• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권7호
• /
• pp.267-274
• /
• 2018

본 논문에서는 PTZ 카메라를 이용한 머리자세추정 방법에 대하여 서술한다. 회전 또는 이동에 의하여 카메라의 외부인자가 변경되면, 추정된 얼굴자세도 변한다. 본 논문에는 PTZ 카메라의 회전과 위치 변화에 독립적으로 머리자세를 추정하는 새로운 방법을 제안한다. 제안하는 방법은 얼굴검출, 특징추출 그리고 자세추정으로 이루어진다. 얼굴검출은 MCT특징을 이용해 검출하고, 얼굴 특징추출은 회귀트리 방법을 이용해 추출하고, 머리자세 추정은 POSIT 알고리즘을 사용한다. 기존의 POSIT 알고리즘은 카메라의 회전을 고려하지 않지만, 카메라의 외부인자 변화에도 강건하게 머리자세를 추정하기 위하여 본 논문은 원근투영법에 기반하여 POSIT를 개선한다. 실험을 통하여 본 논문에서 제안하는 방법이 기존의 방법 보다 RMSE가 약 $0.6^{\circ}$ 개선되는 것을 확인했다.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1307-1317
• /
• 2018

To deal with the problems of occlusion, pose variations and illumination changes in the object tracking system, a regression model weighted multi-templates mean-shift (MS) algorithm is proposed in this paper. Target templates and occlusion templates are extracted to compose a multi-templates set. Then, the MS algorithm is applied to the multi-templates set for obtaining the candidate areas. Moreover, a regression model is trained to estimate the Bhattacharyya coefficients between the templates and candidate areas. Finally, the geometric center of the tracked areas is considered as the object's position. The proposed algorithm is evaluated on several classical videos. The experimental results show that the regression model weighted multi-templates MS algorithm can track an object accurately in terms of occlusion, illumination changes and pose variations.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.35-36
• /
• 2022

본 논문은 딥러닝 사람 자세 추정 모델이 사람의 관절 키포인트를 예측하는데 관절의 2차원 면적에 의해 키포인트별 𝜎, 즉, 표준 편차를 가지는 가우시안 커널(Gaussian Kernel)을 예측하는 방법을 제안한다. 각 관절 키포인트에 대해 다른 𝜎를 가지는 정답 히트맵(Ground Truth Heatmap)과 제안한 Gaussian Mixture Block를 모델에 추가해서 관절의 크기를 맞는 히트맵을 예측한다.

• The International Journal of Costume Culture
• /
• 제12권1호
• /
• pp.13-25
• /
• 2009

This research is progressed to look out for efficient expression-elements of eroticism used in advertisements. Since these expressions of eroticism appealing to sex which is one of the primitive instincts of mankind are increasing in advertisements of cosmetic products which are used more often by recent high-rate-growth and the elevation of living conditions. The most usual expression-elements of eroticism in advertisement are exposure, pose, fashion style, make up, hair style and color. To analyze those expression-elements we made four pieces of fashion advertisement photos with four different types and surveyed both fashion majored students and non-fashion majored students. We applied regression analysis, ANOVA, and frequency analysis to verify the hypothesis. We found that in eroticism, the pose was the most important cognitive feature among the expression-elements and degree of cognition are varied according to major field and sexual interest. As a result, degree of cognition which effected by expression-elements will be varied even in same advertisement. In particular, convincing that the pose was the significant factor of eroticism cognition, expression of eroticism in advertisement would be more diverse and daring.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.87-93
• /
• 2019

This paper presents a 6-DOF relocalization using a 3D laser scanner and a monocular camera. A relocalization problem in robotics is to estimate pose of sensor when a robot revisits the area. A deep convolutional neural network (CNN) is designed to regress 6-DOF sensor pose and trained using both RGB image and 3D point cloud information in end-to-end manner. We generate the new input that consists of RGB and range information. After training step, the relocalization system results in the pose of the sensor corresponding to each input when a new input is received. However, most of cases, mobile robot navigation system has successive sensor measurements. In order to improve the localization performance, the output of CNN is used for measurements of the particle filter that smooth the trajectory. We evaluate our relocalization method on real world datasets using a mobile robot platform.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2523-2538
• /
• 2017

