• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• The KIPS Transactions:PartB
• /
• v.8B no.1
• /
• pp.28-34
• /
• 2001

컴퓨터 시각 인식 방법을 이용하여 얼굴의 3차원 움직임 량을 추정하고자 하는 연구는 가상 현실 환경에서 얼굴 움직임에 의한 3차원 그래픽 화면 조정, 시뮬레이터에서의 훈련자 얼굴 움직임에 의한 화면 조정 및 모니터상의 시선 위치 파악 등을 위해 필수적으로 요구되는 기술로서 최근 활발히 연구되고 있다. 기존에 얼굴의 3차원 움직임 량을 추정하고자 하는 연구들은 대부분 확장 칼만 필터(extended kalman filter)를 이용하였으나, 이러한 방법은 필터의 초기 값을 정확하게 설정해야하는 제약 요소를 갖고 있으며, 또한 얼굴의 회전 방향 변화 시 이에 대처하지 못하는 경우 역시 종종 발생한다. 본 논문에서는 이러한 문제점을 해결하기 위하여 확장 칼만 필터의 변형 형태인 반복적 확장 칼만 필터를 이용하여 얼굴의 3차원 움직임 량을 추정하였다. 반복적 확장 칼만 필터에서는 확장 칼만 필터에서 계산되어 나오는 추정 오차 공분산 행렬 값이 미리 정해진 임계치보다 커지는 경우, 현재 얼굴의 움직임 량을 제대로 추정하지 못하고 있는 것으로 판단하여 칼만 필터에서 사용하는 회전 및 이동 속도, 그리고 회전 및 이동 각 속도를 변형함으로써 얼굴의 움직임 량을 정확하게 추정할 수 있도록 하는 방법이다. 실험 결과 반복적 확장 칼만 필터를 사용하였을 경우에 얼굴의 급격한 회전 방향 변화에도 얼굴의 3차원 움직임 량을 정확하게 추정할 수 있음을 알 수 있었다.

• Korean Journal of Applied Biomechanics
• /
• v.15 no.4
• /
• pp.169-179
• /
• 2005

In the 500m short track speed skating, the matter of who reaches the first corner first can important factor since each competitor races with all speed from the start to the first line. A filed study was attempted to kinematical estimation six female foreign skaters, who participated in the 500m female final round competition, and two Korea skates during the World Short track Skating Championship. The three dimensional motion analysis with DLT method was executed using four video cameras for analyzing the actual competition situation. In point of analyzing the actual competition situation, it is expected that skaters and coaches the effective informations, and the following conclusions are drawn; The elapsed time by phase in start motion of the foreign skaters appeared shorter those of Korea skaters, so the start training of Korea skaters should be strengthed. Also the displacement of C.G in the foreign skaters appeared shorter displacement than those of Korea skaters. Especially in the starting position, the foreign skaters are superior to Korea skaters in displacement of first(left) and next following stroke(right). The velocity of C.G and maximum velocity of skate blade of foreign skaters art faster than those of Korea skaters. And the foreign skaters show the superior early velocity change. Both of leaning body angle, and left and knee angle of the foreign skaters lead to positive point of having the propulsive force in the early starting position. Observing in the most prominent feature of foreign and Korea skaters in start phase, foreign skaters skate quickly the third stroke. These features of Korea skaters would appear disadvantage of location selection in entering the coner course.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.39-47
• /
• 2010

A research of image-based articulated pose estimation has some problems such as detection of human feature, precise pose estimation, and real-time performance. In particular, various methods are currently presented for recovering many joints of human body. We propose the novel numerical inverse kinematics improved with the UKF(unscented Kalman filter) in order to estimate the human pose in real-time. An existing numerical inverse kinematics is required many iterations for solving the optimal estimation and has some problems such as the singularity of jacobian matrix and a local minima. To solve these problems, we combine the UKF as a tool for optimal state estimation with the numerical inverse kinematics. Combining the solution of the numerical inverse kinematics with the sampling based UKF provides the stability and rapid convergence to optimal estimate. In order to estimate the human pose, we extract the interesting human body using both background subtraction and skin color detection algorithm. We localize its 3D position with the camera geometry. Next, through we use the UKF based numerical inverse kinematics, we generate the intermediate joints that are not detect from the images. Proposed method complements the defect of numerical inverse kinematics such as a computational complexity and an accuracy of estimation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.3
• /
• pp.258-268
• /
• 2001

