• Title/Summary/Keyword: Human Pose Estimation

Search Result 119, Processing Time 0.021 seconds

Ordinal Depth Based Deductive Weakly Supervised Learning for Monocular 3D Human Pose Estimation (단안 이미지로부터 3D 사람 자세 추정을 위한 순서 깊이 기반 연역적 약지도 학습 기법)

  • Youngchan Lee;Gyubin Lee;Wonsang You
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2024.05a
    • /
    • pp.826-829
    • /
    • 2024
  • 3D 사람 자세 추정 기술은 다양한 응용 분야에서의 높은 활용성으로 인해 대량의 학습 데이터가 수집되어 딥러닝 모델 연구가 진행되어 온 반면, 동물 자세 추정의 경우 3D 동물 데이터의 부족으로 인해 관련 연구는 극히 미진하다. 본 연구는 동물 자세 추정을 위한 예비연구로서, 3D 학습 데이터가 없는 상황에서 단일 이미지로부터 3D 사람 자세를 추정하는 딥러닝 기법을 제안한다. 이를 위하여 사전 훈련된 다중 시점 학습모델을 사용하여 2D 자세 데이터로부터 가상의 다중 시점 데이터를 생성하여 훈련하는 연역적 학습 기반 교사-학생 모델을 구성하였다. 또한, 키포인트 깊이 정보 대신 2D 이미지로부터 레이블링 된 순서 깊이 정보에 기반한 손실함수를 적용하였다. 제안된 모델이 동물데이터에서 적용 가능한지 평가하기 위해 실험은 사람 데이터를 사용하여 이루어졌다. 실험 결과는 제안된 방법이 기존 단안 이미지 기반 모델보다 3D 자세 추정의 성능을 개선함을 보여준다.

Human Legs Motion Estimation by using a Single Camera and a Planar Mirror (단일 카메라와 평면거울을 이용한 하지 운동 자세 추정)

  • Lee, Seok-Jun;Lee, Sung-Soo;Kang, Sun-Ho;Jung, Soon-Ki
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.16 no.11
    • /
    • pp.1131-1135
    • /
    • 2010
  • This paper presents a method to capture the posture of the human lower-limbs on the 3D space by using a single camera and a planar mirror. The system estimates the pose of the camera facing the mirror by using four coplanar IR markers attached on the planar mirror. After that, the training space is set up based on the relationship between the mirror and the camera. When a patient steps on the weight board, the system obtains relative position between patients' feet. The markers are attached on the sides of both legs, so that some markers are invisible from the camera due to the self-occlusion. The reflections of the markers on the mirror can partially resolve the above problem with a single camera system. The 3D positions of the markers are estimated by using the geometric information of the camera on the training space. Finally the system estimates and visualizes the posture and motion of the both legs based on the 3D marker positions.

Armed person detection using Deep Learning (딥러닝 기반의 무기 소지자 탐지)

  • Kim, Geonuk;Lee, Minhun;Huh, Yoojin;Hwang, Gisu;Oh, Seoung-Jun
    • Journal of Broadcast Engineering
    • /
    • v.23 no.6
    • /
    • pp.780-789
    • /
    • 2018
  • Nowadays, gun crimes occur very frequently not only in public places but in alleyways around the world. In particular, it is essential to detect a person armed by a pistol to prevent those crimes since small guns, such as pistols, are often used for those crimes. Because conventional works for armed person detection have treated an armed person as a single object in an input image, their accuracy is very low. The reason for the low accuracy comes from the fact that the gunman is treated as a single object although the pistol is a relatively much smaller object than the person. To solve this problem, we propose a novel algorithm called APDA(Armed Person Detection Algorithm). APDA detects the armed person using in a post-processing the positions of both wrists and the pistol achieved by the CNN-based human body feature detection model and the pistol detection model, respectively. We show that APDA can provide both 46.3% better recall and 14.04% better precision than SSD-MobileNet.

