• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1121-1141
• /
• 2020

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.661-670
• /
• 2012

Urban forests provide great ecosystem services to population in metropolitan areas even though they occupy little green space in a huge gray landscape. Unfortunately, urbanization inherently results in threatening the green infrastructure, and the recent urbanization trends drew great attention of scientists and policy makers on how to preserve or restore green infrastructure in metropolitan area. For this reason, mapping the spatial distribution of the green infrastructure is important in urban environments since the resulting map helps us identify hot green spots and set up long term plan on how to preserve or restore green infrastructure in urban environments. As a preliminary step for mapping green infrastructure utilizing multi-source remote sensing data in urban environments, the objective of this study is to map vegetation volume by fusing LiDAR and multispectral data in urban environments. Multispectral imageries are used to identify the two dimensional distribution of green infrastructure, while LiDAR data are utilized to characterize the vertical structure of the identified green structure. Vegetation volume was calculated over the metropolitan Chicago city area, and the vegetation volume was summarized over 16 NLCD classes. The experimental results indicated that vegetation volume varies greatly even in the same land cover class, and traditional land cover map based above ground biomass estimation approach may introduce bias in the estimation results.

• Journal of the Korea Furniture Society
• /
• v.25 no.3
• /
• pp.165-172
• /
• 2014

3D form study is one of basic subjects in industrial design education. There are an array of textbooks of visual art, design and architecture, most of which address basic geometrical form study and abstract forms. With the introduction of computerization, current trends are directed to reduce basic form education and students' participation in classes and their accomplishments. This study was intended to develop works under a theme of furniture design with concrete shapes and functions. This study focused on developing relevant process by fusing 3D form study and furniture design which fall into basic design and design studio subjects, respectively. Among 3D form studies, applied were a concept of 3D configuration that explores the relations between surface forms and 3D forms. Furniture design is a challenge to students at beginner or intermediate level in basic design education from initial devising stage to production in kind. To ease high level of difficulties at designing and producing stages, technical education was systematized in the process of conceptualizing, developing idea and production. This type of challenge was carried out during separate semesters, along with a case study done to develop different types of challenges. This study helped students to be motivated and actively participate in classes and well perform advanced form study and technical training from design to actual production.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.4
• /
• pp.281-289
• /
• 2016

Agitation is a secondary process used to increase the PR stripping force on an ITO-glass surface; it is an efficient approach to stripping during production. It activates the stripper to chemically penetrate the PR layer and assists by breaking down the physical bonding forces at the surface. In this study, different stripping tests were conducted by varying the dipping time, the composition, the strip temperature, and the stripper concentration. Optimal PR strip conditions were estimated by using comparative visual inspection of stripped sample surfaces. The stripping process was affected by changes in the moving speeds and the sample positions. It was confirmed that the stripping capability improved at a dilute stripper ratio of 20-40% and a strip temperature of $30-40^{\circ}C$ and within 60 s of strip time.

• Korean Journal of Organic Agriculture
• /
• v.22 no.4
• /
• pp.593-610
• /
• 2014

The whole world concentrates on the reduction of greenhouse gas to effectively cope with policy toward global climate change. To effectively react to climate change, even the agricultural sector requires construction of new farming systems that utilizes new and renewable energy because of rising oil prices and regulations for greenhouse gas emissions. For this reason, we need to fuse the new and renewable energy with the horticulture sector of which the light and heat energy cost accounts for great part, moreover, efforts and researches should me done which can increase income of farmers through reducing carbon dioxide and energy cost in agricultural production expenses. Therefore, this study analyzes economic feasibility and applicability of fusing geothermal heat pump and solar power facilities with high-tech glass greenhouse. As a result, it is concluded that there surely are an applicability and economic feasibility if we apply new development system that can be an alternative for problems of securing premises of existing geothermal heat pump and the RPS system as a power generation company in case of solar power. Therefore, using this analysis data, if new empirical studies fusing and implementing agriculture sector with new and renewable energy fields proliferate and be applied to actual rural and agricultural field, it will increase actual income and will become a new advanced agricultural system that effectively deals with world-wide environmental problems.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.5
• /
• pp.397-402
• /
• 2019

Recently, with the emergence of autonomous vehicles and the increasing interest in safety, a variety of research has been being actively conducted to precisely estimate the position of a vehicle by fusing sensors. Previously, researches were conducted to determine the location of moving objects using GNSS (Global Navigation Satellite Systems) and/or IMU (Inertial Measurement Unit). However, precise positioning of a moving vehicle has lately been performed by fusing data obtained from various sensors, such as LiDAR (Light Detection and Ranging), on-board vehicle sensors, and cameras. This study is designed to enhance kinematic vehicle positioning performance by using feature-based recognition. Therefore, an analysis of the required precision of the observations obtained from the images has carried out in this study. Velocity and attitude observations, which are assumed to be obtained from images, were generated by simulation. Various magnitudes of errors were added to the generated velocities and attitudes. By applying these observations to the positioning algorithm, the effects of the additional velocity and attitude information on positioning accuracy in GNSS signal blockages were analyzed based on Kalman filter. The results have shown that yaw information with a precision smaller than 0.5 degrees should be used to improve existing positioning algorithms by more than 10%.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.595-597
• /
• 2004

In this paper range measurement systems using ultrasonic and visual sensors are designed. By varying the focus of a camera, the range to a target pattern is computed. Pour different methods are tested for the focusing-based range measurement. The best result is obtained when counting edge pixels found by Laplacian operator. Higher accuracy can be obtained by fusing the measurement of camera focusing with that of ultrasonic sensor. The system designed is experimented within the range of 300-450mm.

• Proceedings of the Korean Fiber Society Conference
• /
• 2002.04a
• /
• pp.69-72
• /
• 2002

섬유산업은 fiber로부터 시작하여 yarn, fabric을 거쳐 최종 섬유제품인 clothing을 생산하는 긴 stream을 가지고 있으며, 이와 같이 여러 단계의 공정을 거치는 가운데 섬유물은 새로운 형태를 가지게 되며 부가가치가 형성된다. 특히 garments manufacturing 공정에는 fusing press기가 사용되는데 이 방식은 같은 각속도와 지름을 가진 cylinder로 구동되는 두 개의 상하 벨트구동기구와 내부에 열전식 heather로 구성되어 상하 벨트의 내부로 원단과 심지를 통과시키며 열을 가함으로써 원단과 심지를 접착시킨다. (중략)

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.3
• /
• pp.126-135
• /
• 2008

The development of an unmanned vehicle basically requires the robust and reliable performance of major functions which include global localization, lane detection, obstacle avoidance, path planning, etc. The implementation of major functional subsystems are possible by integrating and fusing data acquired from various sensory systems such as GPS, vision, ultrasonic sensor, encoder, and electric compass. This paper focuses on implementing the functional subsystems, which are designed and developed by a graphical programming tool, NI LabVIEW, and also verifying the autonomous navigation and remote control of the unmanned vehicle.