• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.625-630
• /
• 2009

Researches of image-based 3D reconstruction have recently produced a number of good results, but they assumed that the accurate foreground to be reconstructed is already extracted from each input image. This paper proposes a novel approach to extract more accurate foregrounds by iteratively performing foreground extraction and 3D reconstruction in a manner similar to an EM algorithm on regions segmented in an initial stage, called segments. Here, the segments should preserve foreground boundaries to compensate for the boundary errors generated by visual hull, simple 3D reconstruction to minimize the computational time, and should also be composed of the small number of sets to minimize the user input. Therefore, we utilize image segmentation using the graph-cuts method, which minimizes energy function composed of data and smoothness terms, and the two methods are iteratively performed until the energy function is optimized. In the experiments, more accurate results of the foreground, especially in boundaries, were obtained, although the proposed method used a simple 3D reconstruction method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.1
• /
• pp.38-48
• /
• 2020

In order to inspect the existing or newly constructed ship's hull, a professional diver directly inspects the ship's bottom of the water. However, since it is a work done by people, there are many dangers such as human casualties and crashes. To solve this problem, it is necessary to develop underwater drones for ship inspection for visual inspection. The technology applied to underwater drones, the use and manufacturing process of each component, and the method of manufacture such as firmware development were described, and the difference was compared by measuring the drone's own driving ability and driving ability using crawler under water, and the location tracking device test confirmed the error from the actual location. It is estimated that the use of underwater drones produced through this research will prevent human casualties and achieve economic effects and stability.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.6
• /
• pp.744-750
• /
• 2015

In this paper, development of mobile robot for the inspection of hull surface was mentioned. In the sea, it is difficult to proceed with the visual inspection of hull side and thus mobile robot for checking the status could be run with strap-on its surface. To do this, permanent magnet module to generate magnetic force between hull surface and mobile robot, and structure to minimize variance of the force under curvature circumstance were considered on the design. Based on the design, mobile robot with four NdFeB, four driving wheels and image aquisition module was applied. Load experiment to check the adhesive force, slip test during stop state and driving test to measure driving speed were executed. From the experiments 13 Kgf adhesive force was obtained and slip was not happened until 8 Kgf load on the inclined plate. Driving speed of mobile robot was measured at 0.82 m/s corresponding to 6.5 ampere. We confirmed the effectiveness of developed mobile robot by experiments to check its characteristics.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.361-364
• /
• 2004

This paper describes an automatic 3D models generation algorithm based on 2D silhouette images, using X-ray camera without camera parameters. The algorithm takes a multi steps process approach. First, a series of 2D silhouette images is captured from different directions of object and then converted to binary images. An octree data structure is constructed for voxel-based representation of object. An estimate 3D volume of object can be reconstructed by intersecting voxels and the 2D silhouettes. The marching cube algorithm is applied to get triangle mesh representing of the obtained 3D model for rendering.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.249-257
• /
• 2023

This paper discusses the increasing need for autonomous delivery robots due to the current growth in the delivery market, rising delivery fees, high costs of hiring delivery personnel, and the need for contactless services. Additionally, the cost of hardware and complex software systems required to build and operate autonomous delivery robots is high. To provide a low-cost alternative to this, this paper proposes a autonomous delivery robot platform using a low-cost sensor combination of 2D LIDAR, depth camera and tracking camera to replace the existing expensive 3D LIDAR. The proposed robot was developed using the RTAB-Map SLAM open source package for 2D mapping and overcomes the limitations of low-cost sensors by using the convex hull algorithm. The paper details the hardware and software configuration of the robot and presents the results of driving experiments. The proposed platform has significant potential for various industries, including the delivery and other industries.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.836-850
• /
• 2009

Human posture recognition has attracted tremendous attention in ubiquitous environment, performing arts and robot control so that, recently, many researchers in pattern recognition and computer vision are working to make efficient posture recognition system. However the most of existing studies is very sensitive to human variations such as the rotation or the translation of body. This is why the feature, which is extracted from the feature extraction part as the first step of general posture recognition system, is influenced by these variations. To alleviate these human variations and improve the posture recognition result, this paper presents 3D Star Skeleton and Principle Component Analysis (PCA) based feature extraction methods in the multi-view environment. The proposed system use the 8 projection maps, a kind of depth map, as an input data. And the projection maps are extracted from the visual hull generation process. Though these data, the system constructs 3D Star Skeleton and extracts the rotation invariant feature using PCA. In experimental result, we extract the feature from the 3D Star Skeleton and recognize the human posture using the feature. Finally we prove that the proposed method is robust to human variations.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.789-799
• /
• 2008

For the communication between human and computer in an interactive computing environment, the gesture recognition has been studied vigorously. The algorithms which use the 2D features for the feature extraction and the feature comparison are faster, but there are some environmental limitations for the accurate recognition. The algorithms which use the 2.5D features provide higher accuracy than 2D features, but these are influenced by rotation of objects. And the algorithms which use the 3D features are slow for the recognition, because these algorithms need the 3d object reconstruction as the preprocessing for the feature extraction. In this paper, we propose a method to extract the 3D features combined with the 3D object reconstruction in real-time. This method generates three kinds of 3D projection maps using the modified GPU-based visual hull generation algorithm. This process only executes data generation parts only for the gesture recognition and calculates the Hu-moment which is corresponding to each projection map. In the section of experimental results, we compare the computational time of the proposed method with the previous methods. And the result shows that the proposed method can apply to real time gesture recognition environment.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.150-161
• /
• 2013

