• Journal of Information Processing Systems
• /
• 제18권6호
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• ETRI Journal
• /
• 제39권2호
• /
• pp.264-274
• /
• 2017

Recently, mobile positioning enhancement has attracted much attention in the 3rd generation partnership project long-term evolution system. In particular, for urban canyon environments, the need for three-dimensional (3D) positioning has increased to enable the altitude of users to be measured. For several decades, several time difference of arrival (TDOA-) based 3D positioning methods have been studied; however, they are only available when at least four evolved Node Bs (eNBs) exist nearby or when all eNBs have the same height. Therefore, in this paper, we propose a new 3D positioning method that estimates the 3D coordinates of a user using three types of two-dimensional (2D) TDOAs. However, the give inaccurate results owing to the undefined axis of the 2D coordinate plane. Therefore, we propose a novel derivation of the hyperbola equation, which includes the undefined axis coordinate in the 2D hyperbola equation. Then, we propose an interaction algorithm that mutually supplies the undefined axis coordinate of users among 2D TDOAs. By performing extensive simulations, we verify that the proposed method is the only solution applicable by using three eNBs with different heights.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 A
• /
• pp.609-610
• /
• 2006

As developing the information society, Lighting Emitted diode(LED) which is light source for illumination of next generation is attracted public attention. LED have many problem as narrow light view angle, high price, drift phenomenon of color coordinate, high heating problem for lower power, lower weight and small size. So, many researches have continued in a illumination as LED module type. in this problem, heating problem is very important and difficult and that is caused in decreasing phenomenon of brightness and drift phenomenon of color coordinate. so the problem of heating is urgent question for illumination of LED. In this paper, structural design of PCB changed as two type for solving the heating problem. also the properties of heating is analysed and optical properties is measured with heating image camera and spectrometer according to change in this design.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.2241-2242
• /
• 2006

As developing the information society, Lighting Emitted diode(LED) which is light source for illumination of next generation is attracted public attention. LED have many problem as narrow light view angle, high price, drift phenomenon of color coordinate, high heating problem for lower power, lower weight and small size. So, many researches have continued in a illumination as LED module type. in this problem, heating problem is very important and difficult and that is caused in decreasing phenomenon of brightness and drift phenomenon of color coordinate. so the problem of heating is urgent question for illumination of LED. In this paper, structural design of PCB changed as two type for solving the heating problem. also the properties of heating is analysed and optical properties is measured with heating image camera and spectrometer according to change in this design.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 B
• /
• pp.1275-1276
• /
• 2006

As developing the information society, Lighting Emitted diode(LED) which is light source for illumination of next generation is attracted public attention. LED have many problem as narrow light view angle, high price, drift phenomenon of color coordinate, high heating problem for lower power, lower weight and small size. So, many researches have continued in a illumination as LED module type. in this problem, heating problem is very important and difficult and that is caused in decreasing phenomenon of brightness and drift phenomenon of color coordinate. so the problem of heating is urgent question for illumination of LED. In this paper, structural design of PCB changed as two type for solving the heating problem. also the properties of heating is analysed and optical properties is measured with heating image camera and spectrometer according to change in this design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.435-440
• /
• 2001

The development of web-aware knowledge discovery system has received a great deal of attention in recent years. It plays a key-enabling role for competitive businesses in the E-commerce era. One of the challenges in developing web-aware knowledge discovery systems is to integrate and coordinate and coordinate existing standalone or legacy knowledge discovery applications in a seamless manner, so that cost-effective systems can be developed without the need of costly proprietary products. In this paper, we present an approach for developing a framework of web-aware interoperable knowledge discovery system to achieve this purpose. This approach applies RMI and high-level code wrapper of Java distributed object computing to address the issues of interoperability in heterogeneous environments, which includes programming language, platform, and visual object model. The effectiveness of the proposed framework is demonstrated through the integration and extension of the two well-known standalone knowledge discovery tools, SOM_PAK and Nenet. It confirms that a variety of interoperable knowledge discovery systems can be constructed efficiently on the basis of the framework to meet various requirements of knowledge discovery tasks.

• Coupled systems mechanics
• /
• 제9권3호
• /
• pp.289-309
• /
• 2020

The paper studies the fluid flow profile contained between the orthotropic plate and rigid wall under the action of the moving load on the plate and main attention is focused on the fluid velocity profile in the load moving direction. It is assumed that the plate material is orthotropic one and the fluid is viscous and barotropic compressible. The plane-strain state in the plate and the plane flow of the fluid is considered. The motion of the plate is described by utilizing the exact equations of elastodynamics for anisotropic bodies, however, the flow of the fluid by utilizing the linearized Navier-Stokes equations. For the solution of the corresponding boundary value problem, the moving coordinate system associated with the moving load is introduced, after which the exponential Fourier transformation is employed with respect to the coordinate which indicates the distance of the material points from the moving load. The exact analytical expressions for the Fourier transforms of the sought values are obtained, the originals of which are determined numerically. Presented numerical results and their analyses are focused on the question of how the moving load acting on the face plane of the plate which is not in the contact with the fluid can cause the fluid flow and what type profile has this flow along the thickness direction of the strip filled by the fluid and, finally, how this profile changes ahead and behind with the distance of the moving load.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 C
• /
• pp.1735-1736
• /
• 2006

As developing the information society, Lighting Emitted diode(LED) which is light source for illumination of next generation is attracted public attention. LED have many problem as narrow light view angle, high price, drift phenomenon of color coordinate, high heating problem for lower power, lower weight and small size. So, many researches have continued in a illumination as LED module type. in this problem, heating problem is very important and difficult and that is caused in decreasing phenomenon of brightness and drift phenomenon of color coordinate. so the problem of heating is urgent question for illumination of LED. In this paper, structural design of PCB changed as two type for solving the heating problem. also the properties of heating is analysed and optical properties is measured with heating image camera and spectrometer according to change in this design.

• Annals of Clinical Neurophysiology
• /
• 제8권1호
• /
• pp.44-47
• /
• 2006

Background: The present study used magnetoencephalography (MEG) to investigate the neural substrates for modified version of Treisman's visual search task. Methods: Two volunteers who gave informed consent participated MEG experiment. One was 27- year old male and another was 24-year-old female. All were right handed. Experiment were performed using a 306-channel biomagnetometer (Neuromag LTD). There were three task conditions in this experiment. The first was searching an open circle among seven closed circles (open condition). The second was searching a closed circle among seven uni-directionally open circles (closed condition). And the third was searching a closed circle among seven eight-directionally open circles (random (closed) condition). In one run, participants performed one task condition so there were three runs in one session of experiment. During one session, 128 trials were performed during every three runs. One participant underwent one session of experiment. The participant pressed button when they found targets. Magnetic source localization images were generated using software programs that allowed for interactive identification of a common set of fiduciary points in the MRI and MEG coordinate frames. Results: In each participant we can found activations of anterior cingulate, primary visual and association cortices, posterior parietal cortex and brain areas in the vicinity of thalamus. Conclusions: we could find activations corresponding to anterior and posterior visual attention systems.