• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1846-1856
• /
• 2016

This study proposes a novel feature point initialization method in order to improve the accuracy of feature point positions by fusing a vision sensor and a lidar. The initialization is a process that determines three dimensional positions of feature points through two dimensional image data, which has a direct influence on performance of a 6-DoF bearing-only SLAM. Prior to the initialization, an extrinsic calibration method which estimates rotational and translational relationships between a vision sensor and lidar using multiple calibration tools was employed, then the feature point initialization method based on the estimated extrinsic calibration parameters was presented. In this process, in order to improve performance of the accuracy of the initialized feature points, an iterative automatic scaling parameter tuning technique was presented. The validity of the proposed feature point initialization method was verified in a 6-DoF bearing-only SLAM framework through an indoor and outdoor tests that compare estimation performance with the previous initialization method.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1995년도 추계학술대회발표논문집; 서울대학교, 서울; 30 Sep. 1995
• /
• pp.325-333
• /
• 1995

Back-propagation is the most widely used algorithm for supervised learning in multi-layer feed-forward networks. However, back-propagation is very slow in convergence. In this paper, a new weight initialization method, called rough map initialization, in multi-layer perceptrons is proposed. To overcome the long convergence time, possibly due to the random initialization of the weights of the existing multi-layer perceptrons, the rough map initialization method initialize weights by utilizing relationship of input-output features with singular value decomposition technique. The results of this initialization procedure are compared to random initialization procedure in encoder problems and xor problems.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2003년도 International Meeting on Information Display
• /
• pp.122-125
• /
• 2003

We describe a new method to initialize the raster and convergence of a flat intelligent tracking (F!T) tube. By splitting up the initialization algorithm into three parts, it can comply with the variety of boundary conditions that are stated for a consumer product. Experiments on raster initialization have shown that the new algorithm speeds up the initialization by one order of magnitude.

• 대기
• /
• 제26권1호
• /
• pp.35-45
• /
• 2016

Initialization of the global seasonal forecast system is as much important as the quality of the embedded climate model for the climate prediction in sub-seasonal time scale. Recent studies have emphasized the important role of soil moisture initialization, suggesting a significant increase in the prediction skill particularly in the mid-latitude land area where the influence of sea surface temperature in the tropics is less crucial and the potential predictability is supplemented by land-atmosphere interaction. This study developed a new soil moisture initialization method applicable to the KMA operational seasonal forecasting system. The method includes first the long-term integration of the offline land surface model driven by observed atmospheric forcing and precipitation. This soil moisture reanalysis is given for the initial state in the ensemble seasonal forecasts through a simple anomaly initialization technique to avoid the simulation drift caused by the systematic model bias. To evaluate the impact of the soil moisture initialization, two sets of long-term, 10-member ensemble experiment runs have been conducted for 1996~2009. As a result, the soil moisture initialization improves the prediction skill of surface air temperature significantly at the zero to one month forecast lead (up to ~60 days forecast lead), although the skill increase in precipitation is less significant. This study suggests that improvements of the prediction in the sub-seasonal timescale require the improvement in the quality of initial data as well as the adequate treatment of the model systematic bias.

• 대기
• /
• 제22권1호
• /
• pp.117-128
• /
• 2012

Does snow depth initialization have a quantitative impact on sub-seasonal to seasonal prediction skill? To answer this question, a snow depth initialization technique for seasonal forecast system has been implemented and the impact of the initialization on the seasonal forecast of surface air temperature during the wintertime is examined. Since the snow depth observation can not be directly used in the model simulation due to the large systematic bias and much smaller model variability, an anomaly rescaling method to the snow depth initialization is applied. Snow depth in the model is initialized by adding a rescaled snow depth observation anomaly to the model snow depth climatology. A suite of seasonal forecast is performed for each year in recent 12 years (1999-2010) with and without the snow depth initialization to evaluate the performance of the developed technique. The results show that the seasonal forecast of surface air temperature over East Asian region sensitively depends on the initial snow depth anomaly over the region. However, the sensitivity shows large differences for different timing of the initialization and forecast lead time. Especially, the snow depth anomaly initialized in the late winter (Mar. 1) is the most effective in modulating the surface air temperature anomaly after one month. The real predictability gained by the snow depth initialization is also examined from the comparison with observation. The gain of the real predictability is generally small except for the forecasting experiment in the early winter (Nov. 1), which shows some skillful forecasts. Implications of these results and future directions for further development are discussed.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.497-508
• /
• 2005

