• 한국정밀공학회지
• /
• 제21권1호
• /
• pp.159-166
• /
• 2004

Custom-tailored products are meant by the products having various sizes and shapes to meet the customer's different tastes or needs. Thus fabrication of custom-tailored products inherently involves inefficiency. To minimize this inefficiency, a new paradigm is proposed in this work. In this paradigm, different parts are grouped together according to their sizes and shapes. Then, representative shape of each group is derived and it will be used as the work-piece from which the parts in the group are machined. Once a new product is ordered, the optimal work-piece is selected through making similarity comparisons of new product and each representative shape. Then an effective NC tool-path is generated to machine only the different portions between the work-piece and the ordered product. The efficient machining conditions are also derived from this shape difference. By machining only the different portions between the work-piece and the ordered product, it saves time. Similarity comparison starts with the determination of the closest pose between two shapes in consideration. The closest pose is derived by comparing the ray distances while one shape is virtually rotated with respect to the other. Shape similarity value and overall similarity value calculated from ray distances are used for grouping. A prototype system based on the proposed methodology has been implemented and applied to the grouping and machining of the shoe lasts of various shapes and sizes.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.70-73
• /
• 2003

Custom-tailored products are meant by the products having various sizes and shapes to meet the customer's different tastes or needs. Thus fabrication of custom-tailored products inherently involves inefficiency. To minimize this inefficiency, a new paradigm is proposed in this work. In this paradigm. different paris are grouped together according to their sizes and shapes. Then, representative shape of each group is derived and it will be used as the work-piece from which the parts in the group are machined. Once a new product is ordered, the optimal work-piece is selected through making similarity comparisons of new product and each representative shape. Then an effective NC tool-path is generated to machine only the different portions between the work-piece and the ordered product. The efficient machining conditions are also derived from this shape difference. By machining only the different portions between the work-piece and the ordered product, it saves time. Similarity comparison starts with the determination of the closest pose between two shapes in consideration. The closest pose is derived by comparing the ray distances while one shape is virtually rotated with respect to the other. Shape similarity value and overall similarity value calculated from ray distances are used for grouping. A prototype system based on the proposed methodology has been implemented and applied to the grouping and machining of the shoe lasts of various shapes and sizes.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.1109-1116
• /
• 2020

사람이 따라 하는 능력을 평가하는 스코어는 아동의 발달 단계 혹은 골프, 무용 동작 등을 점검하는 좋은 수단이 될 수 있다. 또한, 이는 AR, VR 응용에서 HCI로도 활용될 수 있다. 본 논문에서는 동작을 주도해서 수행하는 시범자와 그 동작을 따라 하는 참여자 간의 동작 유사도를 평가하는 방안을 제시하고, 여기서 우리는 Openpose의 키포인트 벡터 유사도의 유클리디안 L2 거리를 활용하는 동작 유사도를 제안한다. 제안된 기법은 DTW를 사용하기 때문에 시간 지연차가 있는 동작에 유연하게 대처할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제28권1호
• /
• pp.39-47
• /
• 2023

본 논문에서는 골프 동영상 속 스윙 자세 사이의 유사도를 측정할 수 있는 방법을 제안한다. 딥러닝 기반 인공지능 기술이 컴퓨터 비전 분야에 효과적인 것이 알려지면서 동영상을 기반으로 한 스포츠 데이터 분석에 인공지능을 활용하기 위한 시도가 증가하고 있다. 본 연구에서는 딥러닝 기반의 자세 추정 모델을 사용하여 골프 스윙 동영상 속 사람의 관절 좌표를 획득하였고, 이를 바탕으로 각 스윙 구간별 유사도를 측정하였다. 제안한 방법의 평가를 위해 GolfDB 데이터셋의 Driver 스윙 동영상을 활용하였다. 총 36명의 선수에 대해 스윙 동영상들을 두 개씩 짝지어 스윙 유사도를 측정한 결과, 본인의 또 다른 스윙이 가장 유사하다고 평가한 경우가 26명이었으며, 이때의 유사도 평균 순위는 약 5위로 확인되었다. 이로부터 비슷한 동작을 수행하고 있는 경우에도 면밀히 유사도를 측정하는 것이 가능함을 확인할 수 있었다.

• 스마트미디어저널
• /
• 제13권4호
• /
• pp.16-22
• /
• 2024

투구는 야구의 시작이라 할 만큼 야구에서 주요한 부분을 차지한다. 투구 동작의 정확한 분석은 경기력 향상과 부상 예방 측면에서 매우 중요하다. 올바른 투구 동작을 분석할 때, 현재 주로 사용되는 모션캡처는 환경적으로 치명적인 단점들이 몇 가지 존재한다. 본 논문에서 우리는 이러한 단점들이 존재하는 모션캡처를 대체하기 위하여 RGB 기반의 Human Pose Estimation(HPE) 모델을 활용한 투구 동작의 분석을 제안하며 이에 대한 신뢰도를 검증하기 위해 모션캡처 데이터와 HPE 데이터의 관절 좌표를 Dynamic Time Warping(DTW) 알고리즘의 비교를 통해 두 데이터의 유사도를 검증하였다.

• 한국정보통신학회논문지
• /
• 제19권5호
• /
• pp.1199-1206
• /
• 2015

본 논문은 위상분석 기법을 이용하여, 스켈레톤의 크기, 조인트의 개수, 조인트 이름이 다른 모션들에 대한 유사도를 자동으로 계산하는 알고리즘을 제안한다. 제안하는 알고리즘은 스켈레톤의 계층구조와 기본포즈를 분석하여 k 개의 조인트 그룹으로 자동 분류하며, 분류된 조인트 그룹은 조인트의 전역 위치를 이용한 포인트 클라우드로 변환된다. 이 때, 비교 대상이 되는 각 그룹의 포인트 클라우드 내 포인트의 위치는 스켈레톤의 크기를 고려하여 자동으로 조정되며, 포인트 개수 또한 자동으로 일치하게 된다. 비교 대상이 되는 두 포인트 클라우드들은 유사도 계산을 위해 거리 값을 최소로 하는 최적의 2D변환 행렬을 구하게 되며, 이 행렬을 적용 후 나타나는 포인트 간의 거리의 합을 최종 유사도 값으로 결정한다. 실험을 통해, 제안하는 알고리즘은 스켈레톤의 크기, 조인트의 개수, 조인트 이름에 상관없이 유사도 값을 계산해 줌을 알 수 있었다.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권4호
• /
• pp.1424-1440
• /
• 2015

It is a challenging problem to search the intended images from a large number of candidates. Content based image retrieval (CBIR) is the most promising way to tackle this problem, where the most important topic is to measure the similarity of images so as to cover the variance of shape, color, pose, illumination etc. While previous works made significant progresses, their adaption ability to dataset is not fully explored. In this paper, we propose a similarity learning method on the basis of probabilistic generative model, i.e., probabilistic latent semantic analysis (PLSA). It first derives Fisher kernel, a function over the parameters and variables, based on PLSA. Then, the parameters are determined through simultaneously maximizing the log likelihood function of PLSA and the retrieval performance over the training dataset. The main advantages of this work are twofold: (1) deriving similarity measure based on PLSA which fully exploits the data distribution and Bayes inference; (2) learning model parameters by maximizing the fitting of model to data and the retrieval performance simultaneously. The proposed method (PLSA-FK) is empirically evaluated over three datasets, and the results exhibit promising performance.

• 인터넷정보학회논문지
• /
• 제21권3호
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• 한국멀티미디어학회논문지
• /
• 제24권5호
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.