The compression method is necessarily used to send the high quality moving picture that contains a number of data in image processing. In the field of moving picture compression method, the motion estimation algorithm is used to reduce the temporal redundancy. Block matching algorithm to be usually used is distinguished partial search algorithm with full search algorithm. Full search algorithm be used in this paper is the method to compare the reference block with entire block in the search window. It is very efficient and has simple data flow and control circuit. But the bigger the search window, the larger hardware size, because large computational operation is needed. In this paper, we design the full search block matching motion estimator. Using the DCT DC values, we decide luminance. And we apply 3 bit compare-selector using bit plane to I(Intra coded) picture, not using 8 bit luminance signals. Also it is suggested that use the same selective bit for the P(Predicted coded) and B(Bidirectional coded) picture. We compare based full search method with PSNR(Peak Signal to Noise Ratio) for C language modeling. Its condition is the reference block 8$\times$8, the search window 24$\times$24 and 352$\times$288 gray scale standard video images. The result has small difference that we cannot see. And we design the suggested motion estimator that hardware size is proved to reduce 38.3％ for structure I and 30.7％ for structure II. The memory is proved to reduce 31.3％ for structure I and II.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.236-245
• /
• 2004

A multiview sequence CODEC with view scaiability is proposed in this paper. We define a GGOP (Group of GOP) structure as a basic coding unit to efficiently code multiview sequences. 7he proposed CODEC provides flexible GGOP structures based on the number of views and baseline distances among cameras. Multiview sequences encode consists of disparity estimation/compensation, motion estimation/compensation, residual coding and rate control and generates multiview sequence bitstream. The main bitstream is the same as an MPEG-2 mono-sequence bitstream for MPEG-2 compatibility. The auxiliary bitstream contains information concerning the remaining multiview sequences except for the reference sequences. The proposed CODEC with view scalability provides that a number of view flints are selectively determined at the receiver according to the type of display modes. The proposed multiview sequence CODEC is tested with several multiview sequences to determine its flexibility. compatibility with MPEG-2 and view scaiability. In addition, we subjectively confirm that the decoded bitstreams with view scaiability can be Properly displayed by several types of display modes. including 3D monitors.

• Journal of the Korean GEO-environmental Society
• /
• v.16 no.9
• /
• pp.43-51
• /
• 2015

In this paper, a 3D shell-spring model that can perform time history analysis of buried pipelines is used to evaluate the effect of the incident direction of the earthquake motion. When applying harmonic motions, it is shown that the period of vibration has pronounced influence on the response of buried pipelines. With decrease in the period, the curvature of the pipeline and corresponding response are shown to increase. To evaluate the effect of the incident angle, the motions are applied in the direction of the pipleline, horizontal, and vertical planes. When the motion is applied parallel to the direction of the pipeline, it only induces bending strains and therefore, the response is the lowest. Under motions subjected in horizontal and vertical planes at an angle of $45^{\circ}$ from the longitudinal axis of the buried pipeline, the axial deformation is shown to contribute greatly to the response of the pipelines. When imposing two-components simultaneously, the calculated response is similar to the case where only single-component is imposed. It is because one component only induces bending strain, resulting in very small increase in the response. The trend of the response is shown to be quite similar for recorded motions. Therefore, it is concluded that use of a single-component is sufficient for estimation of the longitudinal response of buried pipelines.

• Earthquakes and Structures
• /
• v.2 no.3
• /
• pp.207-232
• /
• 2011

The development of reliable earthquake mitigation plans and seismic risk management procedures can only be based on the establishment of comprehensive earthquake hazard and loss scenarios. Two cities, Grevena (Greece) and D$\ddot{u}$zce (Turkey), were used as case studies in order to apply a comprehensive methodology for the vulnerability and loss assessment of lifelines. The methodology has the following distinctive phases: detailed inventory, identification of the typology of each component and system, evaluation of the probabilistic seismic hazard, geotechnical zonation, ground response analysis and estimation of the spatial distribution of seismic motion for different seismic scenarios, vulnerability analysis of the exposed elements at risk. Estimating adequate earthquake scenarios for different mean return periods, and selecting appropriate vulnerability functions, expected damages of the water and waste water systems in D$\ddot{u}$zce and of the roadway network and waste water system of Grevena are estimated and discussed; comparisons with observed earthquake damages are also made in the case of D$\ddot{u}$zce, proving the reliability and the efficiency of the proposed methodology. The results of the present study constitute a sound basis for the development of efficient loss scenarios for lifelines and infrastructure facilities in seismic prone areas. The first part of this paper, concerning the estimation of the seismic ground motions, has been utilized in the companion paper by Kappos et al. (2010) in the same journal.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.61-68
• /
• 2021

In this paper, we propose an edge computing-based exercise data collection device that can be provided for exercise rehabilitation services. In the existing cloud computing method, when the number of users increases, the throughput of the data center increases, causing a lot of delay. In this paper, we design and implement a device that measures and estimates the position of keypoints of body joints for movement information collected by a 3D camera from the user's side using edge computing and transmits them to the server. This can build a seamless information collection environment without load on the cloud system. The results of this study can be utilized in a personalized rehabilitation exercise coaching system through IoT and edge computing technologies for various users who want exercise rehabilitation.