• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.733-734
• /
• 2016

This study proposes a novel approach for ground segmentation of 3D point cloud. We combine two techniques: gradient threshold segmentation, and mean height evaluation. Acquired 3D point cloud is represented as a graph data structures by exploiting the structure of 2D reference image. The ground parts nearing the position of the sensor are segmented based on gradient threshold technique. For sparse regions, we separate the ground and nonground by using a technique called mean height evaluation. The main contribution of this study is a new ground segmentation algorithm which works well with 3D point clouds from various environments. The processing time is acceptable and it allows the algorithm running in real time.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1100-1105
• /
• 2022

Denoising, registering, and detecting changes of 3D digital map are generally conducted by skilled technicians, which leads to inefficiency and the intervention of individual judgment. The manual post-processing for analyzing 3D point cloud data of construction sites requires a long time and sufficient resources. This study develops automation technology for analyzing 3D point cloud data for construction sites. Scanned data are automatically denoised, and the denoised data are stored in a specific storage. The stored data set is automatically registrated when the data set to be registrated is prepared. In addition, regions with non-homogeneous densities will be converted into homogeneous data. The change detection function is developed to automatically analyze the degree of terrain change occurred between time series data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.783-786
• /
• 2021

In recent years, the use of LiDAR sensors is increasing as autonomous driving, robot control, and drones are considered more. Contrary to ordinary cameras, LiDAR sensors make it possible to handle challenging problems by calculating the distance between objects. This crucial characteristic makes more active research on deep learning models dealing with point clouds which are data of LiDAR. In this paper, among the schemes of using the point cloud, the Point-based approach is mainly discussed. Furthermore, future streams and insights can be considered by looking at solving methods and the limitations.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• 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.

• Journal of Information Processing Systems
• /
• v.10 no.2
• /
• pp.240-255
• /
• 2014

Cloud computing has increasingly been drawing attention these days. Each big company in IT hurries to get a chunk of meat that promises to be a whopping market in the future. At the same time, information is always associated with security and risk problems. Nowadays, the handling of these risks is no longer just a technology problem, with a good deal of literature focusing on risk or security management and framework in the information system. In this paper, we find the specific business meaning of the BMIS model and try to apply and leverage this model to cloud risk. Through a previous study, we select and determine the causal risk factors in cloud service, which are also known as CSFs (Critical Success Factors) in information management. Subsequently, we distribute all selected CSFs into the BMIS model by mapping with ten principles in cloud risk. Finally, by using the leverage points, we try to leverage the model factors and aim to make a resource-optimized, dynamic, general risk control business model for cloud service providers.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.683-696
• /
• 2024

The point cloud provides viewers with intuitive geometric understanding but requires a huge amount of data. Moving Picture Experts Group (MPEG) has developed video-based point-cloud compression in the range of 300-700. As the compression rate increases, the complexity increases to the extent that it takes 101.36 s to compress one frame in an experimental environment using a personal computer. To realize real-time point-cloud compression processing, the direct patch projection (DPP) method proposed herein simplifies the complex patch segmentation process by classifying and projecting points according to their geometric positions. The DPP method decreases the complexity of the patch segmentation from 25.75 s to 0.10 s per frame, and the entire process becomes 8.76 times faster than the conventional one. Consequently, this proposed DPP method yields similar peak signal-to-noise ratio (PSNR) outcomes to those of the conventional method at reduced times (4.7-5.5 times) at the cost of bitrate overhead. The objective and subjective results show that the proposed DPP method can be considered when low-complexity requirements are required in lightweight device environments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.482-484
• /
• 2019

Learning and analyzing 3D point clouds with deep networks is challenging due to the limited and irregularity of the data. In this paper, we present a data-driven point cloud augmentation technique. The key idea is to learn multilevel features per point and to reconstruct to a similar point set. Our network is applied to a projection loss function that encourages the predicted points to remain on the geometric shapes with a particular target. We conduct various experiments using ShapeNet part data to evaluate our method and demonstrate its possibility. Results show that our generated points have a similar shape and are located closer to the object.

• Korean Journal of Computational Design and Engineering
• /
• v.12 no.4
• /
• pp.274-282
• /
• 2007

In this paper, a method of constructing a rectangular net from unorganized point cloud data is presented. In the method an implicit surface that fits the given point data is generated by using principal component analysis(PCA) and adaptive domain decomposition method(ADDM). Then a complete and quality rectangular net can be obtained by extracting voxel data from the implicit surface and projecting exterior faces of extracted voxels onto the implicit surface. The main advantage of the proposed method is that a quality rectangular net can be extracted from randomly scattered 3D points only without any further information. Furthermore the results of this works can be used to obtain many useful information including a slicing data, a solid STL model and a NURBS surface model in many areas involved in treatment of large amount of point data by proper processing of implicit surface and rectangular net generated previously.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.346-353
• /
• 2023

In this paper, we propose an innovative approach that leverages deep learning to find optimal reference points for achieving precise tooth segmentation in three-dimensional tooth point cloud data. A dataset consisting of 350 aligned maxillary and mandibular cloud data was used as input, and both end coordinates of individual teeth were used as correct answers. A two-dimensional image was created by projecting the rendered point cloud data along the Z-axis, where an image of individual teeth was created using an object detection algorithm. The proposed algorithm is designed by adding various modules to the Unet model that allow effective learning of a narrow range, and detects both end points of the tooth using the generated tooth image. In the evaluation using DSC, Euclid distance, and MAE as indicators, we achieved superior performance compared to other Unet-based models. In future research, we will develop an algorithm to find the reference point of the point cloud by back-projecting the reference point detected in the image in three dimensions, and based on this, we will develop an algorithm to divide the teeth individually in the point cloud through image processing techniques.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.10
• /
• pp.775-784
• /
• 2013

Mobile operators are considering a variety of technical measures to cope with the explosion of data while reducing TCO(Total Cost of Ownership) of their networks. In this paper, to investigate the possibility about one of such technical measures, system level simulation to evaluate the performance of the capacity and mobility was performed in cloud base station structure to apply coordinated multi-point transmission and reception. As a result, we find out that system capacity and mobility performance may be improved according to the scale and application area of cloud base station with the operation of coordinated multi-point transmission and reception, and these mutual causality can provide practical guidelines to mobile network's operation.