This paper aims at studying on K-means Clustering focusing on initialization which affect the clustering results in K-means cluster analysis. The four different methods(the MA method, the KA method, the Max-Min method and the Space Partition method) were compared and the clustering result shows that there were some differences among these methods, especially that the MA method sometimes leads to incorrect clustering due to the inappropriate initialization depending on the types of data and the Max-Min method is shown to be more effective than other methods especially when the data size is large.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.833-838
• /
• 2016

This paper presents a performance evaluation of various feature-initialization algorithms for forward-viewing mono-camera based simultaneous localization and mapping (SLAM), specifically in indoor environments. For mono-camera based SLAM, the position of feature points cannot be known from a single view; therefore, it should be estimated from a feature initialization method using multiple viewpoint measurements. The accuracy of the feature initialization method directly affects the accuracy of the SLAM system. In this study, four different feature initialization algorithms are evaluated in simulations, including linear triangulation; depth parameterized, linear triangulation; weighted nearest point triangulation; and particle filter based depth estimation algorithms. In the simulation, the virtual feature positions are estimated when the virtual robot, containing a virtual forward-viewing mono-camera, moves forward. The results show that the linear triangulation method provides the best results in terms of feature-position estimation accuracy and computational speed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.13-16
• /
• 2001

In reinforcement teaming, Q-learning converges quite slowly to a good policy. Its because searching for the goal state takes very long time in a large stochastic domain. So I propose the speedup method using the Q-value initialization for model-free reinforcement learning. In the speedup method, it learns a naive model of a domain and makes boundaries around the goal state. By using these boundaries, it assigns the initial Q-values to the state-action pairs and does Q-learning with the initial Q-values. The initial Q-values guide the agent to the goal state in the early states of learning, so that Q-teaming updates Q-values efficiently. Therefore it saves exploration time to search for the goal state and has better performance than Q-learning. 1 present Speedup Q-learning algorithm to implement the speedup method. This algorithm is evaluated. in a grid-world domain and compared to Q-teaming.

• 한국멀티미디어학회논문지
• /
• 제21권4호
• /
• pp.441-449
• /
• 2018

Deep learning has been used for various processing centered on image recognition. One core algorithms of the deep learning, convolutional neural network is an deep neural network that specialized in image recognition. In this paper, we use a convolutional neural network to classify forest insects and propose an optimization method. Experiments were carried out by combining two weight initialization and six parameter update methods. As a result, the Xavier-SGD method showed the highest performance with an accuracy of 82.53% in the 12 different combinations of experiments. Through this, the latest learning algorithms, which complement the disadvantages of the previous parameter update method, we conclude that it can not lead to higher performance than existing methods in all application environments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.752-757
• /
• 2003

Recently, 3D structure recovery through self-calibration of camera has been actively researched. Traditional calibration algorithm requires known 3D coordinates of the control points while self-calibration only requires the corresponding points of images, thus it has more flexibility in real application. In general, self-calibration algorithm results in the nonlinear optimization problem using constraints from the intrinsic parameters of the camera. Thus, it requires initial value for the nonlinear minimization. Traditional approaches get the initial values assuming they have the same intrinsic parameters while they are dealing with the situation where the intrinsic parameters of the camera may change. In this paper, we propose new initialization method using the minimum 2 images. Proposed method is based on the assumption that the least violation of the camera’s intrinsic parameter gives more stable initial value. Synthetic and real experiment shows this result.