• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.11-20
• /
• 2016

This paper introduces an effective method for generating 3D stereoscopic images that gives immersive 3D experiences to viewers using mobile-based binocular HMDs. Most of previous AR systems with monocular cameras have a common limitation that the same real-world images are provided to the viewer's eyes without parallax. In this paper, based on the assumption that viewers focus on the marker in the scenario of marker based AR, we recovery the binocular disparity about a camera image and a virtual object using the pose information of the marker. The basic idea is to generate the binocular disparity for real-world images and a virtual object, where the images are placed on the 2D plane in 3D defined by the pose information of the marker. For non-marker areas in the images, we apply blur effects to reduce the visual discomfort by decreasing their sharpness. Our user studies show that the proposed method for 3D stereoscopic image provides high depth feeling to viewers compared to the previous binocular AR systems. The results show that our system provides high depth feelings, high sense of reality, and visual comfort, compared to the previous binocular AR systems.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.2
• /
• pp.121-128
• /
• 2013

There have been various research efforts for pedestrian recognition in embedded imaging systems. However, many suffer from their heavy computational complexities. SVM classification method has been widely used for pedestrian recognition. The reduction of candidate region is crucial for low-complexity scheme. In this paper, We propose a real time HOG based pedestrian detection system on GPU which images are captured by a pair of cameras. To speed up humans on road detection, the proposed method reduces a number of detection windows with disparity-search and near-search algorithm and uses the GPU and the NVIDIA CUDA framework. This method can be achieved speedups of 20% or more compared to the recent GPU implementations. The effectiveness of our algorithm is demonstrated in terms of the processing time and the detection performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.3
• /
• pp.236-241
• /
• 2008

This paper presents a method to recognize the plane regions for movement of walking robots. When the autonomous agencies using stereo camera or laser scanning sensor is under unknown 3D environment, the mobile agency has to detect the plane regions to decide the moving direction and perform the given tasks. In this paper, we propose a very fast method for plane detection using normal vector of a triangle by 3 vertices defined on a small circular region. To reduce the effect of noises and outliers, the triangle rotates with respect to the center position of the circular region and generates a series of triangles with different normal vectors based on different three points on the boundary of the circular region. The vectors for several triangles are normalized and then median direction of the normal vectors is used to test the planarity of the circular region. The method is very fast and we prove the performance of algorithm for real range data obtained from a stereo camera system.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.6
• /
• pp.565-574
• /
• 2015

Recently, a medium-level representation named "Stixel" has been extensively researched in stereo vision-based environmental perception. Obstacle detection using Stixel representation consists of three steps: static Stixel generation, dynamic Stixel generation, and Stixel segmentation. This paper focuses on the Stixel segmentation step and has two contributions. One is that it shows that Stixel segmentation performance can be enhanced by utilizing both image domain and real world domain features. The other is that it suggests that parameters used for Stixel segmentation can be effectively tuned based on genetic algorithm. The proposed method was quantitatively evaluated and the result showed that the proposed method increased Stixel segmentation accuracy compared with the previous method.

• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.104-109
• /
• 2010

The lighting reflection is a common problem in image analysis and causes the many difficulties to extract distinct features in related fields. Furthermore, the problem grows in the rainy night. In this paper, we aim to remove light reflection effects and reconstruct a road surface without lighting reflections in order to extract distinct features. The proposed method utilizes a 3D analysis based on a multiple geometry using captured images, with which we can combine each reflected areas; that is, we can remove lighting reflection effects and reconstruct the surface. At first, the regions of lighting sources and reflected surfaces are extracted by local maxima based on vertically projected intensity-histograms. After that, a fundamental matrix and homography matrix among multiple images are calculated by corresponding points in each image. Finally, we combine each surface by selecting minimum value among multiple images and replace it on a target image. The proposed method can reduces lighting reflection effects and the property on the surface is not lost. While the experimental results with collected data shows plausible performance comparing to the speed, reflection-overlapping areas which can not be reconstructed remain in the result. In order to solve this problem, a new reflection model needs to be constructed.

• Journal of Broadcast Engineering
• /
• v.11 no.4 s.33
• /
• pp.495-506
• /
• 2006

In this paper, we propose a self-calibration of a multi-camera system using factorization techniques for realistic contents generation. The traditional self-calibration algorithms for multi-camera systems have been focused on stereo(-rig) camera systems or multiple camera systems with a fixed configuration. Thus, it is required to exploit them in 3D reconstruction with a mobile multi-camera system and another general applications. For those reasons, we suggest the robust algorithm for general structured multi-camera systems including the algorithm for a plane-structured multi-camera system. In our paper, we explain the theoretical background and practical usages based on a projective factorization and the proposed affine factorization. We show experimental results with simulated data and real images as well. The proposed algorithm can be used for a 3D reconstruction and a mobile Augmented Reality.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.162-170
• /
• 2013

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.102-109
• /
• 2014

A particle system is used for modeling the physical phenomenon. There are many traditional ways for simulation modeling which can be well suited for application including the landscapes of branches, clouds, waves, fog, rain, snow and fireworks in the three-dimensional space. In this paper, we present a new fireworks modeling technique for modeling 3D firework based on Firework Particle Tracking (FPT) using the particle system. Our method can track and recognize the launched and exploded particle of fireworks, and extracts relatively accurate 3D positions of the particles using 3D depth values. It can realize 3D simulation by using tracking information such as position, speed, color and life time of the firework particle. We exploit Region of Interest (ROI) for fast particle extraction and the prevention of false particle extraction caused by noise. Moreover, Kalman filter is used to enhance the robustness in launch step. We propose a new fireworks particle tracking method for the efficient tracking of particles by considering maximum moving range and moving direction of particles, and shall show that the 3D speeds of particles can be obtained by finding the rotation angles of fireworks. Also, we carry out the performance evaluation of particle tracking: tracking speed and accuracy for tracking, classification, rotation angle respectively with respect to four types of fireworks: sphere, circle, chrysanthemum and heart.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4C
• /
• pp.253-261
• /
• 2005

In this paper, we propose an efficient block-based disparity estimation algorithm fur multiple view image coding in EE2 and EE3 in 3DAV. The proposed method emphasizes on visual quality improvement to satisfy the requirements for multiple view generation. Therefore, we perform an adaptive disparity estimation that constructs variable blocks by considering given image features. Examining neighboring features around desired block search range is set up to decrease complexity and additional information than only using quad-tree coding through applying binary-tree and quad-tree coding by taking into account stereo image feature having big disparity. The experimental results show that the proposed method improves PSNR about 1 to 2dB compared to existing other methods and decreases computational complexity up to maximum 68 percentages than FBMA.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.1-8
• /
• 2008

In this paper, an algorithm to compensate the inter-view mismatch in the multi-view video according to the different characteristics of cameras is presented. Interview mismatches make it difficult to merge the multi-view images and decrease the coding performance. So, a preprocessing operation to compensate the mismatches is requisite in the multi-view video coding. It is shown that the mismatch in the outputs of multi-view cameras with different electro-optical transfer functions can be approximated with a linear model of a gain and an offset. In addition, a new algorithm for estimating and compensating the inter-view mismatch based on the detection of the overlapped region is presented. Experimental results using various rectified stereo images show that the proposed method compensates inter-view mismatches more accurately compared to the conventional approach.