• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.232-238
• /
• 2020

In this paper, we study on aerial objects detection and position estimation algorithm for the safety of UAV that flight in BVLOS. We use the vision sensor and LiDAR to detect objects. We use YOLOv2 architecture based on CNN to detect objects on a 2D image. Additionally we use a clustering method to detect objects on point cloud data acquired from LiDAR. When a single sensor used, detection rate can be degraded in a specific situation depending on the characteristics of sensor. If the result of the detection algorithm using a single sensor is absent or false, we need to complement the detection accuracy. In order to complement the accuracy of detection algorithm based on a single sensor, we use the Kalman filter. And we fused the results of a single sensor to improve detection accuracy. We estimate the 3D position of the object using the pixel position of the object and distance measured to LiDAR. We verified the performance of proposed fusion algorithm by performing the simulation using the Gazebo simulator.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.100-108
• /
• 2023

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.4
• /
• pp.293-298
• /
• 2006

In this paper, a sensor fusion based robot navigation method for the autonomous control of a miniature human interaction robot is presented. The method of navigation blends the optimality of the Fuzzy Neural Network(FNN) based control algorithm with the capabilities in expressing knowledge and learning of the networked Intelligent Robotic Space(IRS). States of robot and IR space, for examples, the distance between the mobile robot and obstacles and the velocity of mobile robot, are used as the inputs of fuzzy logic controller. The navigation strategy is based on the combination of fuzzy rules tuned for both goal-approach and obstacle-avoidance. To identify the environments, a sensor fusion technique is introduced, where the sensory data of ultrasonic sensors and a vision sensor are fused into the identification process. Preliminary experiment and results are shown to demonstrate the merit of the introduced navigation control algorithm.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.909-914
• /
• 2007

In this paper, an overload detecting algorithm for an excavator is presented. The proposed overload detecting algorithm is based on the time series analysis especially moving window. The main purpose of this paper is to prevent a damage or crack from the fatigue in advance. 16 channel sensors data are considered and maximum stress is computed by a sensor fusion method every moving window. After the maximum stress every window is compared with a given threshold, this overload detecting algorithm decides overload or not.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.2
• /
• pp.126-131
• /
• 2014

This paper is concerned with a track management method for a naval combat system which receives the tracks information from multi-sensors and multi-tactical datalinks. Since the track management of processing the track information from diverse sources can be formulated as a data fusion problem, this paper will deal with the data fusion architecture, track association and track information determination algorithm for the track management of naval combat systems.

• Journal of Advanced Navigation Technology
• /
• v.15 no.4
• /
• pp.556-561
• /
• 2011

It is generally known that particle filters can produce consistent target tracking performance in comparison to the Kalman filter for non-linear and non-Gaussian systems. In this paper, I propose a Rao-Blackwellized multiple model particle filter(RBMMPF) to enhance computational efficiency of the particle filters as well as to reduce sensitivity of modeling. Despite that the Rao-Blackwellized particle filter needs less particles than general particle filter, it has a similar tracking performance with a less computational load. Comparison results for performance is listed for the using single sensor information RBMMPF and using multisensor data fusion RBMMPF.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.65-65
• /
• 2002

