• 대한조선학회논문집
• /
• 제59권5호
• /
• pp.330-337
• /
• 2022

Research on object detection algorithms using 2D data has already progressed to the level of commercialization and is being applied to various manufacturing industries. Object detection technology using 2D data has an effective advantage, there are technical limitations to accurate data generation and analysis. Since 2D data is two-axis data without a sense of depth, ambiguity arises when approached from a practical point of view. Advanced countries such as the United States are leading 3D data collection and research using 3D laser scanners. Existing processing and detection algorithms such as ICP and RANSAC show high accuracy, but are used as a processing speed problem in the processing of large-scale point cloud data. In this study, PointNet a representative technique for detecting objects using widely used 3D point cloud data is analyzed and described. And RandLA-Net, which overcomes the limitations of PointNet's performance and object prediction accuracy, is described a review of detection technology using point cloud data was conducted.

• 한국산림과학회지
• /
• 제112권2호
• /
• pp.195-208
• /
• 2023

본 연구는 잣나무와 낙엽송을 대상으로 라이다로부터 취득된 3차원의 Point cloud data (PCD)를 이용하여 딥러닝 기반의 수종 분류 모델을 구축하고 분류정확도를 비교·평가하였다. 수종 분류 모델은 라이다 플랫폼(고정식과 이동식), Farthest point sampling (FPS) 기반의 다운샘플링 강도(1024개, 2048개, 4096개, 8192개), 딥러닝 모델(PointNet, PointNet++) 3가지 조건에 따라 총 16개의 모델을 구축하였다. 분류 정확도 평가 결과, 고정식 라이다는 다운샘플링 강도가 8192개인 PCD 자료에 PointNet++ 모델을 적용하였을 때 카파계수가 93.7%로 가장 높았으며, 이동식 라이다는 다운샘플링 강도가 2048개에 PointNet++을 적용하였을 때 카파계수가 96.9%로 가장 높았다. 또한, 플랫폼과 다운샘플링 강도가 동일한 경우 PointNet++이 PointNet보다 정확도가 높았다. 구축된 16개 모델의 오분류 사례는 첫 번째, 수종 간의 구조적인 특징이 유사한 개체목 두 번째, 경사지 또는 임도 주변에 위치하여 편심생장한 개체목 세 번째, 개체목 분할 시 수관부가 수직으로 분할된 개체목에 대해 발생하였다.

• 한국CDE학회논문집
• /
• 제12권4호
• /
• 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.

• 전자공학회논문지B
• /
• 제30B권12호
• /
• pp.12-20
• /
• 1993

In a conventional adaptive echo canceller, an ADF(Adaptive Digital Filter) with TDL(Tapped-Delay Line) structure modelling the echo path uses the LMS(Least Mean Square) algorithm to compute the coefficients, and NET detector using energy comparison method prevents the ADF to update the coefficients during the periods of the NET signal presence. The convergence speed of the LMS algorithm depends on the eigenvalue spread ratio of the reference signal and NET detector using the energy comparison method yields poor detection performance if the magnitude of the NET signal is small. This paper presents a new adaptive echo canceller which uses the pre-whitening filter to improve the convergence speed of the LMS algorithm. The pre-whitening filter is realized by using a low-order lattice predictor. Also, a new NET signal detection algorithm is presented, where the start point of the NET signal is detected by computing the cross-correlation coefficient between the primary input and the ADF output while the end point is detected by using the energy comparison method. The simulation results show that the convergence speed of the proposed adaptive echo canceller is faster than that of the conventional echo canceller and the cross-correlation coefficient yields more accurate detection of the start point of the NET signal.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1992년도 학술논문발표회 논문집 제11권 1호
• /
• pp.23-28
• /
• 1992

