• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.227-230
• /
• 2002

In this paper we concentrate on overall direction of the gaze based on a head pose for human computer interaction. To decide a gaze direction of user in a image, it is important to pick up facial feature exactly. For this, we binarize the input image and search two eyes and the mouth through the similarity of each block ( aspect ratio, size, and average gray value ) and geometric information of face at the binarized image. We create a imaginary plane on the line made by features of the real face and the pin hole of the camera to decide the head orientation. We call it the virtual facial plane. The position of a virtual facial plane is estimated through projected facial feature on the image plane. We find a gaze direction using the surface normal vector of the virtual facial plane. This study using popular PC camera will contribute practical usage of gaze tracking technology.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.199-200
• /
• 2008

머리의 자세 및 움직임 추적은 응시추적 및 시각운율 연구에서 필수적이다. 일반적으로 머리자세를 추정하는 방법은 보정된 카메라를 통해 추출된 얼굴의 특징점 정보를 이용한다. 그러나 실제 응용 분야에서는 보정되지 않은 카메라를 통한 머리 움직임을 추정해야 할 경우가 발생한다. 이에 따라 본 논문에서는 보정되지 않은 하나의 카메라를 이용, 단일특징점 정보를 이용한 머리 자세 추정 방법을 확장하여 최적화 기법을 도입한 다특징점 정보 기반 머리 자세 추정방법에 대하여 논하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.83-83
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot′s end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.89-90
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot's end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.177-186
• /
• 2015

For data fusion of laser range finder (LRF) and vision camera, accurate calibration of external parameters which describe relative pose between two sensors is necessary. This paper proposes a new calibration method which can acquires more accurate external parameters between a LRF and a vision camera compared to other existing methods. The main motivation of the proposed method is that any corner data of a known 3D structure which is acquired by the LRF should be projected on a straight line in the camera image. To satisfy such constraint, we propose a 3D geometric model and a numerical solution to minimize the energy function of the model. In addition, we describe the implementation steps of the data acquisition of LRF and camera images which are necessary in accurate calibration results. In the experiment results, it is shown that the performance of the proposed method are better in terms of accuracy compared to other conventional methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.347-356
• /
• 2003

Camera pose and scene geometry estimation from video sequences is widely used in various areas such as image composition. Structure and motion recovery based on the auto calibration algorithm can insert synthetic 3D objects in real but un modeled scenes and create their views from the camera positions. However, most previous methods require bundle adjustment or non linear minimization process [or more precise results. This paper presents a new auto' calibration algorithm for video sequence based on two steps: the one is key frame selection, and the other removes the key frame with inaccurate camera matrix based on an absolute quadric estimation by LMedS. In the experimental results, we have demonstrated that the proposed method can achieve a precise camera pose estimation and scene geometry recovery without bundle adjustment. In addition, virtual objects have been inserted in the real images by using the camera trajectories.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.3
• /
• pp.61-71
• /
• 2018

When triangular meshes are generated from the point clouds in global space reconstructed through camera pose estimation against captured RGB-D streams, the quality of the resulting meshes improves as more triangles are hired. However, for 3D reconstructed models beyond some size threshold, they become to suffer from the ugly-looking artefacts due to the insufficient precision of RGB-D sensors as well as significant burdens in memory requirement and rendering cost. In this paper, for the generation of 3D models appropriate for real-time applications, we propose an effective technique that extracts high-quality textures for moderate-sized meshes from the captured colors associated with the reconstructed point sets. In particular, we show that via a simple method based on the mapping between the 3D global space resulting from the camera pose estimation and the 2D texture space, textures can be generated effectively for the 3D models reconstructed from captured RGB-D image streams.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.24-34
• /
• 2007

Application systems that easy to access a information have been developed by IT growth and a human life variation. In this paper, we propose a application system to register a 3D footwear model using a monocular camera. In General, a human motion analysis research to body movement. However, this system research a new method to use a foot movement. This paper present a system process and show experiment results. For projection to 2D foot plane from 3D shoe model data, we construct processes that a foot tracking, a projection expression and pose estimation process. This system divide from a 2D image analysis and a 3D pose estimation. First, for a foot tracking, we propose a method that find fixing point by a foot characteristic, and propose a geometric expression to relate 2D coordinate and 3D coordinate to use a monocular camera without a camera calibration. We make a application system, and measure distance error. Then, we confirmed a registration very well.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.