• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.187-188
• /
• 2021

본 논문에서는 Openpose의 신뢰도를 이용해 3D pose estimation의 정확도를 높이는 방법을 제안한다. 모델의 앞뒤양옆 네 방향에서 pose estimation의 진행하기 위해 3D 모델에 AABB(Axis Aligned Bound Box)를 생성한 다음, box의 네 옆면으로 모델을 투영시킨다. 각 면에 투사된 2D image에 대해 Openpose 2D pose estimation의 진행한다. 네 면에서 생성한 2D 스켈레톤들의 평균을 통해 3D 상의 교차점을 획득한다. Openpose에서 제공하는 신뢰도(confidence)를 이용하여 잘못 나온 2D 관절을 제외하는 것으로 더 정확한 pose estimation의 수행하였다. 실험적인 방법을 통해 신뢰도 0.45 이상의 값을 가지는 joint 만을 사용해 3D 교차점을 구함으로써 3D pose estimation의 정확도를 높였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.559-575
• /
• 2023

3D human pose estimation is widely applied in various fields, including action recognition, sports analysis, and human-computer interaction. 3D human pose estimation has achieved significant progress with the introduction of convolutional neural network (CNN). Recently, several researches have proposed the use of multiview approaches to avoid occlusions in single-view approaches. However, as the number of cameras increases, a 3D pose estimation system relying on a CNN may lack in computational resources. In addition, when a single host system uses multiple cameras, the data transition speed becomes inadequate owing to bandwidth limitations. To address this problem, we propose a distributed real-time 3D pose estimation framework based on asynchronous multiple cameras. The proposed framework comprises a central server and multiple edge devices. Each multiple-edge device estimates a 2D human pose from its view and sendsit to the central server. Subsequently, the central server synchronizes the received 2D human pose data based on the timestamps. Finally, the central server reconstructs a 3D human pose using geometrical triangulation. We demonstrate that the proposed framework increases the percentage of detected joints and successfully estimates 3D human poses in real-time.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.76-77
• /
• 2022

본 논문에서는 다시점에서의 자세 추정 결과를 정합하여 3D 볼류메트릭 데이터 시퀀스의 3D 자세 추정 결과의 떨림을 줄이는 방법을 제안한다. 볼류메트릭 모델을 중심으로 원을 그리며 일정 각도 간격의 시점에서 본 모델을 평면에 투사한다. 투영하여 얻은 2D 영상에 대해 Openpose를 이용하여 2D 자세 추정을 진행한 뒤, 2D 관절 정보를 정합하여 3D 관절 위치를 국한한다. 각도 간격에 따라 다른 3D 관절의 떨림의 정도를 수치화하여 표로 나타내고, 안정적인 결과를 위한 최소 조건을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2042-2059
• /
• 2019

Digital shadow puppet has traditionally relied on expensive motion capture equipments and complex design. In this paper, a low-cost driven technique is presented, that captures human pose estimation data with simple camera from real scenarios, and use them to drive virtual Chinese shadow play in a 2.5D scene. We propose a special method for extracting human pose data for driving virtual Chinese shadow play, which is called 2.5D human pose estimation. Firstly, we use the 3D human pose estimation method to obtain the initial data. In the process of the following transformation, we treat the depth feature as an implicit feature, and map body joints to the range of constraints. We call the obtain pose data as 2.5D pose data. However, the 2.5D pose data can not better control the shadow puppet directly, due to the difference in motion pattern and composition structure between real pose and shadow puppet. To this end, the 2.5D pose data transformation is carried out in the implicit pose mapping space based on self-network and the final 2.5D pose expression data is produced for animating shadow puppets. Experimental results have demonstrated the effectiveness of our new method.

• 전기학회논문지
• /
• 제59권2호
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• 자동차안전학회지
• /
• 제14권3호
• /
• pp.71-76
• /
• 2022

In autonomous driving cars, 3D pose estimation can be one of the effective methods to enhance safety control for OOP (Out of Position) passengers. There have been many studies on human pose estimation using a camera. Previous methods, however, have limitations in automotive applications. Due to unexplainable failures, CNN methods are unreliable, and other methods perform poorly. This paper proposes robust real-time multi-human 3D pose estimation architecture in vehicle using monocular RGB camera. Using particle filter, our approach integrates CNN 2D/3D pose measurements with available information in vehicle. Computer simulations were performed to confirm the accuracy and robustness of the proposed algorithm.

