• 전자공학회논문지
• /
• 제52권12호
• /
• pp.150-157
• /
• 2015

보행자 인식은 차량자율주행 및 사고방지를 위해 중요한 요소기술로서 많이 연구되고 있다. 이 기술들은 크게 카메라기반과 LIDAR 기반, 두 가지로 구별할 수 있다. 카메라 기반 방법과 대비되어 LIDAR 기반 방법은 화각이 넓고 조도환경에 영향을 받지 않는다는 강점이 있다. 하지만 LIDAR 기반 방법은 먼 물체를 인식하기엔 센서 해상도가 낮고, 복잡한 환경에서는 분할 오류나 폐색 등의 원인으로 인식률이 낮아진다는 문제점이 있다. 본 논문에서는 3차원 LIDAR 기반 보행자 탐지 알고리즘의 낮은 인식률을 개선시키기 위해 다중객체추적 기법의 하나인 GM-PHD 필터를 이용한 두 가지 성능 향상 방법을 제안한다. 첫 번째 방법은 GM-PHD 필터를 이용해 이전 프레임의 포인트를 현재 프레임의 물체에 자동으로 누적하여 물체 해상도 및 보행자 분류 성능을 향상시킨다. 두 번째 방법은 인식 성능이 낮은 상황에 맞춰 개선된 GM-PHD 필터를 분류된 다중객체에 적용하여 탐지 성능을 더욱 강화시킨다. 직접 취득한 도로 주행 데이터에 두 방법을 적용하여 제안한 방법이 기존의 보행자 탐지 알고리즘 성능을 대폭 향상시키는 것을 정량적으로 증명하였다.

• 한국통신학회논문지
• /
• 제39B권9호
• /
• pp.590-597
• /
• 2014

본 논문은 고품질 파노라마 영상 획득을 위하여 대상 공간을 여러 대의 카메라로 촬영 시, 촬영 정보를 제공하는 모니터링 시스템과 클라우드 컴퓨팅을 이용한 생성 과정 분산 처리에 관한 것이다. 파노라믹 비디오의 특성상 이웃 카메라 간 일정한 중복영역을 가져야 하지만 이로 인하여 동일한 촬영 대상에 대해 촬영 화각이 다르고, 카메라의 물리적인 크기로 인하여 촬영 중심점을 동일하게 맞추기 어려운 상황에서 2D 입력 영상기반으로 모니터링 하여 카메라를 보정하는 경우 시차원인으로 오보정이 발생하는 문제가 있다. 이를 해결하기 위하여 카메라별 촬영 화각에 따라 3차원으로 투영하여 모니터링 함으로써 카메라 오보정 문제를 최소화하고 획득 영상의 품질을 높이는 3차원 기반 모니터링 시스템을 제안한다. 또한 여러 영상을 하나의 영상으로 합성하는 파노라믹 비디오 생성알고리즘은 합성 정보추출과 합성, 두 부분으로 나눌 수 있는데 이를 클라우드와 클라이언트에 적절히 분산하여 고화질의 파노라믹 비디오를 효율적으로 서비스 하는 방법에 대해 제안한다.

• 한국생산제조학회지
• /
• 제6권2호
• /
• pp.10-18
• /
• 1997

This paper presents the development of real-time estimation and control details for a computer vision-based robot control method. This is accomplished using a sequential estimation scheme that permits placement of these points in each of the two-dimensional image planes of monitoring cameras. Estimation model is developed based on a model that generalizes know 4-axis Scorbot manipulator kinematics to accommodate unknown relative camera position and orientation, etc. This model uses six uncertainty-of-view parameters estimated by the iteration method. The method is tested experimentally in two ways : First the validity of estimation model is tested by using the self-built test model. Second, the practicality of the presented control method is verified in performing 4-axis manipulator's assembly task. These results show that control scheme used is precise and robust. This feature can open the door to a range of application of multi-axis robot such as deburring and welding.

• 로봇학회논문지
• /
• 제2권1호
• /
• pp.21-28
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. And the article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguity conditions. We propose to track the moving objects by generating hypotheses not in the image plan but on the top-view reconstruction of the scene. Comparative results on real video sequences show the advantage of our method for multi-object tracking. Also, the method is applied to the intelligent environment and its performance is verified by the experiments.

