• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.530-533
• /
• 2009

This paper proposes a method of recognizing that a person doesn't put on a safety cap using image processing method in DSP(Digital Signal Processor). It processes inputted images by image input devices that equipped in a industrial settings. If the method recognizes a person that doesn't put on a safety cap, a system transfers relevant recognition result to a supervisor and takes proper measures. If an accident happens and someone doesn't put on a safety cap, additional casualities could be. Proposed method can nip additional casualties in the bud. To recognize that a person don't put on a safety cap, images are processed by object abstraction, removal of noise, decision of a thing or a person, abstraction of a head part in a image, recognizing whether a man puts on a safety cap using HSV color space or not, and so on. Image input and image process are processed by DSP. And C language-based codes are optimized by an eignefunction(Intrinsics) for speed improvement of algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.47-54
• /
• 2022

Recently, with the development of deep learning technology, research on recognizing human behavior is in progress. In this paper, a study was conducted to recognize risky behaviors that may occur in a single-person household environment using deep learning technology. Due to the nature of single-person households, personal privacy protection is necessary. In this paper, we recognize human dangerous behavior in privacy protection video with Gaussian blur filters for privacy protection of individuals. The dangerous behavior recognition method uses the YOLOv5 model to detect and preprocess human object from video, and then uses it as an input value for the behavior recognition model to recognize dangerous behavior. The experiments used ResNet3D, I3D, and SlowFast models, and the experimental results show that the SlowFast model achieved the highest accuracy of 95.7% in privacy-protected video. Through this, it is possible to recognize human dangerous behavior in a single-person household environment while protecting individual privacy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2427-2432
• /
• 2009

This paper proposes an monitoring system of elder and feeble person's motion activity using an object's motion activity data. The proposed system used wireless 3-axis sensor module, product by Freescale(Wireless Sensing Triple Axis Reference Design Board (ZSTAR)). We distribute sensing data into three classes using Neural Network System SVM. We find performance of proposed system that simulate some case about walk, past walk, fallen. Classify result data and graph of sensing data present succes rate 80%.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1523-1527
• /
• 2017

Recently, there have been a growing number of services for users to shoot content by themselves and to broadcast this data to a large number through the Internet. One-person media live services are popular in life, and similar services are becoming common. Most of these services are for general users. However, depending on the service model or the situation, there are cases where the object of streaming is limited depending on the security-sensitive service environment. Especially, in the case of closed networks such as military, government, and security organizations, these specialized services are needed. Therefore, in this paper, we implemented a live media system in a closed network environment. We study system components suitable for service environment and study how to develop components.

• Journal of computational fluids engineering
• /
• v.7 no.3
• /
• pp.27-34
• /
• 2002

When caught in a fire inside a building or a tunnel the generated smoke is the main cause of the bad visibility, which makes it difficult for a person to find escape route. Therefore of the fire simulation it is required to visualize the simulated results of smoke realistically form a viewpoint of a person caught in a fire. In the present study, developed is a CFD post-processor which can visualize the object through smoke from the results of CFD fire simulation. Examples of some applications of the program are shown in the paper.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.460-467
• /
• 2003

According to Korea Socity of Cartoon&Animation studies research material, consumer's preference degree about animation genre answered that investigation target's 50% is doing basis in interest. Animation has various factor of interest induction, but we can count as person's action scene among them. Laying stress on Japan animation 'Offended ghost princess' and 'New century Ebangerion', this research Analyze identifying special feature and difference of transfer form of person(object) that show in cut away of action scene, and Recognized whether diagnostic expressions by the result influence as dynamic element to actuality consumers.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.477-480
• /
• 1988

A new image coding system called knowledge- based coding is presented which uses positively the knowledge for coding objects. The 3- dimensional model and the psychological knowledge for a person's face can be used as the knowledge for a coding system, when a person's face is coding object. A transmitter analyzes input images and a receiver synthesizes output images using them. The construction of 3-dimensional model and the introduction of the psychological knowledge to the new coding system are discussed. The basic facial expressions are synthesized from a neutral face using them. The synthesized images are very natural.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2690-2692
• /
• 2004

Medications or cognitive-behavior methods have been mainly used as a treatment of alcoholism. lately the virtualy technology has been applied to the kink of alcoholic disorders. A virtual environment makes him having ability to over come the drink. In this study, we were implemented by making panorama images and 3D object modules using 3D Studio MAX. VRML, JAVA Applet. And the BAR stimulator that composed with a position sensor head mount display, and audio system, is suggested. To illustrate the physiological difference between a person who has a alcoholism and and without a liquor bottle, heart rate was measured during experiment, and also measured a Person's HR after the virtual reality training. we demonstrated the subjective effectiveness of virtual reality psychotherapy through the clinical experiment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.409-414
• /
• 2007

Active Appearance Model is a well-known model that can represent a non-rigid object effectively. However, since it uses the fixed appearance model, the fitting results are often unsatisfactory when the imaging condition of the target image is different from that of training images. To alleviate this problem, incremental AAM was proposed which updates its appearance bases in an on-line manner. However, it cannot deal with the sudden changes of illumination. To overcome this, we propose a novel scheme to update the appearance bases. When a new person appears in the input image, we synthesize illuminated images of that person and update the appearance bases of AAM using it. Since we update the appearance bases using synthesized illuminated images in advance, the AAM can fit their model to a target image well when the illumination changes drastically. The experimental results show that our proposed algorithm improves the fitting performance over both the incremental AAM and the original AAM.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.425-426
• /
• 2007

It is caused by characteristic differences when aligned the electrical aspect of the system with the idiosyncrasy of the human hearing organ. Considering such an issue, this thesis places its purpose in obtaining a favored sound which objectively analyzed and subjectively evaluated. Since a favored sound is different person to person, the research object is limited to peculiar areas in where similar cultural backgrounds are found. An average spectrum is extracted from the sound sources of music albums sold in the areas, and objectively utilized. This study searches for an approaching method in producing AV system to sell in a specific country.