• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.2
• /
• pp.1-9
• /
• 2009

Due to the increase of carbon dioxide in the atmosphere and global warming, the importance of forest ecosystems, as a place of carbon accumulation and emission, has received a great amount of recognition lately. This study was performed to help understand and provide the current status of carbon cycle in the pinus densiflora stand, Korea. The samples were collected from average 35-years-old Pinus densifiora rands in Gongju, Youngdong, Chungsan, Muju, Mupung, and Jangsu regions. Total thirty aboveground sample trees were cut, and ten roots were sampled, and soil samples were collected. Average carbon concentrations in foliage, branch, stem bark, stem wood, and root were 55.7%, 56.0%, 56.0%, 57.3%, and 56.5%, respectively. Carbon content was estimated by the model $Wt=aD^b$ where Wt is oven-dry weight in kg and D is DBH in cm. Total carbon content (aboveground and root) was 42.39tonC/ha in the Pinus densiflora stand. The proportion of each tree component to total carbon content was high in order of stemwood, root, branch, stem bark, and foliage. Total net primary production (aboveground and root) was estimated at 6.51tonC/ha/yr in Pinus densiflora stand. The proportion of each tree component to total net primary carbon content was high in order of sternwood, root, branch, foliage and stembark. Soil carbon contents in the study sites was 43.51tonC/ha at 0-50cm soil depth.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.378-383
• /
• 2009

In these days, many systems are equipped with people to infer their intention and provide the corresponding service. People always carry their own mobile device with various sensors, and the accelerator takes a role in this environment. The accelerator collects motion information, which is useful for the development of gesture-based user interfaces. Generally, it needs to develop an effective method for the mobile environment that supports relatively less computational capability since huge computation is required to recognize time-series patterns such as gestures. In this paper, we propose a 2-stage motion recognizer composed of low-level and high-level motions based on the motion library. The low-level motion recognizer uses the dynamic time warping with 3D acceleration data, and the high-level motion is defined linguistically with the low-level motions.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1184-1195
• /
• 2006

The Internet has brought many changes in our daily lives. Now the recognition on the Internet fashion shopping matt has increased and it requires scientific and systematic research to understand the Internet fashion marketing system more correctly and to strengthen the marketing activity at the virtual space. A big shortcoming of an Internet fashion mall is that the consumers can't wear clothes themselves. Currently there is no system to cover the shortcoming, It would be nice if a 3D avata wears the clothes on behalf of a consumer after inputting the information of physical sizes of a consumer. The consumers can select many clothes, accessories and even the background. After establishing a complete virtual fashion shopping mall, the consumers who sue the Internet fashion shopping mall could wear the clothes at an online shop establishing an online shopping environment. It will be a sole way to ensure the trust of the consumers. This paper studies the read in reflection by PC camera and sample the edge detection. Virtual fitting system that wears virtual fitting model some clothes is establishment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.883-890
• /
• 2017

Among the augmented reality services, the most frequently used services are marker based augmented reality services. However, there is a problem that the augmented reality service can not be provided in an environment in which the marker image can not be recognized. In this paper, we propose a method to provide more stable service by estimating the user's posture even if the marker image can not be correctly recognized due to occlusion, obstacle or marker damage in the marker based augmented reality. In the proposed method, when a failure occurs in the provision of a marker based augmented reality, the attitude of the user is estimated using the 3-dimensional coordinates measured through communication between the three beacons and the user, and it allows the user to receive the augmented reality service continuously. We describe the scenario of augmented reality technique using proposed marker recognition and beacon communication, and present the results of experiments based on the degree of occlusion and damage.

• International Journal of Precision Engineering and Manufacturing
• /
• v.2 no.3
• /
• pp.27-33
• /
• 2001

The aim of the present work is to propose a model for Computer Aided programming of numerical Control lathe. This model is based on the concept by features. It has been developed in an Artificial Intelligence environment, that offers a rapidity as well as a precision for NC code elaboration. In this study a pre-processor has been elaborated to study the geometry of turning workpiece. This pre-processor is a hybrid system which combine a module of design by features and a module of features recognition for a piece provided from an other CAD software. Then, we have conceived a processor that is the heart of the CAD/CAM software. The main functions are to study the fixture of the workpiece, to choose automatically manufacturing cycles, to choose automatically cutting tools (the most relevant), to simulate tool path of manufacturing and calculate cutting conditions, end to elaborate a typical manufacturing process. Finally, the system generates the NC program from information delivered by the processor.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.644-647
• /
• 1996

In this study the theoretical minimum resolution analysis of an active vision system using laser range finder is performed for surrounding recognition and 3D data acquisition in unknown environment. The laser range finder consists of a slitted laser beam generator, a scanning mechanism, CCD camera, and a signal processing unit. A laser beam from laser source is slitted by a set of cylindrical lenses and the slitted laser beam is emitted up and down and rotates by the scanning mechanism. The image of laser beam reflected on the surface of an object is engraved on the CCD array. In the result, the resolution of range data in laser range finder is depend on distance between lens center of CCD camera and light emitter, view and beam angles, and parameters of CCD camera.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.1
• /
• pp.82-87
• /
• 1998

In this study, the theoretical resolution analysis of an active vision system using laser range finder is performed for surrounding recognition and 3D data acquisition in unknown environment. In the result, the resolution of range data in laser range finder is depend on the distance between lens center of CCD camera and light emitter, view angle, beam angle, and parameters of CCD camera. The theoretical resolutions of the laser range finders of various types which are based on parameters effected resolution are calculated and experimental results are obtained in real system.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.587-589
• /
• 1995

The safe navigation of a mobile robot requires the recognition of the environment in terms of vision processing. To be guided in the given path, the robot should acquire the information about where the wall and corridor are located. Also unexpected obstacles should be detected as rapid as possible for the safe obstacle avoidance. In the paper, we assume that the mobile robot should be navigated in the flat surface. In terms of this assumption we simplify the correspondence problem by the free navigation surface and matching features in that coordinate system. Basically, the vision processing system adopts line segment of edge as the feature. The extracted line segments of edge out of both image are matched in the free nevigation surface. According to the matching result, each line segment is labeled by the attributes regarding obstacle and free surface and the 3D shape of obstacle is interpreted. This proposed vision processing method is verified in terms of various simulations and experimentation using real images.

• Journal of Technology Innovation
• /
• v.14 no.3
• /
• pp.1-21
• /
• 2006

The explosion in creation and utilization of IP including Patent since 1980s has been regarded as typical trend affecting the environment for technological innovation. Korea also has shown massive creation of IP. These stimulate the focused interest on the effectiveness of IP for protecting the innovation output. We try to analyze the determinants of this effectiveness in Korean manufacturing sector in terms of the charactenstics of firm's innovation strategy. It is shown that, for protection for product innovation, as being larger, and as having made innovation, the IP protection is regarded as effective, and firms making cooperative R&D have a higher possibility of using IP protection. And larger firms give a higher recognition to effectiveness of IP protection irrespective of the types of innovation such as product innovation and process innovation.