This paper presents a new system which produces high resolution 3D contents by capturing multiview images of an object using multiple cameras, and estimating geometric and texture information of the object from the captured images. Even though a variety of multiview image-based 3D reconstruction systems have been proposed, it was difficult to generate high resolution 3D contents because multiview image-based 3D reconstruction requires a large amount of memory and computation. In order to reduce computational complexity and memory size for 3D reconstruction, the proposed system predetermines the regions in input images where an object can exist to extract object boundaries fast. And for fast computation of a visual hull, the system represents silhouettes and 3D-2D projection/back-projection relations by chain codes and 1D homographies, respectively. The geometric data of the reconstructed object is compactly represented by a 3D segment-based data format which is called DoCube, and the 3D object is finally reconstructed after 3D mesh generation and texture mapping are performed. Experimental results show that the proposed system produces 3D object contents of $800{\times}800{\times}800$ resolution with a rate of 2.2 seconds per frame.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.45 no.1
• /
• pp.46-55
• /
• 2009

To compare and evaluate the suitability and comfort levels of the environment on board a stern trawl training ship, KAYA(GT: 1737 tons, Pukyong National University), with the international standardization guide ISO 6954:2000(E), measurements of the hull vibration on accommodation areas and working areas of the training ship from July 8 to July 10, 2008 were completed upon KAYA's linear sea route. The vibrations along the z-axis were measured with the use of a 3-axis vibration level meter, which included a marine vibration card. Results show accelerations of the vibrations on the passenger's accommodation area to be 42.0-115.8(average: 78.0, standard deviation(SD): 21.0) mm/$s^2$, which is largely below the permissible upper limit, but 75 % of the observation points exceeded the permissible lower limit of 71.5 mm/$s^2$, indicating a comfortable environment. The accelerations of the vibration in a frequency of 10-24Hz lowering the visual performance were measured at 2.5-12.0(average: 7.6, SD: 3.1) mm/$s^2$. The crew s accommodation area experienced vibration accelerations of 42.9-82.3(average: 93.1, SD: 53.1) mm/$s^2$, which is generally below the permissible upper limit of 214.0 mm/$s^2$, and 62.5% of the observation points did not exceed the permissible lower limit of 107.0 mm/$s^2$, denoting a level of comfort. The acceleration of the vibration in a frequency of 10-24Hz were 4.7-28.3(average: 12.4, SD: 8.8) mm/$s^2$. On the crew s working area the accelerations were measured at 86.9-153.9(average 119.3, SD 18.0) mm/$s^2$. These values were generally below the permissible upper limit of 286.0 mm/$s^2$ and only 12.5% of the observation points did not exceed the permissible lower limit of 143.0 mm/$s^2$, the level at which a high level of comfort is maintained. The accelerations in frequency of 10-24Hz and 30Hz were 9.1-29.8 (average 13.8, SD= 4.5) mm/$s^2$ and 8.9-13.7 (average 11.8, SD 2.1) mm/$s^2$, respectively. In conclusion the boarding environment of the training ship was good in general although an improvement of the vibration condition partially needed on the crew s accommodation area near the engine room.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.1031-1036
• /
• 2007

최근 가상현실 기술의 주요 연구 동향으로 몰입감을 증가시키는 실감공간 구현구술이 주목 받고 있다. 실감공간 기술이란 서로 다른 공간에 떨어져 있는 사용자가 같은 공간에 있는 효과를 구현하는 기술이다. 본 논문에서는 특히 상호간의 주변 환경을 일치시키는 기술에 중점을 두고, 실시간으로 두 공간의 조명정보를 일치시키는 기술로서 2가지 핵심 내용을 소개한다. 첫째는 비주얼 헐 데이터를 기반으로 고속으로 노말벡터를 추출하는 방법이고, 둘째는 사용자 주변 조명 환경 정보를 반영하는 라이팅 방법이다. 본 논문에서 수행한 첫번째 방법은 비주얼 헐 데이터의 depth존재영역에서 노말맵을 계산하도록 하고, 노말맵을 계산할 때 주변 폴리곤들 기하학적 변화가 심할수록 노말맵 계산에 사용하는 주변 벡터의 선태을 늘리거나 줄이는 방식으로, 불필요한 계산량을 감소시켰다. 본 논문에서 수행한 두번째 방법에서는 주변 조명 정보에서 빛의 세기와 라이팅을 반영할 객체의 반사율의 특성을 고려하여 라이팅에 사용할 광원을 선택적으로 반영하여 불필요한 연산량을 감소시켰다. 종래의 영상기반 라이팅 기술이 사전에 촬영된 영상을 사용하거나 정지영상에 적용되는 연구를 한 반면에 본 논문은 실시간에서 라이팅을 구현하기 위한 시도로서 고속 라이팅 연산 기법을 제시하고 있다. 본 연구의 결과를 이용하면 영상기반 라이팅 연구의 실제적이고도 폭넓은 적용이 가능할 것으로 사료되며 고화질의 콘텐츠 양산에도 기여할 것으로 사료된다.