• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.192-198
• /
• 2020

The 3D point cloud is a key technology of object detection for virtual reality and augmented reality. In order to apply various areas of object detection, it is necessary to obtain 3D information and even color information more easily. In general, to generate a 3D point cloud, it is acquired using an expensive scanner device. However, 3D and characteristic information such as RGB and depth can be easily obtained in a mobile device. GNN (Graph Neural Network) can be used for object detection based on these characteristics. In this paper, we have generated RGB and RGBD by detecting basic information and characteristic information from the KITTI dataset, which is often used in 3D point cloud object detection. We have generated RGB-GNN with i-GNN, which is the most widely used LiDAR characteristic information, and color information characteristics that can be obtained from mobile devices. We compared and analyzed object detection accuracy using RGBD-GNN, which characterizes color and depth information.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.10
• /
• pp.958-964
• /
• 2015

In this paper, an object recognition method based on the depth information from the RGB-D camera, Xtion, is proposed for an indoor mobile robot. First, the RANdom SAmple Consensus (RANSAC) algorithm is applied to the point cloud obtained from the RGB-D camera to detect and remove the floor points. Next, the removed point cloud is classified by the k-means clustering method as each object's point cloud, and the normal vector of each point is obtained by using the k-d tree search. The obtained normal vectors are classified by the trained multi-layer perceptron as 18 classes and used as features for object recognition. To distinguish an object from another object, the similarity between them is measured by using Levenshtein distance. To verify the effectiveness and feasibility of the proposed object recognition method, the experiments are carried out with several similar boxes.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.4
• /
• pp.106-117
• /
• 2016

Recently, solar power plants have spread widely as part of the transition to greater environmental protection and renewable energy. Therefore, regular solar plant inspection is necessary to efficiently manage solar-light modules. This study implemented a test that can detect solar-light module faults using an UAV based thermal infrared camera and GIS spatial analysis. First, images were taken using fixed UAV and an RGB camera, then orthomosaic images were created using Pix4D SW. We constructed solar-light module layers from the orthomosaic images and inputted the module layer code. Rubber covers were installed in the solar-light module to detect solar-light module faults. The mean temperature of each solar-light module can be calculated using the Zonalmean function based on temperature information from the UAV thermal camera and solar-light module layer. Finally, locations of solar-light modules of more than $37^{\circ}C$ and those with rubber covers can be extracted automatically using GIS spatial analysis and analyzed specifically using the solar-light module's identifying code.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.256-257
• /
• 2022

In this paper, we introduce a method of extracting three-dimensional feature points through the movement of a single mobile device. Using a monocular camera, a 2D image is acquired according to the camera movement and a baseline is estimated. Perform stereo matching based on feature points. A feature point and a descriptor are acquired, and the feature point is matched. Using the matched feature points, the disparity is calculated and a depth value is generated. The 3D feature point is updated according to the camera movement. Finally, the feature point is reset at the time of scene change by using scene change detection. Through the above process, an average of 73.5% of additional storage space can be secured in the key point database. By applying the algorithm proposed to the depth ground truth value of the TUM Dataset and the RGB image, it was confirmed that the\re was an average distance difference of 26.88mm compared with the 3D feature point result.

• The Journal of the Korea Contents Association
• /
• v.21 no.2
• /
• pp.130-139
• /
• 2021

In this study, size of the fruit of Japanese apricot (plum) was estimated through a plum recognition and size estimation program using 3D images in order to control the Eurytoma maslovskii that causes the most damage to plum in a timely manner. In 2018, night shooting was carried out using a Kinect 2.0 Camera. For night shooting in 2019, a RealSense Depth Camera D415 was used. Based on the acquired images, a plum recognition and estimation program consisting of four stages of image preprocessing, sizeable plum extraction, RGB and depth image matching and plum size estimation was implemented using MATLAB R2018a. The results obtained by running the program on 10 images produced an average plum recognition error rate of 61.9%, an average plum recognition error rate of 0.5% and an average size measurement error rate of 3.6%. The continued development of these plum recognition and size estimation programs is expected to enable accurate fruit size monitoring in the future and the development of timely control systems for Eurytoma maslovskii.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.607-616
• /
• 2014

Face recognition is a big challenge in surveillance system since different rotation angles of the face make the difficulty to recognize the face of the same person. This paper proposes a novel method to recognize face with different head poses by using 3D information of the face. Firstly, head pose estimation (estimation of different head pose angles) is accomplished by the POSIT algorithm. Then, 3D face image data is constructed by using head pose estimation. After that, 2D image and the constructed 3D face matching is performed. Face verification is accomplished by using commercial face recognition SDK. Performance evaluation of the proposed method indicates that the error range of head pose estimation is below 10 degree and the matching rate is about 95%.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.716-725
• /
• 2007

In this paper we describe a motion tracking algorithm for 3D human animation using stereo vision system. This allows us to extract the motion data of the end effectors of human body by following the movement through segmentation process in HIS or RGB color model, and then blob analysis is used to detect robust shape. When two hands or two foots are crossed at any position and become disjointed, an adaptive algorithm is presented to recognize whether it is left or right one. And the real motion is the 3-D coordinate motion. A mono image data is a data of 2D coordinate. This data doesn't acquire distance from a camera. By stereo vision like human vision, we can acquire a data of 3D motion such as left, right motion from bottom and distance of objects from camera. This requests a depth value including x axis and y axis coordinate in mono image for transforming 3D coordinate. This depth value(z axis) is calculated by disparity of stereo vision by using only end-effectors of images. The position of the inner joints is calculated and 3D character can be visualized using inverse kinematics.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2004.08a
• /
• pp.808-811
• /
• 2004

A full-color AMOLED display with an RGBW color filter pattern has been fabricated. Displays with this format require about $^1/_2$ the power of analogous RGB displays. RGBW and RGB 2.16inch diagonal displays with average power consumptions of 180 mW and 340 mW, respectively, are demonstrated for a set of standard digital still camera images at a luminance of 100 cd/$m^2$. In both cases, a white-emitting AMOLED is used as the light source. The higher efficiency of the RGBW format results because a large fraction of a typical image can be represented as white, and the white sub-pixel in an RGBW AMOLED display is highly efficient because of the absence of any color filter. RGBW and RGB AMOLED displays have the same color gamut and, aside from the power consumption difference, are indistinguishable.