• Korean Journal of Computational Design and Engineering
• /
• v.13 no.6
• /
• pp.403-411
• /
• 2008

The alignment of facial images is crucial for 2D face recognition. This is the same to facial meshes for 3D face recognition. Most of the 3D face recognition methods refer to 3D alignment but do not describe their approaches in details. In this paper, we focus on describing an automatic 3D alignment in viewpoint of quantitative analysis. This paper presents a framework of 3D face alignment and normalization based on feature points obtained by Active Shape Models (ASMs). The positions of eyes and mouth can give possibility of aligning the 3D face exactly in three-dimension space. The rotational transform on each axis is defined with respect to the reference position. In aligning process, the rotational transform converts an input 3D faces with large pose variations to the reference frontal view. The part of face is flopped from the aligned face using the sphere region centered at the nose tip of 3D face. The cropped face is shifted and brought into the frame with specified size for normalizing. Subsequently, the interpolation is carried to the face for sampling at equal interval and filling holes. The color interpolation is also carried at the same interval. The outputs are normalized 2D and 3D face which can be used for face recognition. Finally, we carry two sets of experiments to measure aligning errors and evaluate the performance of suggested process.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.3
• /
• pp.67-72
• /
• 2015

This paper proposes an object tracking system based on keypoints using homography in mobile environments. The proposed system is based on markerless tracking, and there are four modules which are recognition, tracking, detecting and learning module. Recognition module detects and identifies an object to be matched on current frame correspond to the database using LSH through SURF, and then this module generates a standard object information. Tracking module tracks an object using homography information that generate by being matched on the learned object keypoints to the current object keypoints. Then update the window included the object for defining object's pose. Detecting module finds out the object based on having the best possible knowledge available among the learned objects information, when the system fails to track. The experimental results show that the proposed system is able to recognize and track objects with updating object's pose for the use of mobile platform.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.927-934
• /
• 2014

In this paper, we propose an effective method for recognizing daily human activities from a stream of three dimensional body poses, which can be obtained by using Kinect-like RGB-D sensors. The body pose data provided by Kinect SDK or OpenNI may suffer from both the view variance problem and the scale variance problem, since they are represented in the 3D Cartesian coordinate system, the origin of which is located on the center of Kinect. In order to resolve the problem and get the view-invariant and scale-invariant features, we transform the pose data into the spherical coordinate system of which the origin is placed on the center of the subject's hip, and then perform on them the scale normalization using the length of the subject's arm. In order to represent effectively complex internal structures of high-level daily activities, we utilize Hidden state Conditional Random Field (HCRF), which is one of probabilistic graphical models. Through various experiments using two different datasets, KAD-70 and CAD-60, we showed the high performance of our method and the implementation system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.3
• /
• pp.558-567
• /
• 2017

In this research, we developed an efficient real-time human exercise pose estimation system using multiple Kinects. The main objective of this system is to measure and recognize the user's posture (such as knee curl or lunge) more accurately by employing Kinects on the front and the sides. Especially it is designed as an extensible and modular method which enables to support various additional postures in the future. This system is configured as multiple clients and the Unity3D server. The client processes Kinect skeleton data and send to the server. The server performs the multiple-Kinect calibration process and then applies the pose estimation algorithm based on the Kinect-based posture recognition model using feature extractions and the weighted averaging of feature values for different Kinects. This paper presents the design and implementation of the human exercise pose estimation system using multiple Kinects and also describes how to build and execute an interactive Unity3D exergame.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.499-510
• /
• 2018

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.6
• /
• pp.546-552
• /
• 2016

We present a quantitative evaluation of an algorithm for model-based face recognition. The algorithm actively learns how individual faces vary through video sequences, providing on-line suppression of confounding factors such as expression, lighting and pose. By actively decoupling sources of image variation, the algorithm provides a framework in which identity evidence can be integrated over a sequence. We demonstrate that face recognition can be considerably improved by the analysis of video sequences. The method presented is widely applicable in many multi-class interpretation problems.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2379-2384
• /
• 2005

We propose a novel method for object recognition using the smart tag system with a stereo vision on a pan-tilt mechanism. We developed a smart tag which included IRED device. The smart tag is attached onto the object. We also developed a stereo vision system which pans and tilts for the object image to be the centered on each whole image view. A Stereo vision system on the pan-tilt mechanism can map the position of IRED to the robot coordinate system by using pan-tilt angles. And then, to map the size and pose of the object for the robot to coordinate the system, we used a simple model-based vision algorithm. To increase the possibility of tag-based object recognition, we implemented our approach by using as easy and simple techniques as possible.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.3
• /
• pp.250-255
• /
• 2012

Face recognition has wide applications in security and surveillance systems as well as in robot vision and machine interfaces. Conventional challenges in face recognition include pose, illumination, and expression, and face recognition at a distance involves additional challenges because long-distance images are often degraded due to poor focusing and motion blurring. This study investigates the effectiveness of applying photon-counting linear discriminant analysis (Pc-LDA) to face recognition in harsh environments. A related technique, Fisher linear discriminant analysis, has been found to be optimal, but it often suffers from the singularity problem because the number of available training images is generally much smaller than the number of pixels. Pc-LDA, on the other hand, realizes the Fisher criterion in high-dimensional space without any dimensionality reduction. Therefore, it provides more invariant solutions to image recognition under distortion and degradation. Two decision rules are employed: one is based on Euclidean distance; the other, on normalized correlation. In the experiments, the asymptotic equivalence of the photon-counting method to the Fisher method is verified with simulated data. Degraded facial images are employed to demonstrate the robustness of the photon-counting classifier in harsh environments. Four types of blurring point spread functions are applied to the test images in order to simulate long-distance acquisition. The results are compared with those of conventional Eigen face and Fisher face methods. The results indicate that Pc-LDA is better than conventional facial recognition techniques.