• Journal of Multimedia Information System
• /
• 제1권1호
• /
• pp.1-10
• /
• 2014

In this paper, we propose a new view synthesis technique for coding of multi-view color and depth data in arbitrary camera arrangements. We treat each camera position as a 3-D point in world coordinates and build clusters of those vertices. Color and depth data within a cluster are gathered into one camera position using a hierarchical representation based on the concept of layered depth image (LDI). Since one camera can cover only a limited viewing range, we set multiple reference cameras so that multiple LDIs are generated to cover the whole viewing range. Therefore, we can enhance the visual quality of the reconstructed views from multiple LDIs comparing with that from a single LDI. From experimental results, the proposed scheme shows better coding performance under arbitrary camera configurations in terms of PSNR and subjective visual quality.

• 한국정보통신학회논문지
• /
• 제16권2호
• /
• pp.266-272
• /
• 2012

본 논문에서는 차량 정보를 이용한 멀티뷰 주차 보조 시스템을 제안한다. 제안한 시스템은 운전자에게 차량 주변의 세 방향의 영상을 제공한다. 평행주차나 주차장에서 주차를 할 때 사각지역을 줄이고, 편안하고 안전한 주행을 위해 핸들 조정에 따라 와이드 앵글의 CCD 카메라 영상을 출력한다. 핸들 조향각과 기어 위치는 차량의 ABS ECU에서 OBD-II 포트를 통해 획득한다. 제안한 시스템은 차량 실험을 통해 성능을 확인하였다.

• Journal of Information Display
• /
• 제5권4호
• /
• pp.38-44
• /
• 2004

In this paper, a server and client simulator for the web-based multi-view 3D image communication system is implemented by using the IEEE 1394 digital cameras, Intel Xeon server computer and Microsoft's DirectShow programming library. In the proposed system, two-view image is initially captured by using the IEEE 1394 stereo camera and then, this data is compressed through extraction of its disparity information in the Intel Xeon server computer and transmitted to the client system, in which multi-view images are generated through the intermediate views reconstruction method and finally display on the 3D display monitor. Through some experiments it is found that the proposed system can display 8-view image having a grey level of 8 bits with a frame rate of 15 fps.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.353-358
• /
• 2022

Due to the limited field of view of the pinhole camera, there is a lack of stability and accuracy in camera pose estimation applications such as visual SLAM. Nowadays, multiple-camera setups and large field of cameras are used to solve such issues. However, a multiple-camera system increases the computation complexity of the algorithm. Therefore, in multiple camera-assisted visual simultaneous localization and mapping (vSLAM) the multi-view tracking algorithm is proposed that can be used to balance the budget of the features in tracking and local mapping. The proposed algorithm is based on PanoSLAM architecture with a panoramic camera model. To avoid the scale issue 3D LiDAR is fused with omnidirectional camera setup. The depth is directly estimated from 3D LiDAR and the remaining features are triangulated from pose information. To validate the method, we collected a dataset from the outdoor environment and performed extensive experiments. The accuracy was measured by the absolute trajectory error which shows comparable robustness in various environments.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.314-321
• /
• 2022

Depth information used in SLAM and visual odometry is essential in robotics. Depth information often obtained from sensors or learned by networks. While learning-based methods have gained popularity, they are mostly limited to RGB images. However, the limitation of RGB images occurs in visually derailed environments. Thermal cameras are in the spotlight as a way to solve these problems. Unlike RGB images, thermal images reliably perceive the environment regardless of the illumination variance but show lacking contrast and texture. This low contrast in the thermal image prohibits an algorithm from effectively learning the underlying scene details. To tackle these challenges, we propose multi-channel remapping for contrast. Our method allows a learning-based depth prediction model to have an accurate depth prediction even in low light conditions. We validate the feasibility and show that our multi-channel remapping method outperforms the existing methods both visually and quantitatively over our dataset.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.400-406
• /
• 2002

Recently, the enormous increase in the volume of remotely sensed data is being acquired by an ever-growing number of earth observation satellites. The combining of diversely sourced imagery together is an important requirement in many applications such as data fusion, city modeling and object recognition. Aerial triangulation is a procedure to reconstruct object space from imagery. However, since the different kinds of imagery have their own sensor model, characteristics, and resolution, the previous approach in aerial triangulation (or georeferencing) is performed on a sensor model separately. This study evaluated the advantages of aerial triangulation of large number of images from multi-sensors simultaneously. The incorporated multi-sensors are frame, push broom, and whisky broom cameras. The limits and problems of push-broom or whisky broom sensor models can be compensated by combined triangulation with frame imagery and vise versa. The reconstructed object space from multi-sensor triangulation is more accurate than that from a single model. Experiments conducted in this study show the more accurately reconstructed object space from multi-sensor triangulation.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.53-56
• /
• 2010