In most of the existing literature, the definition of the class label has the following characteristics. First, the class label of the samples from the same object has an absolutely fixed value. Second, the difference between class labels of the samples from different objects should be maximized. However, the appearance of a face varies greatly due to the variations of the illumination, pose, and expression. Therefore, the previous definition of class label is not quite reasonable. Inspired by discriminative least squares regression algorithm (DLSR), a noisy label based discriminative least squares regression algorithm (NLDLSR) is presented in this paper. In our algorithm, the maximization difference between the class labels of the samples from different objects should be satisfied. Meanwhile, the class label of the different samples from the same object is allowed to have small difference, which is consistent with the fact that the different samples from the same object have some differences. In addition, the proposed NLDLSR is expanded to the kernel space, and we further propose a novel kernel noisy label based discriminative least squares regression algorithm (KNLDLSR). A large number of experiments show that our proposed algorithms can achieve very good performance.

• 드라이브 ㆍ 컨트롤
• /
• 제20권4호
• /
• pp.133-139
• /
• 2023

A weighing system calculates the bucket's excavation amount of an excavator. Usually, the excavation amount is computed by the excavator's motion equations with sensing data. But these motion equations have computing errors that are induced by assumptions to the linear systems and identification of the equation's parameters. To reduce computing errors, some commercial weighing system incorporates particular motion into the excavation process. This study introduces a linear regression model on an artificial neural network that has fewer predicted errors and doesn't need a particular pose during an excavation. Time serial data were gathered from a 30tons excavator's loading test. Then these data were preprocessed to be adjusted by MPL (Multi Layer Perceptron) or CNN (Convolutional Neural Network) based linear regression models. Each model was trained by changing hyperparameter such as layer or node numbers, drop-out rate, and kernel size. Finally ID-CNN-based linear regression model was selected.

• 방송공학회논문지
• /
• 제24권2호
• /
• pp.264-272
• /
• 2019

본 논문은 비디오로부터 추출한 프레임으로부터 3차원 인체 형상과 자세 복원을 수행하고 이를 시간 축에서 자연스럽고 부드러운 움직임을 나타내도록 보정하는 기법을 제안한다. 제안하는 기법은 우선 비디오로부터 추출한 개별 프레임으로부터 convolutional neural network을 이용하여 관절의 위치와 인체의 윤곽을 추정한다. 인체의 형상 및 자세는 매개변수 기반의 3차원 변형가능 모델(morphable model)을 2차원 영상으로 투영후 정합하여 최적의 매개변수 값을 추정한다. 이 때 각 프레임에 대한 복원이 개별적으로 수행되면 시간 축에서 자세의 연속성과 체형의 일관성이 보장되지 못하고 올바르지 못한 복원 결과가 나타난다. 제안하는 기법은 이러한 문제점을 보완하기 위하여 각 프레임으로부터 복원된 3차원 변형가능 모델의 주성분 매개변수의 분석 및 보간을 수행한다. 실험결과 3차원 인체 복원에 오류가 발생한 프레임에 대해 이전과 이후 프레임들 사이의 관계를 통해 오류가 보정되어 개선된 복원 결과를 얻을 수 있음을 보인다.

• Journal of International Society for Simulation Surgery
• /
• 제2권1호
• /
• pp.7-9
• /
• 2015

Purpose In the many face-related application such as head pose estimation, 3D face modeling, facial appearance manipulation, the robust and fast facial feature extraction is necessary. We present the facial feature extraction method based on shape regression and feature selection for real-time facial feature extraction. Materials and Methods The facial features are initialized by statistical shape model and then the shape of facial features are deformed iteratively according to the texture pattern which is selected on the feature pool. Results We obtain fast and robust facial feature extraction result with error less than 4% and processing time less than 12 ms. The alignment error is measured by average of ratio of pixel difference to inter-ocular distance. Conclusion The accuracy and processing time of the method is enough to apply facial feature based application and can be used on the face beautification or 3D face modeling.

• 자원ㆍ환경경제연구
• /
• 제10권4호
• /
• pp.619-632
• /
• 2001

The purpose of this study is to test the Kuznets Hypothesis on the relationship between environmental pollution and economic growth by using the panel data. The major results of the study can be summarized threefold as follows. First, previous studies can pose the risk of spurious regression because of the nature of non-stationery of the data used. Second, the result of the co-integration test indicates that the emission of $CO_2$ and per capita income are co-integrated. Finally, according to the results of OLS and DOLS estimation, the turning point in this study is set in far higher level of per capita income compared with those in previous studies.