• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.1
• /
• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• 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.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1109-1116
• /
• 2020

The matching score evaluating human copying ability can be a good measure to check children's developmental stages, or sports movements like golf swing and dance, etc. It also can be used as HCI for AR, VR applications. This paper presents a method to evaluate the motion similarity between demonstrator who initiates movement and participant who follows the demonstrator action. We present a quantification method of the similarity which utilizes Euclidean L2 distance of Openpose keypoins vector similarity. The proposed method adapts DTW, thus can flexibly cope with the time delayed motions.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.39-47
• /
• 2023

In this paper, we propose a method to measure the similarity between golf swings in videos. As it is known that deep learning-based artificial intelligence technology is effective in the field of computer vision, attempts to utilize artificial intelligence in video-based sports data analysis are increasing. In this study, the joint coordinates of a person in a golf swing video were obtained using a deep learning-based pose estimation model, and based on this, the similarity of each swing segment was measured. For the evaluation of the proposed method, driver swing videos from the GolfDB dataset were used. As a result of measuring swing similarity by pairing swing videos of a total of 36 players, 26 players evaluated that their other swing sequence was the most similar, and the average ranking of similarity was confirmed to be about 5th. This ensured that the similarity could be measured in detail even when the motion was performed similarly.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.16-22
• /
• 2024

Pitching is a major part of baseball, so much so that it can be said to be the beginning of baseball. Analysis of accurate pitching motions is very important in terms of performance improvement and injury prevention. When analyzing the correct pitching motion, the currently used motion capture method has several critical environmental drawbacks. In this paper, we propose analysis of pitching motion using the RGB-based Human Pose Estimation (HPE) model to replace motion capture, which has these shortcomings, and use motion capture data and HPE data to verify its reliability. The similarity of the two data was verified by comparing joint coordinates using the Dynamic Time Warping (DTW) algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1199-1206
• /
• 2015

This paper introduces an algorithm for computing similarity between two poses in the motion capture data with different scale of skeleton, different number of joints and different joint names. The proposed algorithm first performs the topological analysis on the skeleton hierarchy for classifying the joints into more meaningful groups. The global joints positions of each joint group then are aggregated into a point cloud. The number of joints and their positions are automatically adjusted in this process. Once we have two point clouds, the algorithm finds an optimal 2D transform matrix that transforms one point cloud to the other as closely as possible. Then, the similarity can be obtained by summing up all distance values between two points clouds after applying the 2D transform matrix. After some experiment, we found that the proposed algorithm is able to compute the similarity between two poses regardless of their scale, joint name and the number of joints.

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• 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)
• /
• v.9 no.4
• /
• 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.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• 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.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• 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.