Driver Group Clustering Technique and Risk Estimation Method for Traffic Accident Prevention

  • Tae-Wook Kim;Ji-Woong Yang;Hyeon-Jin Jung;Han-Jin Lee;Ellen J. Hong
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.8
    • /
    • pp.53-58
    • /
    • 2024
  • Traffic accidents are not only a threat to human lives but also pose significant societal costs. Recently, research has been conducted to address the issue of traffic accidents by predicting the risk using deep learning technology and spatiotemporal information of roads. However, while traffic accidents are influenced not only by the spatiotemporal information of roads but also by human factors, research on the latter has been relatively less active. This paper analyzes driver groups and characteristics by applying clustering techniques to a traffic accident dataset and proposes and applies a method to calculate the Risk Level for each driver group and characteristic. In this process, the preprocessing technique suggested in this paper demonstrates a higher Silhouette Score of 0.255 compared to the commonly used One-Hot Embedding & Min-Max Scaling techniques, indicating its suitability as a preprocessing method.

Training Network Design Based on Convolution Neural Network for Object Classification in few class problem (소 부류 객체 분류를 위한 CNN기반 학습망 설계)

  • Lim, Su-chang;Kim, Seung-Hyun;Kim, Yeon-Ho;Kim, Do-yeon
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.21 no.1
    • /
    • pp.144-150
    • /
    • 2017
  • Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

The process of estimating user response to training stimuli of joint attention using a robot (로봇활용 공동 주의 훈련자극에 대한 사용자 반응상태를 추정하는 프로세스)

  • Kim, Da-Young;Yun, Sang-Seok
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.25 no.10
    • /
    • pp.1427-1434
    • /
    • 2021
  • In this paper, we propose a psychological state estimation process that computes children's attention and tension in response to training stimuli. Joint attention was adopted as the training stimulus required for behavioral intervention, and the Discrete trial training (DTT) technique was applied as the training protocol. Three types of training stimulation contents are composed to check the user's attention and tension level and provided mounted on a character-shaped tabletop robot. Then, the gaze response to the user's training stimulus is estimated with the vision-based head pose recognition and geometrical calculation model, and the nervous system response is analyzed using the PPG and GSR bio-signals using heart rate variability(HRV) and histogram techniques. Through experiments using robots, it was confirmed that the psychological response of users to training contents on joint attention could be quantified.

Real-Time Joint Animation Production and Expression System using Deep Learning Model and Kinect Camera (딥러닝 모델과 Kinect 카메라를 이용한 실시간 관절 애니메이션 제작 및 표출 시스템 구축에 관한 연구)

  • Kim, Sang-Joon;Lee, Yu-Jin;Park, Goo-man
    • Journal of Broadcast Engineering
    • /
    • v.26 no.3
    • /
    • pp.269-282
    • /
    • 2021
  • As the distribution of 3D content such as augmented reality and virtual reality increases, the importance of real-time computer animation technology is increasing. However, the computer animation process consists mostly of manual or marker-attaching motion capture, which requires a very long time for experienced professionals to obtain realistic images. To solve these problems, animation production systems and algorithms based on deep learning model and sensors have recently emerged. Thus, in this paper, we study four methods of implementing natural human movement in deep learning model and kinect camera-based animation production systems. Each method is chosen considering its environmental characteristics and accuracy. The first method uses a Kinect camera. The second method uses a Kinect camera and a calibration algorithm. The third method uses deep learning model. The fourth method uses deep learning model and kinect. Experiments with the proposed method showed that the fourth method of deep learning model and using the Kinect simultaneously showed the best results compared to other methods.

Biomarkers for Canine Mammary Tumors (반려견 유선종양 바이오 마커)

  • Chan-Ho Lee;Young Sun Choi;Suk Jun Lee;Sung-Hak Kim
    • Journal of Life Science
    • /
    • v.34 no.6
    • /
    • pp.434-441
    • /
    • 2024
  • Mammary gland tumors are the most common tumors detected in non-spayed female dogs and pose a significant clinical challenge. Due to the strong similarity between canine mammary tumors (CMT) and human breast cancer (HBC), biomarkers identified in HBC can also be detected in CMT. These biomarkers have been shown to offer valuable insights into early diagnosis, prognosis, and treatment strategies. The purpose of this article is to provide a concise overview of CMT biomarkers based on the current literature. Traditional treatments for CMT in dogs typically begin with surgery, followed by chemotherapy, radiotherapy, or hormonal therapy. However, these treatments alone are not always fully effective. A diagnostic biomarker can detect the presence of a disease or the characteristics of a disease and classify an individual's status. Prognostic biomarkers focus on predicting the expected progression, recurrence, or survival of the disease in patients. By utilizing advances in understanding the mechanism of canine-specific mammary gland tumors, the estimation of biomarkers offers hope for improved outcomes in cancer patients. Novel technologies, such as single-cell RNA sequencing analysis, could provide a valuable resource for deciphering intra- and inter-tumoral heterogeneity. This review paper explores current research on CMT biomarkers and suggests directions for their development.

