• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.9-23
• /
• 2024

In this study, we propose a method to improve the classification accuracy of body mass index (BMI) estimation techniques based on three-dimensional gait data. In previous studies on BMI estimation techniques, the classification accuracy was only about 60%. In this study, we identify the reasons for the low BMI classification accuracy. According to our analysis, the reason is the use of the undersampling technique to address the class imbalance problem in the gait dataset. We propose applying oversampling instead of undersampling to solve the class imbalance issue. We also demonstrate the usefulness of anthropometric and spatiotemporal features in gait data-based BMI estimation techniques. Previous studies evaluated the usefulness of anthropometric and spatiotemporal features in the presence of undersampling techniques and reported that their combined use leads to lower BMI estimation performance than when using either feature alone. However, our results show that using both features together and applying an oversampling technique achieves state-of-the-art performance with 92.92% accuracy in the BMI estimation problem.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.209-216
• /
• 2005

In wireless sensor networks, an estimation method is proposed for distances between nodes within two hops. The method uses only proximity information of nodes without physiccal distance measurements. It drastically improves the performance of localization algorithms based on Proximity information. In addition, it is the first method that estimates distances between nodes exactly in two hops. The distances are estimated from the number of common neighbors under an assumption that the number of common neighbors is proportional to the intersection of two unit disks centered at the two nodes. Simulation analysis shows that the estimation error is roughly from 10 to 20 percent of real distances. Meanwhile, the number of messages required by a distributed algorithm realizing this method is only two times the number of nodes.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.2
• /
• pp.97-104
• /
• 2004

As a channel of a DS-CDMA system is shared among several users, the receivers face the problem of MAI. Also the bandlimited channel leads to ISI. Both components are undesired, but unlike the additive noise process, which is usually completely unpredictable, their space-time structure helps to estimate and remove them. This paper investigates a DS-CDMA system with a fading multipath channel. The investigations have been separated into a channel estimation part and a reception part. In the estimation part of seperated two parts, the multipath parameters such as DOA and TOA are evaluated in this paper. In the part of receiver. we used these parameters and tested the performance of this receiver about space-time beamformers. To assess many different estimation techniques and beamformers, the simulation compared with theoretical values is performed.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.17-25
• /
• 2017

In this paper, we have implemented a low-cost mobile robot supporting the person tracking by detection using RGB-D cameras and ROS(Robot Operating System) framework. The mobile robot was developed based on the Kobuki mobile base equipped with 2's Kinect devices and a high performance controller. One kinect device was used to detect and track the single person among people in the constrained working area by combining point cloud data filtering & clustering, HOG classifier and Kalman Filter-based estimation successively, and the other to perform the SLAM-based navigation supported in ROS framework. In performance evaluation, the person tracking by detection was proved to be robustly executed in real-time, and the navigation function showed the accuracy with the mean distance error being lower than 50mm. The mobile robot implemented has a significance in using the open-source based, general-purpose and low-cost approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.2
• /
• pp.120-133
• /
• 2008

This paper presents a novel approach for facial motion tracking and facial expression cloning to create a realistic facial animation of a 3D avatar. The exact head pose estimation and facial expression tracking are critical issues that must be solved when developing vision-based computer animation. In this paper, we deal with these two problems. The proposed approach consists of two phases: dynamic head pose estimation and facial expression cloning. The dynamic head pose estimation can robustly estimate a 3D head pose from input video images. Given an initial reference template of a face image and the corresponding 3D head pose, the full head motion is recovered by projecting a cylindrical head model onto the face image. It is possible to recover the head pose regardless of light variations and self-occlusion by updating the template dynamically. In the phase of synthesizing the facial expression, the variations of the major facial feature points of the face images are tracked by using optical flow and the variations are retargeted to the 3D face model. At the same time, we exploit the RBF (Radial Basis Function) to deform the local area of the face model around the major feature points. Consequently, facial expression synthesis is done by directly tracking the variations of the major feature points and indirectly estimating the variations of the regional feature points. From the experiments, we can prove that the proposed vision-based facial expression cloning method automatically estimates the 3D head pose and produces realistic 3D facial expressions in real time.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.564-567
• /
• 1997

This paper deals with the problem of extraction of voice signal embedded in 1/f noise. We propose the extraction method using wavelet. This method is based on Wornell's modelling which can construct 1/f process in terms of uncorrelated variables and is well suited on treating 1/f process. Finally, we show further describe our method through simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.82-83
• /
• 2010

• Journal of the Korean Data and Information Science Society
• /
• v.9 no.1
• /
• pp.89-94
• /
• 1998

We shall propose several Bayes estimators for reliability of a two-unit hot standby system with the imperfect switch based upon a complete sample of failure times observed from an exponential distribution, and the proposed reliability Bayesian estimators are compared numerically each other in sense of mean squared error.