• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Spatial Information Research
• /
• 제20권4호
• /
• pp.29-36
• /
• 2012

최근 도시와 도시간의 물류량 증가로 인하여 교통혼잡비용이 증가하고, 기후변화협약에 따른 이산화탄소 감축이 의무화됨에 따라 저탄소 화물운송체계 개념이 소개되었다. 연료소비량 및 탄소배출량을 고려한 화물운송계획을 수립하기 위해서는 현실의 도로 기하정보를 표현하는 3차원 도로망도가 필수적이다. 본 연구는 화물운송의 주요대상인 도시와 도시간의 간선도로를 중심으로 지형 및 도로구조물을 고려하기 위하여 기존 2차원 교통주제도와 수치표고모델을 이용하여 도로의 실제 기하정보를 반영하는 3차원 도로망도 모델을 제안한다. 제안 모델은 실험 도로구간(평택항-의왕IC)을 대상으로 구축하고 GPS/INS 측량을 통해 구축한 3차원 도로망도가 도로의 기하정보를 잘 표현함을 검증하였다(RMSE=0.87m). 또한, 연료소모량 시뮬레이션을 통해 기존의 2차원 도로망도에 비해 제안모델이 현실도로의 연료소모량을 효과적으로 반영함을 알 수 있었다. 본 연구를 통해 복잡한 도로의 3차원 기하정보를 반영하여 에너지 및 환경문제를 효과적으로 고려할 수 있는 Green-ITS기반의 화물 경로계획 및 네비게이션 시스템 개발이 가능할 것이다.

• Structural Engineering and Mechanics
• /
• 제49권6호
• /
• pp.687-703
• /
• 2014

This paper develops a new nonlinear model for active control of three-dimensional (3D) irregular building structures. Both geometrical and material nonlinearities with a neuro-controller training algorithm are applied to a multi-degree-of-freedom 3D system. Two dynamic assembling motions are considered simultaneously in the control model such as coupling between torsional and lateral responses of the structure and interaction between the structural system and the actuators. The proposed control system and training algorithm of the structural system are evaluated by simulating the responses of the structure under the El-Centro 1940 earthquake excitation. In the numerical example, the 3D three-story structure with linear and nonlinear stiffness is controlled by a trained neural network. The actuator dynamics, control time delay and incident angle of earthquake are also considered in the simulation. Results show that the proposed control algorithm for 3D buildings is effective in structural control.

• 전기전자학회논문지
• /
• 제16권2호
• /
• pp.102-108
• /
• 2012

3D-IC는 2D-IC와 비교하여 전력 공급 네트워크 설계 시에 더 큰 공급 전류와 더 많은 전력 공급 경로들 때문에 몇 가지 문제점을 가지고 있다. 전력 공급 네트워크는 전력 범프와 전력 TSV로 구성되고, 각 노드의 전압 강하는 전력 범프와 전력 TSV의 개수와 위치에 따라 다양한 값을 가지게 된다. 그래서 칩이 정상적으로 동작하기 위해서는 전압 강하 조건을 만족시키면서 전력 범프와 전력 TSV를 최적화하는 것이 중요하다. 본 논문에서는 3D-IC 전력 공급 네트워크에서 최적의 전력 메시 구조를 통한 전력 범프와 전력 TSV 최적화를 제안한다.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.125-127
• /
• 2001

Switched reluctance motor (SRM) has some advantages such as low cost, high torque density etc. However SRM has inevitably high torque ripple due to the double salient structure. To apply SRM to industrial field, we have to minimize torque ripple, which is the weak-Point of SRM. This paper presents optimal design process of SRM using numerical method such as 2D finite element method (FEM) and 3D equivalent magnetic circuit network method (EMCNM). The electrical and geometrical design parameters have been adopted as 2D design variables. The overhang structure of rotor has been also adopted as 3D design variable. From this work, we can obtain the optimal design, which minimize the torque ripple and maximize energy conversion loop.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.8-15
• /
• 2018

This paper proposes a convolutional neural network model for distinguishing areas occupied by obstacles from a LiDAR image converted from a 3D point cloud. The channels of a LiDAR image used as input consist of the distances to 3D points, the reflectivities of 3D points, and the heights of 3D points from the ground. The proposed model uses a LiDAR image as an input and outputs a result of a segmented LiDAR image. The proposed model adopts refinement modules with skip connections to segment a LiDAR image. The refinement modules with skip connections in the proposed model make it possible to construct a complex structure with a small number of parameters than a convolutional neural network model with a linear structure. Using the proposed model, it is possible to distinguish areas in a LiDAR image occupied by obstacles such as vehicles, pedestrians, and bicyclists. The proposed model can be applied to recognize surrounding obstacles and to search for safe paths.

• 한국표면공학회지
• /
• 제57권3호
• /
• pp.214-220
• /
• 2024

In this study, three-dimensional (3D) networks structure using single-walled carbon nanotubes (SWCNTs) for Si-graphite composite electrode was developed and studied about effects on the electrochemical performances. To investigate the effect of SWCNTs on forming a conductive 3D network structure electrode, zero-dimensional (0D) carbon black and different SWCNTs composition electrode were compared. It was found that SWCNTs formed a conductive network between nano-Si and graphite particles over the entire area without aggregation. The formation of 3D network structure enabled to effective access for lithium ions leading to improve the c-rate performance, and provided cycle stability by alleviating the Si volume expansion from flexibility and buffer space. The results of this study are expected to be applicable to the electrode design for high-capacity lithium-ion batteries.

• Bulletin of the Korean Chemical Society
• /
• 제35권9호
• /
• pp.2847-2850
• /
• 2014

• 한국재료학회지
• /
• 제18권3호
• /
• pp.163-168
• /
• 2008

The morphology of three-dimensional (3D) cross-linked electrodeposits of copper and tin was investigated as a function of the content of metal sulfate and acetic acid in a deposition bath. The composition of copper sulfate had little effect on the overall copper network structure, whereas that of tin sulfate produced significant differences in the tin network structure. The effect of the metal sulfate content on the copper and tin network is discussed in terms of whether or not hydrogen evolution occurs on electrodeposits. In addition, the hydrophobic additive, i.e., acetic acid, which suppresses the coalescence of evolved hydrogen bubbles and thereby makes the pore size controllable, proved to be detrimental to the formation of a well-defined network structure. This led to a non-uniform or discontinuous copper network. This implies that acetic acid critically retards the electrodeposition of copper.