항공용 Multi-looking 카메라는 1대의 사진기 몸체에 5대의 카메라를 설치하여 동시에 1장의 연직사진과 4개의 경사사진을 획득하므로, 연직방향으로 촬영된 일반 항공사진에 비해 현장에 대한 다양한 정보를 제공한다. 그러나 3차원 공간정보 구축시 다각사진촬영시스템은 대형CCD를 사용하는것이 아니라 중형CCD를 사용하므로, 주요대상물의 전후좌우 영상을 취득하려면, 촬영시 중복도 설정을 고려하여야 하며, 특히 Sideward-looking 카메라의 경우 횡중복도 설정에 의해 특정대상물 촬영 여부를 확인할 수 있다. 이에 본 연구에서는 촬영시 횡중복도 변화에 의한 다각사진의 Sideward Footprint 및 촬영의 효율성에 대하여 분석하였다.

• 대한원격탐사학회지
• /
• 제19권3호
• /
• pp.255-261
• /
• 2003

Recently, the enormous increase in the volume of remotely sensed data is being acquired by an ever-growing number of earth observation satellites. The combining of diversely sourced imagery together is an important requirement in many applications such as data fusion, city modeling and object recognition. Aerial triangulation is a procedure to reconstruct object space from imagery. However, since the different kinds of imagery have their own sensor model, characteristics, and resolution, the previous approach in aerial triangulation (or georeferencing) is purformed on a sensor model separately. This study evaluated the advantages of aerial triangulation of large number of images from multi-sensors simultaneously. The incorporated multi-sensors are frame, push broom, and whisky broom cameras. The limits and problems of push-broom or whisky broom sensor models can be compensated by combined triangulation with other sensors The reconstructed object space from multi-sensor triangulation is more accurate than that from a single model. Experiments conducted in this study show the more accurately reconstructed object space from multi-sensor triangulation.

• 방송공학회논문지
• /
• 제12권2호
• /
• pp.128-136
• /
• 2007

사용자에게 보다 실감나는 입체감을 제공하기 위해 개발되고 있는 다시점 비디오는 두 대 이상의 카메라를 이용하여 촬영한 영상들을 기하학적으로 교정하고 공간적으로 처리하여 여러 방향의 다양한 시점 영상을 사용자에게 제공하는 3차원 영상처리 기술의 새로운 분야이다. 다시점 비디오는 사용자에게 시청 시점을 자유롭게 선택할 수 있는 기회를 주고 넓은 화면을 통한 3차원 입체감을 느낄 수 있는 장점을 가진다. 그러나 다시점 비디오는 시점 수가 증가하는 만큼 데이터 양도 증가하므로 효율적인 데이터 처리 방법이 요구된다. 최근 인접한 시점의 영상을 이용하여 중간시점의 영상을 합성하고 이를 부호화에 적용하는 방법이 연구되고 있다. 다시점 비디오 부호화 효율을 높이기 위해 제안되었던 기존의 영상보간법은 최대변위 설정과 고정된 블록을 이용한 블록정합 방법을 이용한다. 이때, 변위 종류가 다양한 영상이거나 변위차가 큰 영역에 대해서 변위 오류가 많이 발생한다. 이 논문에서는 이러한 문제점을 보완하고 개선된 화질의 중간시점의 영상을 얻기 위한 방법과 이 영상을 이용하여 부호화에 적용하는 방법을 제안한다. 제안한 영상보간법은 변위의 검색 범위를 초기에 설정하지 않고 블록 단위부터 화소 단위까지 변위를 측정하여 중간영상을 합성한다. 또한 이렇게 합성한 영상을 부호화 과정에서 참조 영상으로 추가하여 부호화한다. 이 논문에서 제안한 방법을 이용한 결과, 기존의 영상 보간법보다 약 $1{\sim}4dB$ 정도 개선된 화질의 중간시점 영상을 얻었고, 이 영상들을 이용하여 제안한 부호화 방법으로 부호화한 결과 참조 모델에 비해 최대 0.5 dB의 부호화 효율이 개선됨을 확인했다.