• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.248-251
• /
• 2003

This paper presents a distance perception model based around a moving camera, in the context of driving a self-guidance vehicle. Aligned images, by escape points, and acquired by a moving camera, present objects at different positions depending on its relative distance to camera. The objects that are farthest from the observer(the camera) gradually lose their alignment as the distance diminishes. With the current setup, this lack of alignment is noticeable up to a distance of 10 meters. In the paper, the results of real imagery tests are presented and discussed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.145-154
• /
• 2017

In recent years, demand for 1 / 1,000 digital map production has increased in various fields such as construction and urban planning. As a result, the use of low-cost non-metric cameras that replace expensive aerial photogrammetry equipment is required. In Korea, researches are being continuously carried out to produce a large scale digital map by photographing a small target area with a non-metric camera. However, due to the limitation of the accuracy of the non-metric camera, it is difficult to do digital mapping with stereoscopic photographs. In this study, we tried to verify the possibility of large-scale digital mapping to utilize non-metric camera for public survey. For this purpose, the accuracy of the digital mapping results of the non-metric camera and the results of the DMC camera were compared and analyzed. After performing in-situ self-calibration including 8 standard additional parameters, we plotted to a scale of 1/1,000 and confirmed that the RMSE is suitable for public survey accuracy of ${\pm}0.145m$ in horizontal and ${\pm}0.153$ m in vertical.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.9
• /
• pp.1416-1423
• /
• 2017

Lane detection technology is one of the most important issues on car safety and self-driving capability of autonomous vehicle. This paper introduces an accurate lane detection scheme based on OCC(Optical Camera Communication) for moving vehicles. For lane detection of moving vehicles, the streetlights and the front camera of the vehicle were used for a transmitter and a receiver, respectively. Based on the angle information of multiple streetlights in a captured image, the distance from sidewalk can be calculated using non-linear regression analysis. Simulation results show that the proposed scheme shows robust performance of accurate lane detection.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.128-131
• /
• 2004

In this paper, we describe reconstructed 3D-urban modeling techniques for laser scanner and CCD camera system, which are loading on the vehicle. We use two laser scanners, the one is horizon scanner and the other is vertical scanner. Horizon scanner acquires the horizon data of building for localization. Vertical scan data are main information for constructing a building. We compared extraction of edge aerial image with laser scan data. This method is able to correct the cumulative error of self-localization. Then we remove obstacles of 3D-reconstructed building. Real-texture information that is acquired with CCD camera is mapped by 3D-depth information. 3D building of urban is reconstructed to 3D-virtual world. These techniques apply to city plan. 3D-environment game. movie background. unmanned-patrol etc.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2689-2708
• /
• 2016

Multi-camera systems which integrate two or more low-cost digital cameras are adopted to reach higher ground coverage and improve the base-height ratio in low altitude remote sensing. To guarantee accurate multi-camera integration, the geometric relationship among cameras must be determined through platform calibration techniques. This paper proposed a combined two-step platform calibration method. In the first step, the static platform calibration was conducted based on the stable relative orientation constraint and convergent conditions among cameras in static environments. In the second step, a dynamic platform self-calibration approach was proposed based on not only tie points but also straight lines in order to correct the small change of the relative relationship among cameras during dynamic flight. Experiments based on the proposed two-step platform calibration method were carried out with terrestrial and aerial images from a multi-camera system combined with four consumer-grade digital cameras onboard an unmanned aerial vehicle. The experimental results have shown that the proposed platform calibration approach is able to compensate the varied relative relationship during flight, acquiring the mosaicing accuracy of virtual images smaller than 0.5pixel. The proposed approach can be extended for calibrating other low-cost multi-camera system without rigorously mechanical structure.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.3
• /
• pp.43-51
• /
• 2020

Currently, the second level of the six stages of self-driving technology, as defined by SAE, is commercialized, and the third level is preparing for commercialization. The purpose of ACC is to be evaluated as a system useful for preventing and preventing accidents by minimizing driver fatigue through longitudinal speed control and relative distance control of the vehicle. In this regard, for the study of safety assessment methods in the practical environment of ACC. Distance measurement method using monocular camera and data acquisition equipment such as DGPS are utilized. Based on the evaluation scenario considering the domestic road environment proposed by the preceding study, the relative distance obtained from equipment such as DPGS and the relative distance using a monocular camera in the actual test is verified by comparing and analyzing the safety assessment. The comparison by scenario results showed a minimum error rate of 3.83% in Scenario 1 and a maximum of 14.61% in Scenario 6. The cause of the maximum error is that the lane recognition is not accurate in the camera image and irregular operation conditions such as rushing in or exiting the surrounding area from the walkway. It is expected that safety evaluation using a monocular camera will be possible for other ADAS systems in the future.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1168-1171
• /
• 2003

The visuo-motor map is based on the Kohonen's self-organizing map. The map is learned the relation of the end effecter coordinates and the joint angles. In this paper, a 3 d-o-fmanipulator which moves in the 2D space is targeted. A CCD camera is set beside the manipulator, and the end effecter coordinates are given from the image of a manipulator. As a result of learning, the end effecter can be moved to the destination without exact teaching.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.404-404
• /
• 2000

This paper presents a single vision-based sel(-localization method in an corridor environment. We use the Hough transform for finding parallel lines and vertical lines. And we use these cross points as feature points and it is calculated relative distance from mobile robot to these points. For matching environment map to feature points, searching window is defined and self-localization is performed by matching procedure. The result shows the suitability of this method by experiment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.779-782
• /
• 2010

Self-calibration에서 3차원 좌표의 복원은 호모그래피 행렬 H를 계산하면 얻을 수 있다. 이 호모그래피 행렬을 얻는 방법은 dual absolute quadric, Kruppa Equation(dual conic), plane at infinity(modulus constraint)를 사용하는 방법과 같이 세 가지 방법이 일반적으로 사용된다. 제안하는 방식은 dual absolute quadric을 사용한다. 카메라 내부 속성이 모든 뷰에서 동일하고 비틀림이나 영상의 원점이 중심이라는 가정을 두고 호모그래피 행렬 H를 계산한다. 실험을 통해서 주어진 가정으로 정밀한 복원이 가능함을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2033-2036
• /
• 2004

A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.