• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.2_2
• /
• pp.249-254
• /
• 2023

The use of robots in automated factories requires accurate bin-picking to ensure that objects are correctly identified and selected. In the case of atypical objects with multiple reflections from their surfaces, this is a challenging task. In this paper, we developed a random 3D bin picking system by integrating the low-cost vision system with the robotics system. The vision system identifies the position and posture of candidate parts, then the robot system validates if one of the candidate parts is pickable; if a part is identified as pickable, then the robot will pick up this part and place it accurately in the right location.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.163-170
• /
• 2007

In autonomous navigation of a mobile vehicle or a mobile robot, localization calculated from recognizing its environment is most important factor. Generally, we can determine position and pose of a camera equipped mobile vehicle or mobile robot using INS and GPS but, in this case, we must use enough known ground landmark for accurate localization. hi contrast with homography method to calculate position and pose of a camera by only using the relation of two dimensional feature point between two frames, in this paper, we propose a method to calculate the position and the pose of a camera using relation between the location to predict through perspective transform of 3D feature points obtained by overlaying 3D model with previous frame using GPS and INS input and the location of corresponding feature point calculated using KLT tracking method in current frame. For the purpose of the performance evaluation, we use wireless-controlled vehicle mounted CCD camera, GPS and INS, and performed the test to calculate the location and the rotation angle of the camera with the video sequence stream obtained at 15Hz frame rate.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.95-101
• /
• 2023

Colmap is one of the innovative artificial intelligence technologies, highly effective as a tool in 3D reconstruction tasks. Moreover, it excels at constructing intricate 3D models by utilizing images and corresponding metadata. Colmap generates 3D models by merging 2D images, camera position data, depth information, and so on. Through this, it achieves detailed and precise 3D reconstructions, inclusive of objects from the real world. Additionally, Colmap provides rapid processing by leveraging GPUs, allowing for efficient operation even within large data sets. In this paper, we have presented a method of collecting 2D images of traditional Korean towers and reconstructing them into 3D models using Colmap. This study applied this technology in the restoration process of traditional stone towers in South Korea. As a result, we confirmed the potential applicability of Colmap in the field of cultural heritage restoration.

• Geophysics and Geophysical Exploration
• /
• v.7 no.2
• /
• pp.136-147
• /
• 2004

In this study, the characteristics of magnetotelluric (MT) responses due to a three-dimensional (3-D) body are analyzed with 3-D numerical modeling. The first model for the analysis consists of a single isolated conductive body embedded in a resistive homogeneous half-space. The second model has an additional conductive overburden while the other conditions remain the same as the first one. The analysis of apparent resistivities shows well that the 3-D effects are dominant over some frequency range for the first model. Two mechanisms, current channeling and induction, for secondary electric fields due to the conductive body are analyzed at various frequencies: at high frequencies induction is more dominant than channeling, while at low frequencies channeling is more dominant than induction. Tippers have a strong relation to the position of anomalous body and the real and imaginary parts of induction vector also indicate the position of anomalous body. off-line conductive anomaly sometimes causes severe problem in 2-D interpretation. In such case, induction vector analysis can give information on the existence and location of the anomalous body. Each parameter of the second model shows similar responses as those of the first model. The only difference is that the magnitude of all parameters is decreased and that the domain showing the 3-D effects becomes narrower. As shown in this study, the analysis of 3-D effects provides a useful and effective means to understand the 3-D subsurface structure and to interpret MT survey data.

• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.797-803
• /
• 2014

In this paper, 3D face recognition system is designed by using polynomial based on RBFNNs. In case of 2D face recognition, the recognition performance reduced by the external environmental factors such as illumination and facial pose. In order to compensate for these shortcomings of 2D face recognition, 3D face recognition. In the preprocessing part, according to the change of each position angle the obtained 3D face image shapes are changed into front image shapes through pose compensation. the depth data of face image shape by using Multiple Point Signature is extracted. Overall face depth information is obtained by using two or more reference points. The direct use of the extracted data an high-dimensional data leads to the deterioration of learning speed as well as recognition performance. We exploit principle component analysis(PCA) algorithm to conduct the dimension reduction of high-dimensional data. Parameter optimization is carried out with the aid of PSO for effective training and recognition. The proposed pattern classifier is experimented with and evaluated by using dataset obtained in IC & CI Lab.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2007.04a
• /
• pp.106-109
• /
• 2007

