• 한국산업융합학회 논문집
• /
• 제26권1호
• /
• pp.113-119
• /
• 2023

In this paper, we propose an optimization of a pose estimation deep learning model for recognition of abnormal behavior in unmanned stores using radio frequencies. The radio frequency use millimeter wave in the 30 GHz to 300 GHz band. Due to the short wavelength and strong straightness, it is a frequency with less grayness and less interference due to radio absorption on the object. A millimeter wave radar is used to solve the problem of personal information infringement that may occur in conventional CCTV image-based pose estimation. Deep learning-based pose estimation models generally use convolution neural networks. The convolution neural network is a combination of convolution layers and pooling layers of different types, and there are many cases of convolution filter size, number, and convolution operations, and more cases of combining components. Therefore, it is difficult to find the structure and components of the optimal posture estimation model for input data. Compared with conventional millimeter wave-based posture estimation studies, it is possible to explore the structure and components of the optimal posture estimation model for input data using genetic algorithms, and the performance of optimizing the proposed posture estimation model is excellent. Data are collected for actual unmanned stores, and point cloud data and three-dimensional keypoint information of Kinect Azure are collected using millimeter wave radar for collapse and property damage occurring in unmanned stores. As a result of the experiment, it was confirmed that the error was moored compared to the conventional posture estimation model.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.508-515
• /
• 2012

본 논문은 Active Appearance Model(AAM)을 사용하여 주어진 얼굴영상의 포즈추정과 임의 포즈합성 방법을 설명한다. AAM은 다양한 응용분야에 성공적으로 적용되어지고 있는 예제기반 학습모델로 예제들의 변화정도를 학습한다. 그러나 하나의 모델로는 각도 변화가 큰 포즈 변화량을 수용하기 어렵다. 본 논문은 좁은 범위의 각도 변화를 다루는 모델을 포즈별로 생성한다. 주어진 포즈 얼굴을 다룰 수 있는 모델을 이용하여 정확한 포즈추정과 합성이 가능하다. 이때 합성하고자 하는 포즈의 각도가 포즈 추정을 위해 사용된 모델에 학습되어 있지 않은 경우, 미리 학습된 모델간의 선형관계를 통해 문제를 해결한다. Yale B 공개 얼굴 데이터베이스에 대한 실험을 통해 포즈추정 및 합성 정확도를 보이고, 자체 수집한 포즈변화가 큰 얼굴영상에 대한 성공적인 정면 합성 결과를 제시한다.

• Journal of Astronomy and Space Sciences
• /
• 제41권2호
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.

• 방송공학회논문지
• /
• 제27권2호
• /
• pp.174-184
• /
• 2022

3차원 휴먼 자세 추정 모델은 다시점 모델과 단시점 모델로 분류될 수 있다. 일반적으로 다시점 모델은 단시점 모델에 비하여 뛰어난 자세 추정 성능을 보인다. 단시점 모델의 경우 3차원 자세 추정 성능의 향상은 많은 양의 학습 데이터를 필요로 한다. 하지만 3차원 자세에 대한 참값을 획득하는 것은 쉬운 일이 아니다. 이러한 문제를 다루기 위해, 우리는 다시점 모델로부터 다시점 휴먼 자세 데이터에 대한 의사 참값을 생성하고, 이를 단시점 모델의 학습에 활용하는 방법을 제안한다. 또한, 우리는 각각의 다시점 영상으로부터 추정된 자세의 일관성을 고려하는 다시점 일관성 손실함수를 제안하여, 이것이 단시점 모델의 효과적인 학습에 도움을 준다는 것을 보인다. Human3.6M과 MPI-INF-3DHP 데이터셋을 사용한 실험은 제안하는 방법이 3차원 휴먼 자세 추정을 위한 단시점 모델의 학습에 효과적임을 보여준다.

