• 정보처리학회논문지B
• /
• 제18B권5호
• /
• pp.255-264
• /
• 2011

본 논문에서는 스테레오 비전기반의 컬럼 검출과 조감도 맵핑을 이용한 전방 차량 검출 알고리즘을 제안한다. 제안된 알고리즘은 실제 복잡한 도로 환경에서 전방 차량을 강건하게 검출할 수 있다. 전체적인 알고리즘은 도로 특징기반의 컬럼 검출, 조감도 기반의 장애물체 세그멘테이션, 차량 특징기반의 영역 재결합, 차량 검증으로 크게 네 단계로 구성되어 있다. 먼저 v-시차맵상에서 최대 빈도값을 이용하여 도로 특징 정보만을 추출한 후, 이를 기반으로 컬럼 검출을 수행한다. 도로 특징 정보는 기존의 중앙값과 달리 도로 환경에 영향을 받지 않아 도로상의 장애물체 유무를 판단하는 기준으로 적절하다. 그러나 다수의 장애물체가 동일한 장애물체로 검출되는 것을 해결하기 위하여 조감도 기반의 세그멘테이션을 수행한다. 조감도는 시차맵과 카메라 정보를 기반으로 계산된 장애물체들의 위치를 평면상에 표시함으로써 장애물체를 쉽게 분리할 수 있다. 그러나 분리된 장애물체 중에는 동일한 장애물체인 경우도 있으므로, 도로상의 차량 특징을 기반으로 장애물체가 동일한지를 판단하여 재결합하는 과정을 수행한다. 마지막으로 시차맵과 그레이 영상기반의 차량 검증 단계를 수행하여 차량만 검출한다. 제안된 알고리즘을 실제 복잡한 도로 영상에 적용함으로써 차량 검증 성능을 검증한다.

• 대한전기학회논문지
• /
• 제40권4호
• /
• pp.351-359
• /
• 1991

This paper describes performances of speaker adaptation using a probabilistic spectral mapping matrix in hidden-Markov model(HMM) -based Korean isolated word recognition. Speaker adaptation based on probabilistic spectral mapping uses a well-trained prototype HMM's and is carried out by Viterbi, dynamic time warping, and forward-backward algorithms. Among these algorithms, the best performance is obtained by using the Viterbi approach together with codebook adaptation whose improvement for isolated word recognition accuracy is 42.6-68.8 %. Also, the selection of the initial values of the matrix and the normalization in computing the matrix affects the recognition accuracy.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.183-185
• /
• 2003

Spatially referenced mobile mapping (MM) images contain rich information of man-made objects , e.g. road centerlines, buildings, light poles, traffic signs ,billboards and line trees etc. Therefore, the applications in transportation, urban 3D reconstruction, utility management are implemented increasingly. It’s a fundamental issue lies in MM image process that how to orient this image in the object space including interior orientation of camera and the exterior orientation of image. In this paper, the algorithm of automatic acquirement of DC (Digital Camera) parameters based on MM images is illustrated. And then, the mapping between image space and object space for MM images is described.

• 로봇학회논문지
• /
• 제18권1호
• /
• pp.59-65
• /
• 2023

This paper proposes an Extended and Adaptive Inverse Perspective Mapping (EA-IPM) model that can obtain an accurate bird's-eye view (BEV) from the forward-looking monocular camera on the sidewalk with various curves. While Inverse Perspective Mapping (IPM) is a good way to obtain ground information, conventional methods assume a fixed relationship between the camera and the ground. Due to the nature of the driving environment of the mobile robot, there are more walking environments with frequent motion changes than flat roads, which have a fatal effect on IPM results. Therefore, we have developed an extended IPM process to be applicable in IPM on sidewalks by adding a formula for complementary Y-derive processes and roll motions to the existing adaptive IPM model that is robust to pitch motions. To convince the performance of the proposed method, we evaluated our results on both synthetic and real road and sidewalk datasets.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2154-2159
• /
• 2005