The purpose of this paper is to develop a new adaptive echo canceller improving convergence speed and near-end-talker detection performance of the conventional echo canceller. In a conventional adaptive echo canceller, an adaptive digital filter with TDL(Tapped-Delay Line) structure modelling the echo path uses the LMS(Least Mean Square) algorithm to cote the coefficients, and NET detector using energy comparison method prevents the adaptive digital filter to update the coefficients during the periods of the NET signal presence. The convergence speed of the LMS algorithm depends on the eigenvalue spread ratio of the reference signal and NET detector using the energy comparison method yields poor detection performance if the magnitude of the NET signal is small. This paper presents a new adaptive echo canceller which uses the pre-whitening filter to improve the convergence speed of the LMS algorithm. The pre-whitening filter is realized by using a low-order lattice predictor. Also, a new NET signal detection algorithm is presented, where the start point of the NET signal is detected by computing the cross-correlation coefficient between the primary input and the ADF(Adaptive Digital Filter) output while the end point is detected by using the energy comparison method. The simulation results show that the convergence speed of the proposed adaptive echo canceller is faster than that of the conventional echo canceller and the cross-correlation coefficient yield more accurate detection of the start point of the NET signal.

• Korean Journal of Mathematics
• /
• 제10권1호
• /
• pp.5-10
• /
• 2002

In this paper, we investigate the prefilter base on a fuzzy set and fuzzy net ${\varphi}$ on the fuzzy topological space (X,${\delta}$). And we show that the prefilter base $\mathcal{B}({\varphi})$ determines by the fuzzy net ${\varphi}$ converge to a fuzzy point $p$ iff the fuzzy net ${\varphi}$ converge to a fuzzy point $p$. Also we prove that if the prefilter base $\mathcal{B}$ converge to a fuzzy point $p$, then the $\mathcal{B}$ has the cluster point $p$.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.51-60
• /
• 2012

In this paper, we provide the analysis of device model and method between device models for compatible M&S V&V of the NetSPIN. First of all, we analysis features, structure, and classification of the NetSPIN. The second, as a part of reliable V&V process, we analysis network system modeling process, correlation between device modeling process for M&S of the NetSPIN. The third, we suggest making a kind of pool of reference model and module of devices for the increase factor of reuse between device model. We also, at the point view of M&S V&V, conclude that there is the validity of the fidelity in device modeling process. Through the analysis of the NetSPIN device model and suggestion of the method for higher compatibility between device modes, the development process of device model be clearly understood. Also we present the effective method of the development for reliable device mode as the point of V&V.

• 한국지반공학회논문집
• /
• 제17권6호
• /
• pp.225-233
• /
• 2001

본 논문에서는 격자망식 전선배치에 의한 침출수 누출감지시스템을 개발하기 위하여 현장모형시험을 통하여 적용성을 평가하였으며, 전기회로시험을 통하여 격자망 전선 배치에서 발생하는 전기회로적 효과를 파악하고자 하였다. 침출수는 전기저항을 감소시키기 때문에 누출지점에서는 다른 지점에 비해 낮은 전기저항값을 나타내었다. 따라서, 전기저항을 측정하는 본 누출감지시스템에 의하여 임의 지점에서 발생하는 침출수의 누출 감지가 가능하였으며, 평면적 분포도를 통하여 누출위치의 파악이 가능하였다. 전기저항이 감소된 지점과 동일한 전선상에 위치한 다른 센서에 서의 측정값도 약간 감소하는 경향을 나타내었으나, 이는 저항이 작은 곳으로 전류의 흐름이 발생하는 전기회로적 효과로 설명할 수 있었다.

• 스마트미디어저널
• /
• 제11권7호
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1447-1455
• /
• 2017

In a trawl-net simulation, it is very important to process the physical phenomenons resulting from real collisions between a net and fishes. However, because it is very difficult to reconstruct the surface with mass points, many researchers have generally detect the collision using an approximation model employing a sphere, a cube or a cylinder. These approaches occur often result in inaccurate movements of a fish due to the difference between a real-net and a designed-net. So, many systems have manually adjusted a net surface based on actual measurements of mass points. These methods are very inefficient because it needs much times in an adjustment and also causes more incorrect inputs according to a rapid increment in the number of points. Therefore, in this paper, we propose a reconstruction method that it semi-automatically reconstructed trawl-net surfaces using the equation of motion at each mass point in a mass-spring model. To get an easy start in a beginning step of the spread, it enables users to get interactive adjustment on each mass point. We had designed a trawl-net model using geometrical structures of trawl-net and then automatically reconstructed the trawl-net surface using scale-space meshing techniques. Last, we improve the accuracy of reconstructed result by correction user interaction.