• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권8호
• /
• pp.309-314
• /
• 2014

물체의 360도 방향에서 다수의 RGB-D(RGB-Depth) 카메라를 이용하여 깊이영상을 획득하고 3차원 모델을 생성하기 위해서는 RGB-D 카메라 간의 3차원 변환관계를 구하여야 한다. 본 논문에서는 구형 물체를 이용하여 4대의 RGB-D 카메라 사이의 변환관계를 간편하게 구할 수 있는 시점보정(view calibration) 방법을 제안한다. 기존의 시점보정 방법들은 평면 형태의 체크보드나 코드화된 패턴을 가진 3차원 물체를 주로 사용함으로써 패턴의 특징이나 코드를 추출하고 정합하는 작업에 상당한 시간이 걸린다. 본 논문에서는 구형 물체의 깊이영상과 사진영상을 동시에 사용하여 간편하게 시점을 보정할 수 있는 방법을 제안한다. 우선 하나의 구를 모델링 공간에서 연속적으로 움직이는 동안 모든 RGB-D 카메라에서 구의 깊이영상과 사진영상을 동시에 획득한다. 다음으로 각 RGB-D 카메라의 좌표계에서 획득한 구의 3차원 중심좌표를 월드좌표계에서 일치되도록 각 카메라의 외부변수를 보정한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.162-163
• /
• 2012

본 논문에서는 Kinect를 이용하여 획득된 영상으로 집적 영상 기반의 3D 디스플레이를 수행하기 위한 요소 영상 변환 방법을 제안한다. Kinect로 얻어지는 RGB영상과 깊이영상은 직접적으로 공간 3D영상으로 사용될 수 없기 때문에 집적영상 디스플레이용 요소 영상으로 변환이 필요하다. 이를 위해서 본 논문에서 RGB 영상과 깊이 영상으로부터 생성된 깊이 분할 영상에 대해서 기하광학적 매핑기법으로 요소 영상을 제작하였다. 제안한 시스템의 효용성을 보이기 위하여, Kinect에서 주로 사용되는 인체인식 기반으로 실험을 수행하고 그 결과를 보고한다.

• Computers and Concrete
• /
• 제34권5호
• /
• pp.535-546
• /
• 2024

Slump is an important index for concrete fluidity, which has a direct guiding effect on construction. In recent years, using RGB images for evaluating slump has been confirmed by scholars. Based on previous studies, this paper investigates the superiority of RGB-D image data over RGB image data in predicting slump of concrete and proposes three RGB-D fusion models: The early-stage-fusion model performs feature fusion in the data input stage, while the fully-connected-layer-fusion model performs feature fusion in the classification layer and the middle-stage-fusion model performs feature fusion after each residual block. In the classification of slump 120 mm, 150 mm and 200 mm, the Precision, Recall and F1-score are used to evaluate the model's ability to classify a single class, and the Accuracy, Macro-F1, Kappa and MCC are used to evaluate the model's performance. The experimental results showed that compared with the model using only RGB images, the fusion model achieve better performance, indicating that RGB-D image data can better evaluate concrete slump.

• 한국정보통신학회논문지
• /
• 제25권5호
• /
• pp.637-644
• /
• 2021

일반적으로, 컴퓨터 비전, 로보틱스, 증강현실 분야에서 3차원 공간 및 3차원 객체 검출 및 인식기술의 중요성이 대두되고 있다. 특히, 마이크로소프트사의 키넥트(Microsoft Kinect) 방식을 사용하는 영상 센서를 통하여 RGB 영상과 깊이 영상을 실시간 획득하는 것이 가능해짐으로 인하여 객체 검출, 추적 및 인식 연구에 많은 변화를 가져오고 있다. 본 논문에서는 다시점 카메라 시스템 상에서의 깊이 기반(RGB-Depth) 카메라를 통해 획득된 영상을 처리하여 3D 복원 영상의 품질을 향상하는 방법을 제안한다. 본 논문에서는 컬러 영상으로부터 획득한 마스크 적용을 통해 객체 바깥쪽 잡음을 제거하는 방법과 객체 안쪽의 픽셀 간 깊이 정보 차이를 구하는 필터링 연산을 결합하여 적용하는 방법을 제시하였다. 각 실험 결과를 통해 제시한 방법이 효과적으로 잡음을 제거하여 3D 복원 영상의 품질을 향상할 수 있음을 확인하였다.

