• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.728-741
• /
• 2015

Stereo vision has become an important technical issue in the field of 3D imaging, machine vision, robotics, image analysis, and so on. The depth map extraction from stereo video is a key technology of stereoscopic 3D video requiring stereo correspondence algorithms. This is the matching process of the similarity measure for each disparity value, followed by an aggregation and optimization step. Since it requires a lot of computational power, there are significant speed-performance advantages when exploiting parallel processing available on processors. In this situation, multi-core CPU may allow many parallel programming technologies to be realized in users computing devices. This paper proposes parallel implementations for calculating disparity map using a shared memory programming and exploiting the streaming SIMD extension technology. By doing so, we can take advantage both of the hardware and software features of multi-core processor. For the performance evaluation, we implemented a parallel SAD algorithm with OpenMP and SSE2. Their processing speeds are compared with non parallel version on stereoscopic streaming video. The experimental results show that both technologies have a significant effect on the performance and achieve great improvements on processing speed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1D
• /
• pp.89-94
• /
• 2012

The RFM (Rational Function Model), as an alternative to physical sensor models has been widely used for photogrammetric processing of high resolution optical satellite imagery. However, the application of RF modeling to the SAR (Synthetic Aperture Radar) is very limited. In this paper, stereo radargrammetric processing of TerraSAR-X stereo pairs with RFM is implemented and analyzed. The investigation has shown that the accuracy of TerraSAR-X DSM is similar to that of the commercial S/W product. Finally, it is demonstrated that RFM is effective and feasible in the application to the radargrammetric SAR image processing.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.683-686
• /
• 2005

This study addresses a photogrammetric approach to generate Mars topographic products from mapping data of Mars Global Surveyor (MGS). High-resolution stereo images and laser altimetry data collected from the MGS mission are combined and processed to produce Digital Elevation Models (DEM) and orthoimages. First, altimeter data is registered to high resolution images and considerable registration offset (around 325 m) is discovered on high resolution stereo images. Altimetry data, exterior orientation elements of the camera and conjugate points are used for bundle adjustment to solve this mis-registration and detennine the ground coordinates. The mis-registration of altimetry data are effectively eliminated after the bundle adjustment. Using the adjusted exterior orientation the ground coordinates of conjugate points are detennined. A sufficient number of corresponding points collected through image matching and their precise 3-D ground coordinates are used to generate DEM and orthoimages. A posteriori standard deviations of ground points after bundle adjustment indicate the accuracy of OEM generated in this study. This paper addresses the photogrammetric procedure: the registration of altimetry data to stereo pair images, the bundle adjustment and the evaluation, and the generation of OEM and orthoimages.

• Journal of the HCI Society of Korea
• /
• v.4 no.2
• /
• pp.9-16
• /
• 2009

3D stereo display systems gain more interests recently. Multiple-view autostereoscopic display system enables observers to watch stereo image from multiple viewpoints not wearing specific devices such as shutter glasses or HMD. Therefore, the Multiple-view autostereoscopic display is being spotlighted in the field of virtual reality, mobile, 3D TV and so on. However, one of the critical disadvantages of the system is that observer can enjoy the system only in a small designated area where the system is designed to work properly. This research provides an effective way of GPU based rendering technique to present seamless 3D stereo experiences from an arbitrary observer's view position.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.5
• /
• pp.241-246
• /
• 2015

Although many different methods have been used to solve stereo correspondent problems, the deviation of accuracy is too big. Among those many methods, the one that uses segmentation information of input image has received high attention in academic field since it is very close to vision recognition. In this thesis, the existing method of acquiring a single value by using the segment information and initial disparity value was viewed in NP-hard problem to propose a new method. In order to verify the validity of the proposed method, well-known data were used for experiment and the resulted data was analyzed. Although there were some disadvantages in the time aspect, it showed somewhat useful results in the accuracy aspect.