The spray plume characteristics of liquid water jet injected into subsonic cross-flow at 42 m/s were experimentally investigated. Nozzle has a 1.0 m diameter and L/D=5. Droplet sizes, velocities, volume flux were measured at each downstream area of the injector exit using phase Doppler particle anemometry. Measuring probe position is moved with 3-way transversing machine. Experimental results indicate that SMD is varied from 75 to $120{\mu}m$ distribution and it is uncertain layer structure. SMD peaks at the top of the spray plume. This phenomenon is related to the momentum exchange between column waves and cross-flow stream. Droplet vector velocities were varied from 11.5 to 33 m/s. A higher-velocity region can be identified in down edge region at Z/D : 40, 70 and 100. Lower-velocity region were observed on bottom position of the spray plume. Volume flux is a criterion to the droplet concentration. All volume flux distribution has a same structure that continuously decreases from the center region to the edge of the plume. Z/D : 20 is spatially less concentrated than in Z/D : 100.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.941-951
• /
• 2018

Utilization and demand of UAV (unmanned aerial vehicle) for the generation of 3D city model are increasing. In this study, we performed an experiment to adjustment position/orientation of UAV with incomplete attitude information and to extract point cloud data. In order to correct the attitude of the UAV, the rotation angle was calculated by using the continuous position information of UAV movements. Based on this, the corrected position/orientation information was obtained by applying IBA (Incremental Bundle Adjustment) based on photogrammetry. Each pair was transformed into an epipolar image, and the MDR (Multi-Dimensional Relaxation) technique was applied to obtain high precision DSM. Each extracted pair is aggregated and output in the form of a single point cloud or DSM. Using the DJI inspire1 and Phantom4 images, we can confirm that the point cloud can be extracted which expresses the railing of the building clearly. In the future, research will be conducted on improving the matching performance and establishing sensor models of oblique images. After that, we will continue the image processing technology for the generation of the 3D city model through the study of the extraction of 3D cloud It should be developed.

• Journal of Advanced Navigation Technology
• /
• v.20 no.3
• /
• pp.218-225
• /
• 2016

Null steering and beam steering are known well as anti-jamming methods in GPS anti-jamming system. Null steering gets a noise attenuation effect for the direction of jamming and beam steering earns additional gain synthesis for the direction of satellite signals. According to the research in the article for signal processing, it expresses that the N array antenna is effective for N-1 number of jamming signal by math public interest, however, the two algorithms analysis is not unknown for the operating condition of the realistic vehicle. In this paper, we modeled anti-jamming system using 4 and 7 array antenna and showed the two algorithms performance (PM, LCMV) when considering the number of antenna array, jammers and vehicle position (horizontal, vertical). In result, we showed that the case of vertical position of the vehicle which has large tilt angle for the relative position of satellites and jammers, has about 10 dB gain more in comparison with one of vertical position in spite of same JSR condition.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.2
• /
• pp.27-38
• /
• 2015

In this study, the 3D position coordinates were calculated for the targets using DLT and self-calibration bundle adjustment with additional parameters in close-range photogrammetry. And then, the accuracy of the results were analysed. For this purpose, the results of camera calibration and orientation parameters were calculated for each images by performing reference surveying using total station though the composition of experimental conditions attached numerous targets. To analyze the accuracy, 3D position coordinates were calculated for targets that has been identically selected and compared with the reference coordinates obtained from a total station. For the image coordinate measurement of the stereo images, we performed the ellipse fitting procedure for measuring the center point of the circular target. And then, the results were utilized for the image coordinate for targets. As a results from experiments, position coordinates calculated by the stereo images-based photogrammetry have resulted out the deviation of less than an average 4mm within the maximum error range of less than about 1cm. From this result, it is expected that the stereo images-based photogrammetry would be used to field of various close-range photogrammetry required for precise accuracy.