• 도시과학
• /
• 제6권2호
• /
• pp.17-27
• /
• 2017

최근, 하천의 수질오염 및 악취발생으로 민원이 증가하여 하천환경개선에 큰 관심이 모아지고 있다. 본 연구의 목적은 하수 유입부에 대해 무인항공기(UAV)를 활용하여 RGB 및 적외 열 영상을 획득하고 하천제방 정비 계획 및 하천 오염 현황의 모니터링을 위한 응용성을 검토하였다. 특히, 하천 인근 공장에서 배출되는 폐수를 적외 열 영상으로 검출하여 폐수의 전파를 모니터링하였다. 또한 하천 제방 정비대상 지역과 인근지역에 대한 RGB영상을 SfM(Structure from Motion)기반 영상 해석을 통해 고정밀 3차원 모형을 제작하고 정확성을 검토하였다. 연구결과, UAV영상을 활용, 폐수유입에 따른 하천의 온도변화를 감지하여 수질오염의 유입부 및 전파 현상을 모니터링 할 수 있었다. 또한 고정밀 3차원 모델(수치지형도, 정사영상)을 제작, 정확성을 검토하고 하천의 제방정비를 위한 정밀 3차원 정보 및 식생 피복정보를 도출할 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제20권4호
• /
• pp.629-639
• /
• 2017

Interpolation based information hiding methods are widely used to get information security. Conventional interpolation methods use the neighboring pixel value and simple calculation like average to embed secret bit stream into the image. But these information hiding methods are not appropriate to color images like military images because the characteristics of military images are not considered and these methods are restricted in grayscale images. In this paper, the new information hiding method based on interpolation using RGB pixel values of color image is proposed and the effectiveness is analyzed through experiments.

• Journal of Web Engineering
• /
• 제21권3호
• /
• pp.729-750
• /
• 2022

In general, the importance of 6DoF (degree of freedom) 3D (dimension) volumetric contents technology is emerging in 5G (generation) telepresence service, Web-based (WebGL) graphics, computer vision, robotics, and next-generation augmented reality. Since it is possible to acquire RGB images and depth images in real-time through depth sensors that use various depth acquisition methods such as time of flight (ToF) and lidar, many changes have been made in object detection, tracking, and recognition research. In this paper, we propose a method to improve the quality of 3D models for 5G telepresence by processing images acquired through depth and RGB cameras on a multi-view camera system. In this paper, the quality is improved in two major ways. The first concerns the shape of the 3D model. A method of removing noise outside the object by applying a mask obtained from a color image and a combined filtering operation to obtain the difference in depth information between pixels inside the object were proposed. Second, we propose an illumination compensation method for images acquired through a multi-view camera system for photo-realistic 3D model generation. It is assumed that the three-dimensional volumetric shooting is done indoors, and the location and intensity of illumination according to time are constant. Since the multi-view camera uses a total of 8 pairs and converges toward the center of space, the intensity and angle of light incident on each camera are different even if the illumination is constant. Therefore, all cameras take a color correction chart and use a color optimization function to obtain a color conversion matrix that defines the relationship between the eight acquired images. Using this, the image input from all cameras is corrected based on the color correction chart. It was confirmed that the quality of the 3D model could be improved by effectively removing noise due to the proposed method when acquiring images of a 3D volumetric object using eight cameras. It has been experimentally proven that the color difference between images is reduced.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• Advances in robotics research
• /
• 제2권2호
• /
• pp.129-140
• /
• 2018

With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1595-1613
• /
• 2017

The IR camera and laser-based IR projector provide an effective solution for real-time collection of moving targets in RGB-D videos. Different from the traditional RGB videos, the captured depth videos are not affected by the illumination variation. In this paper, we propose a novel feature extraction framework to describe human activities based on the above optical video capturing method, namely spatial-temporal texture features for 3D human activity recognition. Spatial-temporal texture feature with depth information is insensitive to illumination and occlusions, and efficient for fine-motion description. The framework of our proposed algorithm begins with video acquisition based on laser projection, video preprocessing with visual background extraction and obtains spatial-temporal key images. Then, the texture features encoded from key images are used to generate discriminative features for human activity information. The experimental results based on the different databases and practical scenarios demonstrate the effectiveness of our proposed algorithm for the large-scale data sets.