• Journal of Korea Multimedia Society
• /
• v.20 no.12
• /
• pp.1865-1873
• /
• 2017

The feature-based visual SLAM requires 3D positions for the extracted feature points to perform 3D-2D motion estimation. LiDAR can provide reliable and accurate 3D position information with low computational burden, while stereo camera has the problem of the impossibility of stereo matching in simple texture image region, the inaccuracy in depth value due to error contained in intrinsic and extrinsic camera parameter, and the limited number of depth value restricted by permissible stereo disparity. However, the sparsity of LiDAR data may increase the inaccuracy of motion estimation and can even lead to the result of motion estimation failure. Therefore, in this paper, we propose three interpolation methods which can be applied to interpolate sparse LiDAR data. Simulation results obtained by applying these three methods to a visual odometry algorithm demonstrates that the selective bilinear interpolation shows better performance in the view point of computation speed and accuracy.

• Journal of Broadcast Engineering
• /
• v.11 no.4 s.33
• /
• pp.533-540
• /
• 2006

In this study we propose to use a facial motion capture technique to track facial motions and expressions effectively by using the stereo vision module, which has two CMOS IMAGE SENSORS. In the proposed tracking algorithm, a center point tracking technique and correlation tracking technique, based on neural networks, were used. Experimental results show that the two tracking techniques using stereo vision motion capture are able to track general face expressions at a 95.6% and 99.6% success rate, for 15 frames and 30 frames, respectively. However, the tracking success rates(82.7%,99.1%) of the center point tracking technique was far higher than those(78.7%,92.7%) of the correlation tracking technique, when lips trembled.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.60-65
• /
• 2010

This paper describes the results of 2D mapping, feature detection and matching to create the surrounding environment in the mounted stereo camera on Mobile robot. Extract method of image's feature in real-time processing for quick operation uses the edge detection and Sum of Absolute Difference(SAD), stereo matching technique can be obtained through the correlation coefficient. To estimate the location of a mobile robot using ZigBee beacon and encoders mounted on the robot is estimated by Kalman filter. In addition, the merged gyro scope to measure compass is possible to generate map during mobile robot is moving. The Simultaneous Localization and Mapping (SLAM) of mobile robot technology with an intelligent robot can be applied efficiently in human life would be based.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.3
• /
• pp.230-237
• /
• 2004

Lane Sensing techniques based on vision sensors are regarded promising because they require little infrastructure on the highway except clear lane markers. However, they require more intelligent processing algorithms in vehicles to generate the previewed roadway from the vision images. In this paper, a lane sensing algorithm using vision sensors is developed to improve the sensing robustness. The parallel stereo-camera is utilized to regenerate the 3-dimensional road geometry. The lane geometry models are derived such that their parameters represent the road curvature, lateral offset and heading angle, respectively. The parameters of the lane geometry models are estimated by the Kalman filter and utilized to reconstruct the lane geometry in the global coordinate. The inverse perspective mapping from the image plane to the global coordinate considers roll and pitch motions of a vehicle so that the mapping error is minimized during acceleration, braking or steering. The proposed sensing system has been built and implemented on a 1/10-scale model car.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.580-583
• /
• 2007

Various matching methods have been introduced by investigators to improve digital elevation model (DEM) accuracy of satellite imagery. This study proposed an area-based matching method according to land cover property using correlation coefficient of pixel brightness value between the two images for DEM generation from IKONOS stereo imagery. For this, matching line (where "matching line" implies straight line that is approximated to complex nonlinear epipolar geometry) is established by exterior orientation parameters to minimize search area. The matching is carried out based on this line. Land cover classes are divided off into water, urban land, forest and agricultural land. Matching size is selected using a correlation-coefficient image in the four areas. The selected sizes are $81{\times}81$ pixels window, $21{\times}21$ pixels window, $119{\times}119$ pixels window and $51{\times}51$ pixels window in the water area, urban land, forest land and agricultural land, respectively. And hence, DEM is generated from IKONOS stereo imagery using the selected matching sizes and land cover map on the four types.