• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.667-670
• /
• 2020

최근에는 증강현실, 로봇공학 등의 분야에서 객체의 위치 검출 이외에도, 객체의 자세에 대한 추정이 요구되고 있다. 객체의 자세 정보가 포함된 데이터셋은 위치 정보만 포함된 데이터셋에 비하여 상대적으로 매우 적기 때문에 인공 신경망 구조를 활용하기 어려운 측면이 있으나, 최근에 들어서는 기계학습 기반의 자세 추정 알고리즘들이 여럿 등장하고 있다. 본 논문에서는 이 가운데 Dense 6d Pose Object detector (DPOD) [11]의 구조를 기반으로 하여 가구의 조립 설명서에 그려진 가구 부품들의 자세를 추정하고자 한다. DPOD [11]는 입력으로 RGB 영상을 받으며, 해당 영상에서 자세를 추정하고자 하는 객체의 영역에 해당하는 픽셀들을 추정하고, 객체의 영역에 해당되는 각 픽셀에서 해당 객체의 3D 모델의 UV map 값을 추정한다. 이렇게 픽셀 개수만큼의 2D - 3D 대응이 생성된 이후에는, RANSAC과 PnP 알고리즘을 통해 RGB 영상에서의 객체와 객체의 3D 모델 간의 변환 관계 행렬이 구해지게 된다. 본 논문에서는 사전에 정해진 24개의 자세 후보들을 기반으로 가구 부품의 3D 모델을 2D에 투영한 RGB 영상들로 인공 신경망을 학습하였으며, 평가 시에는 실제 조립 설명서에서의 가구 부품의 자세를 추정하였다. 실험 결과 IKEA의 Stefan 의자 조립 설명서에 대하여 100%의 ADD score를 얻었으며, 추정 자세가 자세 후보군 중 정답 자세에 가장 근접한 경우를 정답으로 평가했을 때 100%의 정답률을 얻었다. 제안하는 신경망을 사용하였을 때, 가구 조립 설명서에서 가구 부품의 위치를 찾는 객체 검출기(object detection network)와, 각 개체의 종류를 구분하는 객체 리트리벌 네트워크(retrieval network)를 함께 사용하여 최종적으로 가구 부품의 자세를 추정할 수 있다.

• Journal of Internet of Things and Convergence
• /
• v.10 no.5
• /
• pp.19-26
• /
• 2024

This study presents and verifies an easy, fast, and relatively cost-effective method for 6D pose estimation using industrial robots for bin picking in the manufacturing sector. Specifically, it details a method involving the integration of industrial robots with 2D cameras to ① acquire multi-view images of objects and collect training data, ② select variables from the collected data and implement a linear regression model, and ③ apply the trained model to estimate, verify, and evaluate the 6D pose of objects on industrial robots. The proposed data collection method and implemented linear regression model demonstrated statistically significant results. The estimated 6D poses were validated against ground true values and evaluated in their application to industrial robots, confirming their validity. By using feature point information extracted from images instead of direct image inputs as inputs to the regression model, the data size was reduced, enabling direct embedding on the robot. This research approaches the problem of spatial coordinates in 3D from a data analysis perspective, rather than from geometrical or computer vision perspectives.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• 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.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.41-51
• /
• 2018

Recently, in the field of video surveillance, deep learning based learning method is applied to intelligent video surveillance system, and various events such as crime, fire, and abnormal phenomenon can be robustly detected. However, since occlusion occurs due to the loss of 3d information generated by projecting the 3d real-world in 2d image, it is need to consider the occlusion problem in order to accurately detect the object and to estimate the pose. Therefore, in this paper, we detect moving objects by solving the occlusion problem of object detection process by adding depth information to existing RGB information. Then, using the convolution neural network in the detected region, the positions of the 14 keypoints of the human joint region can be predicted. Finally, in order to solve the self-occlusion problem occurring in the pose estimation process, the method for 3d human pose estimation is described by extending the range of estimation to the 3d space using the predicted result of 2d keypoint and the deep neural network. In the future, the result of 2d and 3d pose estimation of this research can be used as easy data for future human behavior recognition and contribute to the development of industrial technology.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.100-105
• /
• 2021

본 논문에서는 뉴럴넷 기반 렌더링 비교 방식을 사용하여 가구 조립 설명서에 표기된 부품의 자세를 추정하는 방법을 제안한다. 제안하는 방법은 부품의 자세를 임의로 가정한 후, 가정한 자세로 투사한 부품의 영상과 설명서의 부품 영상을 비교하여 두 영상의 부품을 일치시키는 자세 변화를 추정하는 방식으로 진행된다. 또한, 설명서에 반복적으로 모델을 적용하여 부품의 자세를 점차적으로 정확하게 보정하는 방식을 사용하였으며, 네트워크의 구성 및 자세 추정에 사용되는 목표 함수를 다양하게 실험하여 성능을 비교하였다. 본 연구에선 IKEA 의 Stefan 의자 조립 설명서의 부품 데이터셋으로 실험을 진행하였으며, 해당 데이터셋에 대하여 제안하는 방법이 정확하게 자세를 보정함을 확인하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.7
• /
• pp.659-666
• /
• 2016

Magnetic disturbance is one of the main factors that deteriorate the accuracy of orientation estimation methods based on inertial/magnetic sensor signals. This paper proposes a parallel Kalman filter(KF) that explicitly detects magnetic disturbances and thus can accurately estimate 3D orientation in magnetically disturbed environments. Due to the parallel nature of the proposed KF, even severe magnetic disturbances only affect yaw estimation, while roll and pitch values remain accurate. Consequently, the proposed KF can be effectively used in various applications that involve magnetically inhomogeneous environments, such as robots, ships, and planes.

• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.178-179
• /
• 2018

증강현실 환경에서 현실 세계의 물체를 포착하여 디지털화 시키는 것은 몰입감 향상에 있어 매우 중요한 기술이다. Faster R - CNN 은 영상에서 여러 물체를 인식하는 기술 중 하나이며, 지금껏 많은 응용 기술의 개발과 함께 많은 연구가 진행되고 있다. 본 논문은 증강현실 환경에서 평면물체의 2D 변환관계를 설명하는 Homography 와 Faster R - CNN 을 활용하여 여러 개의 비콘에 대한 6 자유도(6DOF) 를 추정하는 방법을 제안한다. 또한 증강현실에서 주로 사용되는 마커 기술에 존재하는 단점들을 극복할 수 있는 비콘 구조를 소개하고 여러 개의 비콘을 용이하게 관리하는 시스템을 제안한다.