• 자동차안전학회지
• /
• 제13권4호
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• 한국멀티미디어학회논문지
• /
• 제16권6호
• /
• pp.764-781
• /
• 2013

본 논문에서는 시차영상 생성과 레이블링(labeling)을 동시에 수행하는 빌보드 스윕 스테레오 시차정합 알고리즘을 적용하고, 두 단계로 구성된 복합 가설생성(hypothesis generation) 단계를 적용함으로서 거짓알림(false alarm)을 줄이고, 차량 검출의 정확도를 높이는 방법을 제안한다. 먼저 차량의 정면에 장착된 두 대의 카메라를 이용하여 영상을 획득하고, 이 영상을 사용하여 빌보드 스윕 스테레오 시차정합 알고리즘을 수행하여 지면과 배경이 제거된 장애물(obstacle)만이 존재하는 특수한 형태의 시차영상을 생성한다. 이렇게 생성된 지면과 배경이 제거된 레이블링된 시차영상을 이용하여 차량 검출 및 추적을 수행한다. 차량 검출 및 추적단계는 크게 세 단계로 나눠진다. 첫 번째 단계는 학습 단계로서 학습데이터로부터 Gabor필터를 사용해서 특징점을 추출하고, 추출된 특징점을 학습한 뒤 서포트 벡터머신 분류기를 생성하는 단계이다. 두 번째 단계는 스테레오 카메라의 영상 중 주 카메라의 영상으로부터 에지 정보를 추출하고, 지면과 배경이 제거된 시차 영상으로부터 얻어진 시차정보를 이용해서 차량이 존재하는 후보영역을 뽑은 뒤 서포트 벡터머신 분류기를 사용하여 차량을 검출하는 단계이다. 마지막 단계는 차량 추적단계로서 검출이 완료된 차량들은 다음 프레임에서 템플릿 매칭을 수행하여 추적한다. 이는 추적에 성공할 경우 다음 프레임의 차량 검출시 후보영역에서 배제함으로서 전체적인 차량 검출 성능을 향상시킨다.

• 한국측량학회지
• /
• 제26권2호
• /
• pp.149-156
• /
• 2008

본 연구에서는 고해상도 단영상과 수치지도를 이용하여 건물정보 추출 및 갱신을 위한 방법을 개발하는데 연구의 목적이 있다. 이를 위해 우선 QuicBird 단영상과 수치지도의 자동기하보정을 통한 수치정사영상을 제작하였다. 건물레이어와 Canny 에지 추출자에 의해 획득된 영상에지와의 템플릿 매칭과정을 통해 건물높이정보를 추출하였다. 최종적으로 앞선 매칭결과를 그리디 스네이크 알고리즘의 초기치로 사용하여 일부건물에 대한 형상을 수정하였다. 제안된 기법의 효율성을 평가하기위해 LiDAR DSM과 1:1,000 수치지도를 이용하여 정확도 평가를 수행하였다. 실험결과 제안한 기법은 건물정보 추출 및 갱신에 유용하게 적용될 수 있으리라 판단된다.

• Spatial Information Research
• /
• 제13권2호
• /
• pp.185-194
• /
• 2005

본 연구의 목적은 지적기반의 주소 알고리즘의 개발을 통하여 주소체계의 표준화를 확립하고 GIS와 연계하여 전국을 하나의 정보권역으로 설정하기 위한 시도이다. 이를 위해 전자정부의 지적정보 현황을 분석하고 행정정보와 지적정보의 통합 방안을 제시하여 주소 알고리즘의 활용방안을 모색하였다. 본 연구는 민간과 공공부문의 효율적인 업무연계를 위한 매개체로 활용되며, 자치단체의 정보화를 더욱 활성화할 것으로 사료된다.

• 대한임베디드공학회논문지
• /
• 제3권3호
• /
• pp.143-150
• /
• 2008

In this paper, we investigate a real-time environment recognition system based on stereo vision for moving object. This system consists of stereo matching, obstacle detection and distance estimation. In stereo matching part, depth maps can be obtained real road images captured adjustable baseline stereo vision system using belief propagation(BP) algorithm. In detection part, various obstacles are detected using only depth map in case of both v-disparity and column detection method under the real road environment. Finally in estimation part, asymmetric parabola fitting with NCC method improves estimation of obstacle detection. This stereo vision system can be applied to many applications such as unmanned vehicle and robot.

• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.108-114
• /
• 2015

Automated driving systems require a high level of performance regarding environmental perception, especially in urban environments. Today's on-board sensors such as radars or cameras do not reach a satisfying level of development from the point of view of robustness and availability. Thus, map data is often used as an additional data input to support these systems. An accurate digital map is used as a powerful additional sensor. In this paper, we propose a new approach for vehicle localization using a lane map and a single-layer LiDAR. The maps are created beforehand using a highly accurate DGPS and a single-layer LiDAR. A pose estimation of the vehicle was derived from an iterative closest point (ICP) match of LiDAR's intensity data to the lane map, and the estimated pose was used as an observation inside a Kalmanfilter framework. The achieved accuracy of the proposed localization algorithm is evaluated with a highly accurate DGPS to investigate the performance with respect to lateral vehicle control.