• 한국재난정보학회 논문집
• /
• 제20권2호
• /
• pp.302-314
• /
• 2024

연구목적: 본 연구는 지하공동구 내 다수 작업자의 낙상을 자동으로 판별하기 위한 Top-down 방식의 딥러닝 자세 추정 모델 기반 낙상 검출 모델을 제안하고, 제안 모델의 성능을 평가한다. 연구방법: Top-down 방식의 자세 추정모델 중 하나인 YOLOv8-pose로부터 추론된 결과와 낙상 판별 규칙을 결합한 모델을 제시하고, 지하공동구 내 2인 이하 작업자가 출현한 기립 및 낙상 이미지에 대해 모델 성능지표를 평가하였다. 또한 동일한 방법으로 Bottom-up 방식 자세추정모델(OpenPose)을 적용한 결과를 함께 분석하였다. 두 모델의 낙상 검출 결과는 각 딥러닝 모델의 작업자 인식 성능에 의존적이므로, 작업자 쓰러짐과 함께 작업자 존재 여부에 대한 성능지표도 함께 조사하였다. 연구결과: YOLOv8-pose와 OpenPose의 모델의 작업자 인식 성능은 F1-score 기준으로 각각 0.88, 0.71로 두 모델이 유사한 수준이었으나, 낙상 규칙을 적용함에 따라 0.71, 0.23로 저하되었다. 작업자의 신체 일부만 검출되거나 작업자간 구분을 실패하여, OpenPose 기반 낙상 추론 모델의 성능 저하를 야기한 것으로 분석된다. 결론: Top-down 방식의 딥러닝 자세 추정 모델을 사용하는 것이 신체 관절점 인식 및 개별 작업자 구분 측면에서 지하공동구 내 작업자 낙상 검출에 효과적이라 판단된다.

• 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.

• 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.

• 로봇학회논문지
• /
• 제11권4호
• /
• pp.226-234
• /
• 2016

In this study, a model-referenced underwater navigation algorithm is proposed for high-precise underwater navigation using monocular vision near underwater structures. The main idea of this navigation algorithm is that a 3D model-based pose estimation is combined with the inertial navigation using an extended Kalman filter (EKF). The spatial information obtained from the navigation algorithm is utilized for enabling the underwater robot to navigate near underwater structures whose geometric models are known a priori. For investigating the performance of the proposed approach the model-referenced navigation algorithm was applied to an underwater robot and a set of experiments was carried out in a water tank.

• International journal of advanced smart convergence
• /
• 제7권2호
• /
• pp.95-100
• /
• 2018

In this paper, we propose a binarized multi-scale module to accelerate the speed of the pose estimating deep neural network. Recently, deep learning is also used for fine-tuned tasks such as pose estimation. One of the best performing pose estimation methods is based on the usage of two neural networks where one computes the heat maps of the body parts and the other computes the part affinity fields between the body parts. However, the convolution filtering with a large kernel filter takes much time in this model. To accelerate the speed in this model, we propose to change the large kernel filters with binarized multi-scale modules. The large receptive field is captured by the multi-scale structure which also prevents the dropdown of the accuracy in the binarized module. The computation cost and number of parameters becomes small which results in increased speed performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제2권2호
• /
• pp.120-133
• /
• 2008

This paper presents a novel approach for facial motion tracking and facial expression cloning to create a realistic facial animation of a 3D avatar. The exact head pose estimation and facial expression tracking are critical issues that must be solved when developing vision-based computer animation. In this paper, we deal with these two problems. The proposed approach consists of two phases: dynamic head pose estimation and facial expression cloning. The dynamic head pose estimation can robustly estimate a 3D head pose from input video images. Given an initial reference template of a face image and the corresponding 3D head pose, the full head motion is recovered by projecting a cylindrical head model onto the face image. It is possible to recover the head pose regardless of light variations and self-occlusion by updating the template dynamically. In the phase of synthesizing the facial expression, the variations of the major facial feature points of the face images are tracked by using optical flow and the variations are retargeted to the 3D face model. At the same time, we exploit the RBF (Radial Basis Function) to deform the local area of the face model around the major feature points. Consequently, facial expression synthesis is done by directly tracking the variations of the major feature points and indirectly estimating the variations of the regional feature points. From the experiments, we can prove that the proposed vision-based facial expression cloning method automatically estimates the 3D head pose and produces realistic 3D facial expressions in real time.