• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.47-58
• /
• 2022

In recent years, navigation aids, which plays as sea traffic lights, have been digitized, and are developing beyond simple sign purpose to provide various functions such as marine information collection, supervision, control, etc. For example, Busan Port which is located in South Korea is leading the application of the advanced technologies by installing cameras on buoys and recording video images to supervise maritime accidents. However, there are difficulties to perform their major functions since the advanced technologies require long-term battery operation and also management and maintenance of them are hampered by marine characteristics. This study proposes a system that can automatically notify maritime objects passing around buoys by analyzing image information. In the existing sensor-based accident prevention systems, the alarms are generated by a collision detection sensor. The system can identify the cause of the accident whilst even though it is difficult not possible to fundamentally prevent the accidents. Therefore, in order to overcome these limitations, the proposed a maritime object detection system is based on marine characteristics. The experiments demonstrate that the proposed system shows about 5 times faster processing speed than other existing algorithms.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2B
• /
• pp.129-137
• /
• 2003

Multimedia streams, like MPEG continuously retrieve multimedia data because of their incessant playback. While these streams need an efficient support of kernel, the current buffer cache mechanism of Linux kernel such as Unix operating system was designed apt for small files, which is aperiodically requested as well as time uncritical. But, in case of continuous media, the CPU must enormously copy memory from kernel address space to user address space. This must lead to a large CPU overhead. This overhead both degrades system throughput and cannot guarantee QOS. In this paper, we have designed and implemented two memory copy reduction schemes in Linux kernel, direct I/O and one copy. The direct I/O skips the buffer cache layer of Linux kernel and results in dramatic reduction of CPU memory copy overhead. And, the one copy provides a fast disk-to-network data path without copying to user address space. The experimental results show considerable reduction of CPU overhead and throughput improvements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8A
• /
• pp.879-888
• /
• 2004

In this paper, we propose a real time QoS(Quality of Service) guaranteed transmission mechanism for MPEG video traffic at the congested node in IP based networks. Recent spread of the Internet has increased the demands of a real time multimedia service of the quality, Because the type of Internet services can, however, offer the best effort delivery strategies, it is difficult to treat all the types of traffic with differential COS (Class of Service). Most of all, the hierarchical coding method of MPEG data utilizes the reference frame for the motion prediction. The loss of the reference frames makes QoS of the video traffic degraded because the reference frame bit error causes the consecutive packet loss. Therefore we have studied the real time QoS guaranteed mechanism for video traffic by analyzing the previous methods. Computer simulation results show that the proposed scheme has better performance than the previous one.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.2
• /
• pp.31-39
• /
• 2003

The MPEG-2 source coding algorithm is very sensitive to transmission errors due to using of variable-length coding. When the compressed data are transmitted, transmission errors are generated and error correction scheme is not able to be corrected well them. In the decoder error concealment (EC) techniques must be used to conceal errors and it is able to minimize degradation of video quality. The proposed algorithm is method to conceal successive macroblock errors of I-frame and utilize temporal information of B-frame and spatial information of P-frame In the previous GOP which is temporally the nearest location to I-frame. This method can improve motion distortion and blurring by temporal and spatial errors which cause at existing error concealment techniques. In network where the violent transmission errors occur, we can conceal more efficiently severe slice errors. This algorithm is Peformed in MPEG-2 video codec and Prove that we can conceal efficiently slice errors of I-frame compared with other approaches by simulations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.101-107
• /
• 2009

In this paper, we describe a method of detecting emergency situation using images from surveillance cameras and propose a mobile robot tracking system for detailed examination of that situation. We are able to track a few persons and recognize their actions by an analyzing image sequences acquired from a fixed camera on all sides of buildings. When emergency situation is detected, a mobile robot moves and closely examines the place where the emergency is occurred. In order to recognize actions of a few persons using a sequence of images from surveillance cameras images, we need to track and manage a list of the regions which are regarded as human appearances. Interest regions are segmented from the background using MOG(Mixture of Gaussian) model and continuously tracked using appearance model in a single image. Then we construct a MHI(Motion History Image) for a tracked person using silhouette information of region blobs and model actions. Emergency situation is finally detected by applying these information to neural network. And we also implement mobile robot tracking technology using the distance between the person and a mobile robot.

• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.962-971
• /
• 2013

In this paper, we propose a method to infer the user's behavior and situation through collected data from multi-sensor equipped with a smart clothing and it was implemented as a smart-phone App. This smart-clothes is able to monitor wearer users' health condition and activity levels through the gyro, temp and acceleration sensor. Sensed vital signs are transmitted to a bluetooth-enabled smart-phone in the smart-clothes. Thus, users are able to have real time information about their user condition, including activities level on the smart-application. User context reasoning and behavior determine is very difficult using multi-sensor depending on the measured value of the sensor varies from environmental noise. So, the reasoning and the digital filter algorithms to determine user behavior reducing noise and are required. In this paper, we used Multi-black Filter and SVM processing behavior for 3-axis value as a representative value of one.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.678-683
• /
• 2006

A novel and intuitive way of accessing applications of mobile devices is presented. The key idea is to use grip-pattern, which is naturally produced when a user tries to use the mobile device, as a clue to determine an application to be launched. To this end, a capacitive touch sensor system is carefully designed and installed underneath the housing of the mobile terminal to capture the image of the user's grip-pattern. The captured data is then recognized by a recognizer with dedicated preprocessing and postprocessing algorithms. The recognition test is performed to validate the feasibility of the proposed user interface system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1121-1125
• /
• 2004

The RT(Robot Technology) has been developed as the next generation of a future technology. According to the 2002 technical report from Mitsubishi R&D center, IT(Information Technology) and RT(Robotic Technology) fusion system will grow five times larger than the current IT market at the year 2015. Moreover, a recent IEEE report predicts that most people will have a robot in the next ten years. RCP(Robotic Cellular Phone), CP(Cellular Phone) having personal robot services, will be an intermediate hi-tech personal machine between one CP a person and one robot a person generations. RCP infra consists of $RCP^{Mobility}$, $RCP^{Interaction}$, $RCP^{Integration}$ technologies. For $RCP^{Mobility}$, human-friendly motion automation and personal service with walking and arming ability are developed. $RCP^{Interaction}$ ability is achieved by modeling an emotion-generating engine and $RCP^{Integration}$ that recognizes environmental and self conditions is developed. By joining intelligent algorithms and CP communication network with the three base modules, a RCP system is constructed. Especially, the RCP interaction system is really focused in this paper. The $RCP^{interaction}$(Robotic Cellular Phone for Interaction) is to be developed as an emotional model CP as shown in figure 1. $RCP^{interaction}$ refers to the sensitivity expression and the link technology of communication of the CP. It is interface technology between human and CP through various emotional models. The interactive emotion functions are designed through differing patterns of vibrator beat frequencies and a feeling system created by a smell injection switching control. As the music influences a person, one can feel a variety of emotion from the vibrator's beats, by converting musical chord frequencies into vibrator beat frequencies. So, this paper presents the definition, the basic theory and experiment results of the RCP interaction system. We confirm a good performance of the RCP interaction system through the experiment results.