• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.3
• /
• pp.86-95
• /
• 2009

SIFT is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vertices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3D image reconstructions and intelligent vision system for robots. In this paper, we implement a hardware to sift feature detection algorithm for real time processing in embedded systems. We estimate that the hardware implementation give a performance 25ms of $1,280{\times}960$ image and 5ms of $640{\times}480$ image at 100MHz. And the implemented hardware consumes 45,792 LUTs(85%) with Synplify 8.li synthesis tool.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• 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.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.