitive to motion translations caused by driver's head movements. The proposed Local Variance Histogram (LVH) is robust to the pixel intensity changes from both illumination change and translation change. Hence, for improved performance in environmental changes, we adopt the novel threshold estimation using total variance change. In the experimental results, the proposed VVAD algorithm achieves robustness in various driving situations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.11
• /
• pp.935-940
• /
• 2002

For robot navigation and visual reconstruction, structure from motion (SFM) is an active issue in computer vision community and its properties arc also becoming well understood. In this paper, when using stereo image sequence and direct method as a tool for SFM, we present a new method for overcoming bas-relief ambiguity. We first show that the direct methods, based on optical flow constraint equation, are also intrinsically exposed to such ambiguity although they introduce robust methods. Therefore, regarding the motion and depth estimation by the robust and direct method as approximated ones. we suggest a method that refines both stereo displacement and motion displacement with sub-pixel accuracy, which is the central process f3r improving its ambiguity. Experiments with real image sequences have been executed and we show that the proposed algorithm has improved the estimation accuracy.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1347-1349
• /
• 1996

Most real image sequences contain multiple moving objects or multiple motions. In this paper, we segmented the moving objects with optical flow. Motion estimation by this method can estimate and compress the image sequences better than other methods such as block matching method. And, especially, we can make new image sequences by synthesizing the segmented objects. But, it takes too much time for motion estimation. And, it is not easy for a hardware implementation.

• Journal of the HCI Society of Korea
• /
• v.9 no.1
• /
• pp.11-21
• /
• 2014

We present an experimental framework to analyze the physical reactions and causal factors of Visually Induced Motion Sickness (VIMS) using electroencephalography (EEG) signals and vital signs. We studied eleven subjects who are voluntarily participated in the experiments and conducted online and offline surveys. In order to simulate videos including global motions that could cause the motion sickness, we extracted global motions by optical flow estimation method from hand-held captured video recordings containing intense motions. Then, we applied the extracted global motions to our test videos with action movies and texts. Each genre of video includes three levels of different motions depending on its intensity. EEG signal and vital sign that were measured by a portable electrocorticography device and an electronic monometer in real time while the subjects watch the videos including ones with the extracted motions. We perform an analysis of the EEG signals using Distance Map(DM) calculated by correlation among each channel of brain signal. Analysis using the vital signs and the survey results is also performed to obtain relationship between the VIMS and causal factors. As a result, we clustered subjects into three groups based on the analysis of the physical reaction using the DM and the correlation between vital sign and survey results, which shows high relationships between the VIMS and the intensity of motions.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.4
• /
• pp.507-514
• /
• 2003

Most of CAE analyses for injection molding have been based on the Mele Shaw's approximation: two-dimensional flow analysis. in some cases, that approximation causes significant errors due to loss of the geometrical information as well as simplification of the flow characteristics in the thickness direction. Although injection molding analysis software using three-dimensional solid elements has been developed recently, such as Moldflow Flow3D, it does not contain a deformation analysis function yet. The present work covers three-dimensional deformation analysis or injection molded plastic parts using solid elements. A numerical scheme for deformation analysis has bun proposed from the results of injection molding analysis using Moldflow Flow3D. The accuracy of the proposed approach has been verified through a numerical analysis of rectangular plates with various thicknesses in comparison with the classical shell-based approach. In addition, the reliability of the approach has also been proved through an industrial example. an optical plastic lens, in comparison of real experiments.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.519-528
• /
• 2012

Voice activity detection (VAD) is generally conducted by extracting features from the acoustic signal and a decision rule. The performance of such VAD algorithms driven by the input acoustic signal highly depends on the acoustic noise. When video signals are available as well, the performance of VAD can be enhanced by using the visual information which is not affected by the acoustic noise. Previous visual VAD algorithms usually use single visual feature to detect the lip activity, such as active appearance models, optical flow or intensity variation. Based on the analysis of the weakness of each feature, we propose to combine intensity change measure and the optical flow in the mouth region, which can compensate for each other's weakness. In order to minimize the computational complexity, we develop simple measures that avoid statistical estimation or modeling. Specifically, the optical flow is the averaged motion vector of some grid regions and the intensity variation is detected by simple thresholding. To extract the mouth region, we propose a simple algorithm which first detects two eyes and uses the profile of intensity to detect the center of mouth. Experiments show that the proposed combination of two simple measures show higher detection rates for the given false positive rate than the methods that use a single feature.

• Journal of Biosystems Engineering
• /
• v.41 no.4
• /
• pp.408-417
• /
• 2016

Purpose: Yield monitoring systems are an essential component of precision agriculture. They indicate the spatial variability of crop yield in fields, and have become an important factor in modern harvesters. The objective of this paper was to review research trends related to yield monitoring sensors for grain crops. Methods: The literature was reviewed for research on the major sensing components of grain yield monitoring systems. These major components included grain flow sensors, moisture content sensors, and cutting width sensors. Sensors were classified by sensing principle and type, and their performance was also reviewed. Results: The main targeted harvesting grain crops were rice, wheat, corn, barley, and grain sorghum. Grain flow sensors were classified into mass flow and volume flow methods. Mass flow sensors were mounted primarily at the clean grain elevator head or under the grain tank, and volume flow sensors were mounted at the head or in the middle of the elevator. Mass flow methods used weighing, force impact, and radiometric approaches, some of which resulted in measurement error levels lower than 5% ($R^2=0.99$). Volume flow methods included paddle wheel type and optical type, and in the best cases produced error levels lower than 3%. Grain moisture content sensing was in many cases achieved using capacitive modules. In some cases, errors were lower than 1%. Cutting width was measured by ultrasonic distance sensors mounted at both sides of the header dividers, and the errors were in some cases lower than 5%. Conclusions: The design and fabrication of an integrated yield monitoring system for a target crop would be affected by the selection of a sensing approach, as well as the layout and mounting of the sensors. For accurate estimation of yield, signal processing and correction measures should be also implemented.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.1-9
• /
• 2008

In this paper, we proposed automatic face detection and tracking which is robustness in rotation. To detect a face image in complicated background and various illuminating conditions, we used face skin color detection. we used Harris corner detector for extract facial feature points. After that, we need to track these feature points. In traditional method, Lucas-Kanade feature tracker doesn't delete useless feature points by occlusion in current scene (face rotation or out of camera). So we proposed the estimation function, which delete useless feature points. The method of delete useless feature points is estimation value at each pyramidal level. When the face was occlusion, we deleted these feature points. This can be robustness to face rotation and out of camera. In experimental results, we assess that using estimation function is better than traditional feature tracker.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.1
• /
• pp.40-49
• /
• 2007

In a visual driver-assistance system, separating moving objects from fixed objects are an important problem to maintain multiple hypothesis for the state. Color and edge-based tracker can often be 'distracted' causing them to track the wrong object. Many researchers have dealt with this problem by using multiple features, as it is unlikely that all will be distracted at the same time. In this paper, we improve the accuracy and robustness of real-time tracking by combining a color histogram feature with a brightness of Optical Flow-based feature under a Sequential Monte Carlo framework. And it is also excepted from Tracking as time goes on, reducing density by Adaptive Particles Number in case of the fixed object. This new framework makes two main contributions. The one is about the prediction framework which separating moving objects from fixed objects and the other is about measurement framework to get a information from the visual data under a partial occlusion.