• 제어로봇시스템학회논문지
• /
• 제14권2호
• /
• pp.133-140
• /
• 2008

In this paper, a small and effective attitude estimation system for a humanoid robot was developed. Four small inertial sensors were packed and used for inertial measurements(3D accelerometer and three 1D gyroscopes.) An effective 3D pose estimation algorithm for low cost DSP using an extended Kalman filter was developed and evaluated. The 3D pose estimation algorithm has a very simple structure composed by 3 modules of a linear acceleration estimator, an external acceleration detector and an pseudo-accelerometer output estimator. The algorithm also has an effective switching structure based on probability and simple feedback loop for the extended Kalman filter. A special test equipment using linear motor for the testing of the 3D pose sensor was developed and the experimental results showed its very fast convergence to real values and effective responses. Popular DSP of TMS320F2812 was used to calculate robot's 3D attitude and translated acceleration, and the whole system were packed in a small size for humanoids robots. The output of the 3D sensors(pitch, roll, 3D linear acceleration, and 3D angular rate) can be transmitted to a humanoid robot at 200Hz frequency.

• 정보보호학회논문지
• /
• 제24권4호
• /
• pp.607-616
• /
• 2014

현재 영상감시 시스템에서 얼굴 인식을 통한 사람의 신원 확인은 정면 얼굴이 아닌 관계로 매우 어려운 기술에 속한다. 일반적인 사람들의 얼굴 영상과 입력된 얼굴 영상을 비교하여 유사도를 파악하고 신원을 확인 하는 기술은 각도의 차이에 따라 정확도의 오차가 심해진다. 이런 문제를 해결하기 위해 본 논문에서는 POSIT을 사용하여 얼굴 포즈 측정을 하고, 추정된 각도를 이용하여 3D 얼굴 영상을 제작 후 매칭 하여 일반적인 정면 영상끼리의 매칭이 아닌 rotated face를 이용한 매칭을 해보기로 한다. 얼굴을 매칭 하는 데는 상용화된 얼굴인식 알고리즘을 사용하였다. 얼굴 포즈 추정은 $10^{\circ}$이내의 오차를 보였고, 얼굴인증 성능은 약 95% 정도임을 확인하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제36권4호
• /
• pp.512-519
• /
• 2012

본 논문은 원형 링 패턴의 인식에 기반한 물체의 3차원 위치/자세 추정 시스템을 제안한다. 단일 비전 기반의 자세추정 문제를 다루기 위하여, 본 논문은 물체인식 과정의 단순화를 위한 원형 링 패턴의 설계방법을 기술한다. 또한, 본 논문은 2차원 투영공간에서 원형 링 패턴이 가지는 기하학적 변환관계를 적극 활용한 실내용 위치/자세 추정 절차를 상세히 설명한다. 제안된 방법은 쿼드로터형 비행체의 3차원 위치/자세 추정에 적용되며 정확도 및 정밀도 분석을 통해 평가된다.

• 로봇학회논문지
• /
• 제12권1호
• /
• pp.33-41
• /
• 2017

We present a region-based approach for accurate pose estimation of small mechanical components. Our algorithm consists of two key phases: Multi-view object co-segmentation and pose estimation. In the first phase, we explain an automatic method to extract binary masks of a target object captured from multiple viewpoints. For initialization, we assume the target object is bounded by the convex volume of interest defined by a few user inputs. The co-segmented target object shares the same geometric representation in space, and has distinctive color models from those of the backgrounds. In the second phase, we retrieve a 3D model instance with correct upright orientation, and estimate a relative pose of the object observed from images. Our energy function, combining region and boundary terms for the proposed measures, maximizes the overlapping regions and boundaries between the multi-view co-segmentations and projected masks of the reference model. Based on high-quality co-segmentations consistent across all different viewpoints, our final results are accurate model indices and pose parameters of the extracted object. We demonstrate the effectiveness of the proposed method using various examples.