A Study on The Content of Liver Protein, Nucleic Acids, and Guanine Deaminase Activity of Mouse During Acute Starvation (급성(急性) 기아(饑餓)마우스의 간단백질(肝蛋白質), 핵산(核酸) 및 Guanine Deaminase 활성(活性)에 관(關)한 연구(硏究))

  • Park, Seung-Hee;Kim, Seung-Won
    • Journal of Nutrition and Health
    • /
    • v.1 no.2
    • /
    • pp.107-115
    • /
    • 1968
  • Number of aspects, not only nutritional but social as well as political involved in human starvation pose nowadays global problems. In order to help establish the minimum nutritional requirements in the daily life of a man and to free people as well from either undernourishment, malnutrition or even starvation many workers have devoted themselves so far on the research programs to know what and how number of metabolic events take place in animals in vivo. It is the purpose of the present paper to examine in effect to what extent both of the protein and nucleic acids (DNA & RNA) together with an enzyme, guanine deaminase, which converts guanine into xanthine and in turn ends up to uric acid as an end product, undergo changes, quantitatively during acute starvation, using the mouse as an experimental animal. The mouse was strictly inhibited from taking foods except drinking water ad libitum and was sacriflced 24, 48, and 72 hours following starvation thus acutely induced. The animals consisted of two experimental groups, one control and another starvation groups, each being consisted of 6-24 mice of whose body weights ranged in the vicinity of 10 g. The animals were sacriflced by a blow on the head, followed by immediate excision of their livers into ice-cold distilled water, washing adherent blood and other contaminant tissues. The liver was minced foramin, by an all-glass homogenizer immersing it in an ice-bath, followed by subsequent fractionatin of the homogenate (10% W/V in 0.25M sucrose solution made up with 0.05M phosphate buffer of pH 7.4). For the liver protein and guanine deaminase assay, the 10% homogenate was centrifuged at 600 x g for 10 minutes to eliminate the nuclear fraction; and for the estimation of DNA and RNA, the homogenate was prepared by the addition of 10% trichloroacetic acid in order to free the homogenate from the acid-soluble fraction, the remaining residue being delipidate by the addition of alcohol and dried in vacuo for later KOH (IN) hydrolysis. The changes in body and liver wegihts during acute starvation were checked gravimetrically. Protein contents in the liver were monitored by the method of Lowry et al; and guanine deaminase activities were followed by the assay of liberated ammonia from the substrate utilizing the Caraway's colorimetry. The extraction of both DNA and RNA was performed by the Schmidt-Thannhauser's method, which was followed by Marmur's method of purification for DNA and by Chargaff's method of purification for RNA. The determinations of both DNA and RNA were carried out by the diphenylamine reaction for the former and by the orcinol reaction for the latter. The following resume was the results of the present work. 1. It was observed that the body as well as liver weights fall abruptly during starvation, and that the loss of body weight showed no statistical correlation with the decreases in the content of liver protein. 2. The content of liver protein and activity of liver guanine deaminase activity as well decline dramatically, and the specific activities of the enzyme (activity/protein), however, decreased gradually as starvation proceeded. 3. Both of the nucleic acids, DNA and RNA, showed decrements in the liver of mouse during acute starvation; the latter, however, being more striking in the decline as compared to the former. 4. The decreases in the liver protein content as resulted from the acute starvation had no statistically significant correlation with the decrements of DNA in the same tissue, but had regressed with a significant statistical correlation with the fall of RNA in the tissue. 5. The decrease in the activity of guanine deaminase in the liver of mouse during acute starvation was functionally more proportional to the decrease in RNA than DNA, and moreover correlated with the changes in the content of the liver protein. 6. The possible mechanisms involved during in this acute starvation as bring the decreases in the contents of DNA, protein, and guanine deaminase were discussed briefly.

  • PDF