• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.575-582
• /
• 2022

In the manufacturing environment, research to minimize robot collisions with human beings have been widespread, but in order to interact with robots, it is important to precisely recognize and predict human actions. In this research, after enhancing performance by applying group normalization to the Hourglass model to detect the operator motion, the skeleton was estimated and data were created using this model. And then, three types of operator's movements were recognized using LSTM. As results of the experiment, the accuracy was enhanced by 1% using group normalization, and the recognition accuracy was 99.6%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.63-71
• /
• 2008

In this paper, we propose a color based hierarchically propagated particle filter that extends the color based particle filter into the articulated upper body tracking. Since color feature is robust to partial occlusion and rotation, the color based particle filter is widely used for object tracking. However, in articulated body tacking, it is not desirable to use the traditional particle filter because the dimension of the state vector usually is high and thus, many samples are required for robust hacking. To overcome this problem, we use a hierarchical tracking method for each body part based on the blown body part. By using a hierarchical tracking method, we can reduce the number of samples for robust tracking in the cluttered environment. Also for human pose recognition, we classify the human pose into eight categories using Support Vector Machine(SVM) according to the angle between upper- arm and fore-arm. Experimental results show that our proposed method is more efficient than the traditional particle filter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• 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.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.499-510
• /
• 2018

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.

• The Journal of Korea Robotics Society
• /
• v.5 no.3
• /
• pp.262-269
• /
• 2010

This paper presents a probabilistic head tracking method, mainly applicable to face recognition and human robot interaction, which can robustly track human head against various variations such as pose/scale change, illumination change, and background clutters. Compared to conventional particle filter based approaches, the proposed method can effectively track a human head by regularizing the sample space and sequentially weighting multiple visual cues, in the prediction and observation stages, respectively. Experimental results show the robustness of the proposed method, and it is worthy to be mentioned that some proposed probabilistic framework could be easily applied to other object tracking problems.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.2
• /
• pp.178-183
• /
• 2008

Human motion analysis is researched as a new method for human-robot interaction (HRI) because it concerns with the key techniques of HRI such as motion tracking and pose recognition. To analysis human motion, extracting features of human body from sequential images plays an important role. After finding the silhouette of human body from the sequential images obtained by CCD color camera, the skeleton model is frequently used in order to represent the human motion. In this paper, using the silhouette of human body, we propose the feature extraction method based on hybrid skeleton for detecting human motion. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.607-616
• /
• 2014

Face recognition is a big challenge in surveillance system since different rotation angles of the face make the difficulty to recognize the face of the same person. This paper proposes a novel method to recognize face with different head poses by using 3D information of the face. Firstly, head pose estimation (estimation of different head pose angles) is accomplished by the POSIT algorithm. Then, 3D face image data is constructed by using head pose estimation. After that, 2D image and the constructed 3D face matching is performed. Face verification is accomplished by using commercial face recognition SDK. Performance evaluation of the proposed method indicates that the error range of head pose estimation is below 10 degree and the matching rate is about 95%.