• 한국정보처리학회논문지
• /
• 제6권11호
• /
• pp.3165-3177
• /
• 1999

With the recent outstanding advance in computer software and hardware, a number of researches to enhance the manufacturing speed and the process accuracy has been undertaken in many fields of textile industry. Frequently issued problems of automatic recognition of textile wrinkles in a grey scale image are as follows. First, changes in grey level intensity of wrinkles are so minute. Second, as both colors and patterns in a grey scale image appear in grey level intensity, it is difficult to sort out the wrinkle information only. Third, it is also difficult to distinguish grey level intensity changed by wrinkles from those by uneven illumination. This paper suggests a method of automatic recognition of textile wrinkles that can solve above problems concerned with wrinkles, which can be raised in a manufacturing process as one of errors. In this paper, we first make the outline of wrinkles distinctly, apply the block matching algorithm used in motion estimation, and then estimate block locations of target images corresponding to blocks of standard images with the assumption that wrinkles are kind of textile distortions caused by directional forces. We plot a "wrinkle map" considering distances between wrinkles as depths of wrinkles. But because mismatch can occur by different illumination intensity and changes in tensions and directions of the force, there are also undesirable patterns in the map. Post processing is needed to filter them out and get wrinkles information only. We use average grey level intensity of wrinkle map to recognize wrinkles. When it comes to textile with colors and patterns, previous researches on wrinkles in grey scale image hasn't been successful. But we make it possible by considering wrinkles as distortion.istortion.

• Journal of Electrical Engineering and information Science
• /
• 제3권2호
• /
• pp.211-221
• /
• 1998

It is becoming apparent that stereo matching algorithms need much information from high level cognitive processes. Otherwise, conventional algorithms based on bottom-up control alone are susceptible to local minima. We introduce a system that consists of two levels. A lower level, using a usual matching method, is based upon the local neighborhood and a second level, that can integrate the partial information, is aimed at contextual matching. Conceptually, the introduction of bottom-up and top-down feedback loop to the usual matching algorithm improves the overall performance. For this purpose, we model the image attributes using a Markov random field (MRF) and thereupon derive a maximum a posteriori (MAP) estimate. The energy equation, corresponding to the estimate, efficiently represents the natural constraints such as occlusion and the partial informations from the other levels. In addition to recognition, we derive a training method that can determine the system informations from the other levels. In addition to recognition, we derive a training method that can determine the system parameters automatically. As an experiment, we test the algorithms using random dot stereograms (RDS) as well as natural scenes. It is proven that the overall recognition error is drastically reduced by the introduction of contextual matching.

• ETRI Journal
• /
• 제35권6호
• /
• pp.1011-1020
• /
• 2013

In this paper, we present a method for obtaining a high-quality 3D depth. The advantages of active pattern projection and passive stereo matching are combined and a system is established. A diffractive optical element (DOE) is developed to project the active pattern. Cross guidance (CG) and auto guidance (AG) are proposed to perform the passive stereo matching in a stereo image in which a DOE pattern is projected. When obtaining the image, the CG emits a DOE pattern periodically and consecutively receives the original and pattern images. In addition, stereo matching is performed using these images. The AG projects the DOE pattern continuously. It conducts cost aggregation, and the image is restored through the process of removing the pattern from the pattern image. The ground truth is generated to estimate the optimal parameter among various stereo matching algorithms. Using the ground truth, the optimal parameter is estimated and the cost computation and aggregation algorithm are selected. The depth is calculated and bad-pixel errors make up 4.45% of the non-occlusion area.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2011년도 춘계 종합학술대회 논문집
• /
• pp.57-58
• /
• 2011

스테레오 정합 방법에는 크게 영역기반 방식과 특징기반 방식으로 나뉠수 있으며 보통 사용자가 특징점을 입력해야 하는 특징기반보다는 광범위하게 사용할 수 있는 영역기반 방식의 스테레오 정합법이 많이 사용되고 있다. 하지만 영역기반은 해당 영역 즉 블록 단위로 비교를 해야 하기 때문에 실시간 스테레오 정합에는 계산 시간이 많이 걸리게 된다. 따라서 본 연구에서 제안하는 Line Disparity Map 알고리즘은 정합 점을 라인별로 비교하기 때문에 블록 방식보다 빠르고, 라인의 기울기를 바탕으로 정합점을 찾기 때문에 주변환경에 영향을 받지 않는 장점이 있다.