• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.6_2
• /
• pp.593-605
• /
• 2012

LiDAR systems provide dense and accurate topographic information. A pre-requisite to achieving the potential accuracy of LiDAR is having a proper system calibration, which aims at estimating all the systematic errors in the system measurements and the mounting parameters relating the different components. This paper presents a rigorous and two approximate methods for LiDAR system calibration. The rigorous approach makes use of the LiDAR equation and the system raw measurements. The approximate approaches utilize simplified LiDAR equations using some assumptions, which allow for less strict requirements regarding the raw measurements. The first presented approximate method, denoted as quasi-rigorous, assumes that we are dealing with a vertical platform (i.e., small pitch and roll angles). This method requires time-tagged point cloud and trajectory position data. The second approximate method, denoted as simplified, assumes that we are dealing with parallel strips, vertical platform, and minor terrain elevation variations compared to the flying height above ground. Such method can be performed using the LiDAR point cloud only. Experimental results using a real dataset, whose characteristics deviate to some extent from the utilized assumptions in the approximate methods, are presented to provide a comparative analysis of the outcome from the introduced methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.5
• /
• pp.331-341
• /
• 2019

With the popularity of sensor-rich environments, smartphones have become one of the major platforms for obtaining and sharing information. Since it is difficult to utilize GNSS (Global Navigation Satellite System) inside the area with many buildings, the localization of smartphone in this case is considered as a challenging task. To resolve problem of localization using smartphone a four step image-based localization method and procedure is proposed. To improve the localization accuracy of smartphone datasets, MMS (Mobile Mapping System) and Google Street View were utilized. In our approach first, the searching for candidate matching image is performed by the query image of smartphone's using GNSS observation. Second, the SURF (Speed-Up Robust Features) image matching between the smartphone image and reference dataset is done and the wrong matching points are eliminated. Third, the geometric transformation is performed using the matching points with 2D affine transformation. Finally, the smartphone location and attitude estimation are done by PnP (Perspective-n-Point) algorithm. The location of smartphone GNSS observation is improved from the original 10.204m to a mean error of 3.575m. The attitude estimation is lower than 25 degrees from the 92.4% of the adjsuted images with an average of 5.1973 degrees.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.35-47
• /
• 2022

The receiver operating characteristic (ROC) curve was developed to quantify the classification ability of marker values (covariates) on the response variable and has been extended to survival data with diverse missing data structure. When survival data is understood as binary data (status of being alive or dead) at each time point, the ROC curve expressed at every time point results in time-dependent ROC curve and time-dependent area under curve (AUC). In particular, a follow-up study brings the change of cohort and incomplete data structures such as censoring and competing risk. In this paper, we review time-dependent ROC estimators under several contexts and perform simulation to check the performance of each estimators. We analyzed a dementia dataset to compare the prognostic power of markers.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.1
• /
• pp.171-190
• /
• 2023

This study aims to develop algorithms for automatic extraction landmarks from the lower body of women aged 20-54 using the Grasshopper programming language, based on 3D scan data in the 8th SizeKorea dataset. First, 11 landmarks were defined using the morphological features of 3D body surfaces and clothing applications, from which automatic landmark extraction algorithms were developed. To verify the accuracy of the algorithm, this study developed an additional algorithm that could automatically measure 16 items, and algorithm-derived measurements and SizeKorea measurements were compared using paired t-test analysis. The statistical differences between the scan-derived measurements and the SizeKorea measurements were compared, with an allowable tolerance of ISO 20685-1:2018. This study found that the algorithm successfully identified most items except for the crotch point and gluteal fold point. In the case of landmarks with significant differences, the algorithms were modified. This study was significant because scan editing, landmark search, and measurement extraction were successfully performed in one interface, and the developed algorithm has a high efficiency and strong adaptability.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.1-11
• /
• 2023

In this paper, instead of using recurrent neural network, we compare a classification performance of time series imaging algorithms using convolution neural network. There are traditional algorithms that imaging time series data (e.g. GAF(Gramian Angular Field), MTF(Markov Transition Field), RP(Recurrence Plot)) in TSC(Time Series Classification) community. Furthermore, we compare STFT(Short Time Fourier Transform) algorithm that can acquire spectrogram that visualize feature of voice data. We experiment CNN's performance by adjusting hyper parameters of imaging algorithms. When evaluate with GunPoint dataset in UCR archive, STFT(Short-Time Fourier transform) has higher accuracy than other algorithms. GAF has 98~99% accuracy either, but there is a disadvantage that size of image is massive.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.4
• /
• pp.324-341
• /
• 2023

Topological data analysis (TDA) is a data analysis technique, recently developed, that investigates the overall shape of a given dataset. The mapper algorithm is a TDA method that considers the connectivity of the given data and converts the data into a mapper graph. Compared to persistent homology, another popular TDA tool, that mainly focuses on the homological structure of the given data, the mapper algorithm is more of a visualization method that represents the given data as a graph in a lower dimension. As it visualizes the overall data connectivity, it could be used as a prediction method that visualizes the new input points on the mapper graph. The existing mapper packages such as Giotto-TDA, Gudhi and Kepler Mapper provide the descriptive mapper algorithm, that is, the final output of those packages is mainly the mapper graph. In this paper, we develop a simple predictive algorithm. That is, the proposed algorithm identifies the node information within the established mapper graph associated with the new emerging data point. By checking the feature of the detected nodes, such as the anomality of the identified nodes, we can determine the feature of the new input data point. As an example, we employ the fraud credit card transaction data and provide an example that shows how the developed algorithm can be used as a node prediction method.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Advances in Computational Design
• /
• v.3 no.4
• /
• pp.319-338
• /
• 2018

High-performing architecture should be designed by taking into account the mutual dependency between the new building and the local context. The performative architecture plays an important role to avert any unforeseen failures after the building has been built; particularly ones related to the microclimate impacts that affect the human comfort. The use of the concept of solar envelopes helps designers to construct the developable mass of the building design considering the solar access and the site obstruction. However, the current analysis method using solar envelopes lack in terms of integrating the detailed information of the existing context during the simulation process. In architectural design, often the current site modelling not only absent in preserving the complex geometry but also information on the surface characteristics. Currently, the emerging applications of point clouds offer a great possibility to overcome these limitations, since they include the attribute information such as XYZ as the position information and RGB as the color information. This study particularly presents a comparative analysis between the manually built 3D models and the models generated from the point cloud data. The modelling comparisons focus on the relevant factors of solar radiation and a set of simulation to calculate the performance indicators regarding selected portions of the models. The experimental results emphasize an introduction of the design approach and the dataset visibility of the 3D existing environments. This paper ultimately aims at improving the current architectural decision of support environment means, by increasing the correspondence between the digital models for performance analysis and the real environments (context of design) during the conceptual design phase.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.