• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.37-38
• /
• 2023

본 논문에서는 딥러닝을 기반으로 하는 키포인트 인식 모델을 산업용 품질검사 머신비전에 응용하는 방법을 제안한다. 전이학습 방법을 이용하여 딥러닝 모델의 인식률을 높이는 방법을 제시하였고, 전이시킨 특성 추출 모델에 대해 추가로 데이터 세트에 대한 학습을 진행하는 것이 특성추출 모델의 초기 ImageNet 가중치를 동결시켜 학습하는 것보다 학습 속도나 정확도가 높다는 것을 보여준다. 실험을 통해 딥러닝을 응용하는 산업용 품질 검사 공정에는 특성추출 모델의 추가 학습이 중요하다는 점을 확인할 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.35-36
• /
• 2022

본 논문은 딥러닝 사람 자세 추정 모델이 사람의 관절 키포인트를 예측하는데 관절의 2차원 면적에 의해 키포인트별 𝜎, 즉, 표준 편차를 가지는 가우시안 커널(Gaussian Kernel)을 예측하는 방법을 제안한다. 각 관절 키포인트에 대해 다른 𝜎를 가지는 정답 히트맵(Ground Truth Heatmap)과 제안한 Gaussian Mixture Block를 모델에 추가해서 관절의 크기를 맞는 히트맵을 예측한다.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.85-92
• /
• 2017

Recently, in the field of video surveillance, a Deep Learning based learning method has been applied to a method of detecting a moving person in a video and analyzing the behavior of a detected person. The human activity recognition, which is one of the fields this intelligent image analysis technology, detects the object and goes through the process of detecting the body keypoint to recognize the behavior of the detected object. In this paper, we propose a method for Body Keypoint Localization based on Object Detection using RGB-D information. First, the moving object is segmented and detected from the background using color information and depth information generated by the two cameras. The input image generated by rescaling the detected object region using RGB-D information is applied to Convolutional Pose Machines for one person's pose estimation. CPM are used to generate Belief Maps for 14 body parts per person and to detect body keypoints based on Belief Maps. This method provides an accurate region for objects to detect keypoints an can be extended from single Body Keypoint Localization to multiple Body Keypoint Localization through the integration of individual Body Keypoint Localization. In the future, it is possible to generate a model for human pose estimation using the detected keypoints and contribute to the field of human activity recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.187-194
• /
• 2021

A person's behavioral recognition is the recognition of what a person does according to joint movements. To this end, we utilize computer vision tasks that are utilized in image processing. Human behavior recognition is a safety accident response service that combines deep learning and CCTV, and can be applied within the safety management site. Existing studies are relatively lacking in behavioral recognition studies through human joint keypoint extraction by utilizing deep learning. There were also problems that were difficult to manage workers continuously and systematically at safety management sites. In this paper, to address these problems, we propose a method to recognize risk behavior using only joint keypoints and joint motion information. AlphaPose, one of the pose estimation methods, was used to extract joint keypoints in the body part. The extracted joint keypoints were sequentially entered into the Long Short-Term Memory (LSTM) model to be learned with continuous data. After checking the behavioral recognition accuracy, it was confirmed that the accuracy of the "Lying Down" behavioral recognition results was high.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.29-30
• /
• 2024

본 논문은 Krafton의 PUBG: BATTLEGROUNDS 게임에서 플레이어 분류를 목표로 하며, 포즈 추정기술을 사용하여 일반 플레이어와 봇을 구분한다. 이는 게임에서 직접 수집한 비디오 데이터를 기반으로 하며, 다음과 같은 두 가지 접근 방식을 제안한다. 첫 번째 방법은 동작 시퀀스 분석을 통해, 사용자의 특정동작 패턴을 식별하고 로지스틱 회귀 모델을 활용해 사용자 유형을 분류한다. 두 번째 방법은 YOLO-pose 모델을 사용하여 비디오 데이터에서 키포인트를 추출하고, 이를 LSTM 모델에 적용하여 프레임별로 사용자의 유형을 분류한다. 이러한 이중 접근 방식은 게임의 공정성과 사용자 경험을 향상시키는 새로운 도구를 제공하며, 보다 안전한 게임 환경에 기여할 수 있다. 이 연구는 게임 산업뿐만 아니라 보안 및 모니터링 분야에서도 동작 분석에 대한 혁신적인 접근 방식으로 활용될 잠재력을 가지고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.157-160
• /
• 2022

딥러닝이 각광받기 시작하면서 인간의 자세와 행동을 인식하고 분류하기 위한 인공지능 기술 또한 급속도로 발전하게 되었다. 영상에서 인간의 자세를 디지털 데이터로 표현할 때 인체의 주요 관절점의 위치와 연결관계를 나타내는 스켈레톤 표현 방식을 주로 사용한다. 본 논문에서는 스켈레톤 데이터에 비밀 메시지를 은닉할 수 있는 스테가노그라피 알고리즘에 대해 소개하고, 스켈레톤을 구성하는 주요 관절점 키포인트를 조작했을 때 행동 인식 인공지능 모델이 어떻게 반응하는지 살펴봄으로써 스켈레톤 데이터에 대한 스테가노그라피 알고리즘의 특성과 보안성에 대해 논의한다.

• 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.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.477-481
• /
• 2008

Place recognition is necessary for a mobile user to be provided with place-dependent information. This paper proposes real-time video based place recognition system that identifies users' current place while moving in the building. As for the feature extraction of a scene, there have been existing methods based on global feature analysis that has drawback of sensitive-ness for the case of partial occlusion and noises. There have also been local feature based methods that usually attempted object recognition which seemed hard to be applied in real-time system because of high computational cost. On the other hand, researches using statistical methods such as HMM(hidden Markov models) or bayesian networks have been used to derive place recognition result from the feature data. The former is, however, not practical because it requires huge amounts of efforts to gather the training data while the latter usually depends on object recognition only. This paper proposes a combined approach of global and local feature analysis for feature extraction to complement both approaches' drawbacks. The proposed method is applied to a mobile information system and shows real-time performance with competitive recognition result.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.3
• /
• pp.393-400
• /
• 2009

Recently demand for the 3D modeling technology to reconstruct real world is getting increasing. However, existing geospatial data are mainly based on the 2D space. In addition, most of the geospatial data provide geometric information only. In consequence, there are limits in various applications to utilize information from those data and to reconstruct the real world in 3D space. Therefore, it is required to develop efficient 3D mapping methodology and data for- mat to establish geospatial database. Especially digital elevation model(DEM) is one of the essential geospatial data, however, DEM provides only spatially distributed 3D coordinates of the natural and artificial surfaces. Moreover, most of DEMs are generated without considering terrain properties such as surface roughness, terrain type, spatial resolution, feature and so on. This paper suggests adaptive and flexible geospatial data format that has possibility to include various information such as terrain characteristics, multiple resolutions, interpolation methods, break line information, model keypoints, and other physical property. The study area was categorized into mountainous area, gently rolling area, and flat area by taking the terrain characteristics into account with respect to terrain roughness. Different resolutions and interpolation methods were applied to each area. Finally, a 3D digital map derived from aerial photographs was integrated with the geospatial data and visualized.