In remote sensing, images are acquired over the same area by sensors of different spectral ranges (from the visible to the microwave) and/or with different number, position, and width of spectral bands. These images are generally partially redundant, as they represent the same scene, and partially complementary. For many applications of image classification, the information provided by a single sensor is often incomplete or imprecise resulting in misclassification. Fusion with redundant data can draw more consistent inferences for the interpretation of the scene, and can then improve classification accuracy. The common approach to the classification of multisensor data as a data fusion scheme at pixel level is to concatenate the data into one vector as if they were measurements from a single sensor. The multiband data acquired by a single multispectral sensor or by two or more different sensors are not completely independent, and a certain degree of informative overlap may exist between the observation spaces of the different bands. This dependence may make the data less informative and should be properly modeled in the analysis so that its effect can be eliminated. For modeling and eliminating the effect of such dependence, this study employs a strategy using self and conditional information variation measures. The self information variation reflects the self certainty of the individual bands, while the conditional information variation reflects the degree of dependence of the different bands. One data set might be very less reliable than others in the analysis and even exacerbate the classification results. The unreliable data set should be excluded in the analysis. To account for this, the self information variation is utilized to measure the degrees of reliability. The team of positively dependent bands can gather more information jointly than the team of independent ones. But, when bands are negatively dependent, the combined analysis of these bands may give worse information. Using the conditional information variation measure, the multiband data are split into two or more subsets according the dependence between the bands. Each subsets are classified separately, and a data fusion scheme at decision level is applied to integrate the individual classification results. In this study. a two-level algorithm using hierarchical clustering procedure is used for unsupervised image classification. Hierarchical clustering algorithm is based on similarity measures between all pairs of candidates being considered for merging. In the first level, the image is partitioned as any number of regions which are sets of spatially contiguous pixels so that no union of adjacent regions is statistically uniform. The regions resulted from the low level are clustered into a parsimonious number of groups according to their statistical characteristics. The algorithm has been applied to satellite multispectral data and airbone SAR data.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.674-682
• /
• 2005

This paper proposes classification of multi-spectral satellite image based on fusion of fuzzy G-K (Gustafson-Kessel) algorithm and PCM algorithm. The suggested algorithm establishes the initial cluster centers by selecting training data from each category, and then executes the fuzzy G-K algorithm. PCM algorithm perform using classification result of the fuzzy G-K algorithm. The classification categories are allocated to the corresponding category when the results of classification by fuzzy G-K algorithm and PCM algorithm belong to the same category. If the classification result of two algorithms belongs to the different category, the pixels are allocated by Bayesian maximum likelihood algorithm. Bayesian maximum likelihood algorithm uses the data from the interior of the average intracluster distance. The information of the pixels within the average intracluster distance has a positive normal distribution. It improves classification result by giving a positive effect in Bayesian maximum likelihood algorithm. The proposed method is applied to IKONOS and Landsat TM remote sensing satellite image for the test. As a result, the overall accuracy showed a better outcome than individual Fuzzy G-K algorithm and PCM algorithm or the conventional maximum likelihood classification algorithm.

• Korean Journal of Remote Sensing
• /
• v.26 no.1
• /
• pp.39-45
• /
• 2010

This study used the keypoint observed simultaneously on two images and on twodimensional intensity image data, which was obtained along with the two point clouds data that were approached for automatic focus among points on terrestrial LiDAR data, and selected matching point through SIFT algorithm. Also, for matching error diploid, RANSAC algorithm was applied to improve the accuracy of focus. As calculating the degree of three-dimensional rotating transformation, which is the transformation-type parameters between two points, and also the moving amounts of vertical/horizontal, the result was compared with the existing result by hand. As testing the building of College of Science at Konkuk University, the difference of the transformation parameters between the one through automatic matching and the one by hand showed 0.011m, 0.008m, and 0.052m in X, Y, Z directions, which concluded to be used as the data for automatic focus.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.1
• /
• pp.17-27
• /
• 2014

As the importance of Cooperative Engagement Capability and network-centric warfare has been dramatically increasing, it is necessary to develop distributed tracking systems. Under the development of distributed tracking systems, it requires tracking filters and data fusion theory for nonlinear systems. Therefore, in this paper, the problem of nonlinear track fusion, which is suitable for distributed networks, is formulated, four algorithms to solve the problem of nonlinear track fusion are introduced, and performance of introduced algorithms are analyzed. It is a main problem of nonlinear track fusion that cross-covarinaces among multiple platforms are unknown. Thus, in order to solve the problem, two techniques are introduced; a simplification technique and a approximation technique. The simplification technique that help to ignore cross-covariances includes two algorithms, i.e. the sample mean algorithm and the Millman formula algorithm, and the approximation technique to obtain approximated cross-covariances utilizes two approaches, by using analytical linearization and statistical linearization based on the sigma point approach. In simulations, BCS fusion is the most efficient scheme because it reduces RMSE by approximating cross-covariances with low complexity.