This paper presents the kinematic analysis of two robots, an exoskeleton type master robot and a human like slave robot with two arms. Two robots are designed and built to be equivalent as motion following robots. The operator wears the exoskeleton robot to generate motions, then the slave robot is required to follow after the motion of the master robot. However, different kinematic configuration yields position mismatches of the end-effectors. To synchronize motions of two robots, kinematic analysis of mapping is analyzed. The forward and inverse kinematics have been simulated and the corresponding experiments are also conducted to confirm the proposed mapping analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2273-2286
• /
• 2018

This paper describes transformations between elemental image arrays and a RGBD image for three-dimensional integral imaging and transmitting systems. Two transformations are introduced and analyzed in the proposed method. Normally, a RGBD image is utilized in efficient 3D data transmission although 3D imaging and display is restricted. Thus, a pixel-to-pixel mapping is required to obtain an elemental image array from a RGBD image. However, transformations and their analysis have little attention in computational integral imaging and transmission. Thus, in this paper, we introduce two different mapping methods that are called as the forward and backward mapping methods. Also, two mappings are analyzed and compared in terms of complexity and visual quality. In addition, a special condition, named as the hole-free condition in this paper, is proposed to understand the methods analytically. To verify our analysis, we carry out experiments for test images and the results indicate that the proposed methods and their analysis work in terms of the computational cost and visual quality.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.897-900
• /
• 2000

본 논문에서는 종방향 충돌경보 및 회피시스템(FCWA ; forward collision warning and avoidance)의 일환으로 가변적인 경사도를 가지는 고속도로상의 차선, 차량, 그리고 도로의 곡률을 효과적으로 검출할 수 있는 알고리듬을 제안하였다. 먼저 2D 영상좌표계에 나타나는 투영효과를 제거하기 위한 역투영(IPM; inverse perspective mapping)기법을 소개하였다. 또한 IPM과 필터로부터 차선과 차량을 효과적으로 검출할 수 있는 알고리듬을 소개하였다. 마지막으로 경사가 있는 실제도로영상에 대한 IMP의 수정된 파라미터 보정에 대한 개념 및 실제도로의 곡률 검출을 위한 기하학적 함수 추정기법을 설명하였다 실험결과 제안한 알고리듬이 실제도로영상에서 차선, 차량, 그리고 곡률의 검출에 효과적임을 확인할 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.349-350
• /
• 2008

Average throughput estimation of EV-DO forward link is implemented on the basis of the serving coverage area per sector instead of time consuming and complicated Monte Carlo simulation. For the implementation of this analysis function in cell planning tool, $CellTREK^{(R)}$, developed by KT, both SNR vs. DRC mapping table and receiver sensitivity are suggested as the satisfying criteria to be satisfied above each threshold level simultaneously.

• International Journal of Precision Engineering and Manufacturing
• /
• 제9권4호
• /
• pp.45-50
• /
• 2008

The Fourier-Mellin transform is the theoretical basis for the translation, rotation, and scale invariance of an image. However, its implementation requires a log-polar map of the original image, which requires logarithmic sampling of a radial variable in that image. This means that the mapping process is accompanied by considerable loss of data. To solve this problem, we propose a dual log-polar map that uses both a forward image map and a reverse image map simultaneously. Data loss due to the forward map sub-sampling can be offset by the reverse map. This is the first step in creating an invertible log-polar map. Experimental results have demonstrated the effectiveness of the proposed scheme.

• 한국정밀공학회지
• /
• 제15권2호
• /
• pp.7-13
• /
• 1998

This paper presents a methodology for determining machining conditions in Electric Discharge Wire-Cut. Unification of two phase neural network approach with an automatic generation of machining parameters is designed. The first phase neural network, which is 1 to M backward-mapping neural net, produces approximate machining conditions. Using approximate conditions, all possible conditions are newly created by the proposed automatic generation procedure. The second phase neural net, which is a M to 1 forward-mapping neural net, determines the best one among the generated candidates. Simulation results with ANN are given to verify that the presenting methodology could apply for determining machining parameters in Electric Discharge Wire-Cut.