• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• 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.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1428-1436
• /
• 2012

This paper presents the delta image composition methods using Depth-Image-Based Rendering (DIBR) for 3D stereoscopic broadcasting for the low bandwidth mobile DMB broadcasting system. With DIBR, a left and depth images are transmitted to a mobile device, which restores the right view, whose quality may be poor. This paper describes delta image composition methods for the restoration while minimizing the amount of the transmitted data.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.11
• /
• pp.853-858
• /
• 2006

In this paper, we propose a practical method for hardware-accelerated rendering of the depth image-based representation(DIBR) of 3D graphic object using graphic processing unit(GPU). The proposed method overcomes the drawbacks of the conventional rendering, i.e. it is slow since it is hardly assisted by graphics hardware and surface lighting is static. Utilizing the new features of modem GPU and programmable shader support, we develop an efficient hardware-accelerating rendering algorithm of depth image-based 3D object. Surface rendering in response of varying illumination is performed inside the vertex shader while adaptive point splatting is performed inside the fragment shader. Experimental results show that the rendering speed increases considerably compared with the software-based rendering and the conventional OpenGL-based rendering method.

• Journal of the Korean GEO-environmental Society
• /
• v.20 no.2
• /
• pp.49-58
• /
• 2019

A study on the analysis of underground ground condition using 3D-GPR exploration was carried out in this paper. The test bed was constructed similar to the field, and the detection analysis was carried out for each depth of cavity and underground burial. Through this, we were able to know the permittivity of the ground by inversion, and we could confirm the depth of detection for the joint by accurate calculation. We confirmed the signal waveforms in the cavity under the road through 3D-GPR exploration, analyzed more quantitatively in subjective and empirical analysis. The subsidence and depth of the subsurface settlement can be observed through 3D-GPR survey, and ground condition change after the ground reinforcement can be confirmed through the exploration section.

• Journal of Engineering Education Research
• /
• v.19 no.6
• /
• pp.49-56
• /
• 2016

The Human Robot Interface (HRI) based on 3D depth sensor on the docent robot is developed and the localization algorithm based on extended Kalman Filter (EKFLA) are proposed through the capstone design by graduate students in this paper. In addition to this, the performance of the proposed EKFLA is also analyzed. The developed HRI system consists of the route generation and localization algorithm, the user behavior pattern awareness algorithm, the map data generation and building algorithm, the obstacle detection and avoidance algorithm on the robot control modules that control the entire behaviors of the robot. It is confirmed that the improvement ratio of the localization error in EKFLA on the scenarios 1-3 is increased compared with the localization algorithm based on Kalman Filter (KFLA) as 21.96%, 25.81% and 15.03%, respectively.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.941-942
• /
• 2006

A depth measurement system to recognize 3D shape of objects using single camera, line laser and a rotating mirror has been investigated. The camera and the light source are fixed, facing the rotating mirror. The laser light is reflected by the mirror and projected to the scene objects whose locations are to be determined. The camera detects the laser light location on object surfaces through the same mirror. The scan over the area to be measured is done by mirror rotation. The Segmentation process of object recognition is performed using the depth data of restored 3D data. The Object recognition domain can be reduced by separating area of interest objects from complex background.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.230-239
• /
• 2003

This paper presents face recognition algorithm using projection vector reflecting local feature for the area in contour lines. The outline shape of a face has many difficulties to distinguish people because human has similar face shape. For 3 dimensional(3D) face images include depth information, we can extract different face shapes from the nose tip using some depth values for a face image. In this thesis deals with 3D face image, because the extraction of contour lines from 2 dimensional face images is hard work. After finding nose tip, we extract two areas in the contour lilies from some depth values from 3D face image which is obtained by 3D laser scanner. And we propose a method of projection vector to localize the characteristics of image and reduce the number of index data in database. Euclidean distance is used to compare of similarity between two images. Proposed algorithm can be made recognition rate of 94.3% for face shapes using depth information.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.6
• /
• pp.1431-1438
• /
• 1995

In this paper, we present a multiple-view stereo matching method in case of moving in the direction of optical axis with stereo camera. Also we analyze the obtainable depth precision to show that multiple-view stereo increases the virtual baseline with single-view stereo. This method decides candidate points for correspondence in each image pair and then search for the correct combinations of correspondences among them using the geometrical consistency they must satisfy. Adantages of this method are capability in increasing the accuracy in matching by using the multiple stereo images and less computation due to local processing. This method computes 3-D depth by averaging the depth obtained in each multiple-view stereo. We show that the resulting depth has more precision than depth obtainable by each independent stereo when the position of image feature is uncertain due to image noise. This paper first defines a multipleview stereo agorithm in case of moving in the direction of optical axis with stereo camera and analyze the obtainable precision of computed depth. Then we represent the effect of removing the incorrect matching candidate and precision enhancement with experimental result.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1371-1374
• /
• 2009

According to depth cues of an image, the optical engine of the solid volumetric true 3D display can project a sequence of slices of a 2D image to corresponding display at a set of liquid shutters (LC) locating at different depth. A single DLP optical engine developed for a solid volumetric true 3D display consists of a lamp, reflector, color wheel, hollow integrator, relays, DMD, and projection lens. The simulation results show that the optical engine designed for single DLP volumetric true 3D display satisfies the requirements.