• Journal of information and communication convergence engineering
• /
• 제10권4호
• /
• pp.411-419
• /
• 2012

This paper proposes a semi-automatic image-based approach for 3-dimensional (3D) modeling of buildings along streets. Image-based urban 3D modeling techniques are typically based on the use of aerial and ground-level images. The aerial image of the relevant area is extracted from publically available sources in Google Maps by stitching together different patches of the map. Panoramic images are common for ground-level recording because they have advantages for 3D modeling. A panoramic video recorder is used in the proposed approach for recording sequences of ground-level spherical panoramic images. The proposed approach has two advantages. First, detected camera trajectories are more accurate and stable (compared to methods using multi-view planar images only) due to the use of spherical panoramic images. Second, we extract the texture of a facade of a building from a single panoramic image. Thus, there is no need to deal with color blending problems that typically occur when using overlapping textures.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.566-571
• /
• 2009

A calibration method for multiple sets of stereo vision cameras is proposed. To measure the three-dimensional shape of a very long object, measuring the object at different viewpoints and registration of the data are necessary. In this study, two lasers beams generate two strings of calibration targets, which form straight lines in the world coordinate system. An evaluation function is defined to calculate the sum of the squares of the distances between each transformed target and the fitted line representing the laser beam to each target, and the distances between points appearing in the data sets of two adjacent viewpoints. The calculation process for the approximation method based on data linearity is presented. The experimental results show the effectiveness of the method.

• Journal of Platform Technology
• /
• 제6권4호
• /
• pp.18-25
• /
• 2018

This paper describes a real-time human and robot tracking method in Intelligent Space with multi-camera networks. The proposed method detects candidates for humans and robots by using the histogram of oriented gradients (HOG) feature in an image. To classify humans and robots from the candidates in real time, we apply cascaded structure to constructing a strong classifier which consists of many weak classifiers as follows: a linear support vector machine (SVM) and a radial-basis function (RBF) SVM. By using the multiple view geometry, the method estimates the 3D position of humans and robots from their 2D coordinates on image coordinate system, and tracks their positions by using stochastic approach. To test the performance of the method, humans and robots are asked to move according to given rectangular and circular paths. Experimental results show that the proposed method is able to reduce the localization error and be good for a practical application of human-centered services in the Intelligent Space.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.216-217
• /
• 2019

Light Field (LF) image can be understood as a set of images captured by a multi-view camera array at the same time. The changes among views can be modeled by a general motion model such as affine motion model. In this paper, we study the impact of affine coding tool of Versatile Video Coding (VVC) on LF image compression. Our experimental results show a small contribution by affine coding tool in overall LF image compression of roughly 0.2% - 0.4%.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.297-299
• /
• 2020

본 논문에서는 다시점 카메라 시스템을 통해 실사기반의 3D 모델을 획득하여 모션센서와 같은 별도의 기기 없이 해당 모델에 대한 고정밀 스켈레톤 추출 기법에 대해서 제시한다. 다시점 카메라 시스템을 이용하여 생성한 3D 모델을 앞, 뒤, 좌, 우 각 위치에서의 사상 매트릭스로 사상 영상을 생성하고 딥러닝 기술을 이용하여 2D 스켈레톤을 추출한다. 그리고 사상 매트릭스의 역변환 과정을 통해 2D 스켈레톤의 삼차원 좌표를 계산하고 추가적인 후처리를 통해 고정밀 스켈레톤을 획득한다.

• 한국산업융합학회 논문집
• /
• 제27권2_2호
• /
• pp.319-324
• /
• 2024

In this paper, the Artificial Intelligence Space(AI-Space) for human-robot interface is presented, which can enable human-computer interfacing, networked camera conferencing, industrial monitoring, service and training applications. We present a method for representing, tracking, and objects(human, robot, chair) following by fusing distributed multiple vision systems in AI-Space. The article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguous conditions. We propose to track the moving objects(human, robot, chair) by generating hypotheses not in the image plane but on the top-view reconstruction of the scene.