• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.135-142
• /
• 2003

Robust extraction of 3D object's features, shape and global motion information from 2D image sequence is described. The object's 21 feature points on the pyramid type synthetic object are extracted automatically using color transform technique. The extracted features are used to recover the 3D shape and global motion of the object using stereo paraperspective camera model and sequential SVD(Singuiar Value Decomposition) factorization method. An inherent error of depth recovery due to the paraperspective camera model was removed by using the stereo image analysis. A 30 synthetic object with 21 features reflecting various position was designed and tested to show the performance of proposed algorithm by comparing the recovered shape and motion data with the measured values.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.238-245
• /
• 2024

In this paper, we propose a framework for improving the performance of semantic segmentation of agricultural multispectral image using feature fusion techniques. Most of the semantic segmentation models being studied in the field of smart farms are trained on RGB images and focus on increasing the depth and complexity of the model to improve performance. In this study, we go beyond the conventional approach and optimize and design a model with multispectral and attention mechanisms. The proposed method fuses features from multiple channels collected from a UAV along with a single RGB image to increase feature extraction performance and recognize complementary features to increase the learning effect. We study the model structure to focus on feature fusion and compare its performance with other models by experimenting with favorable channels and combinations for crop images. The experimental results show that the model combining RGB and NDVI performs better than combinations with other channels.

• Journal of Korean Dental Science
• /
• v.7 no.2
• /
• pp.66-79
• /
• 2014

Purpose: To analyze the amount and pattern of tooth movement and the changes in arch dimension of mandibular dentition after orthodontic treatment using a new three-dimensional (3D)-indirect superimposition method. Materials and Methods: The samples consisted of fifteen adult patients with class I bialveolar protrusion and minimal anterior crowding, treated by extraction of four first premolars with conventional sliding mechanics. After superimposition of 3D-virtual maxillary models before and after treatment using best-fit method, 3D-virtual mandibular model at each stage was placed into a common coordinate of superimposition using 3D-bite information, which resulted in 3D-indirect superimposition for mandibular dentition. The changes in mandibular dental and arch dimensional variables were measured with Rapidform 2006 (INUS Technology). Paired t-test was used for statistical analysis. Result: The anterior teeth moved backward, displaced laterally, and inclined lingually. The posterior teeth showed statistically significant contraction toward midsagittal plane. The amounts of backward movement of anterior teeth and forward movement of posterior teeth showed a ratio of 6 : 1. Although the inter-canine width increased slightly (0.8 mm, P<0.05), the inter-second premolar, inter-first molar, and inter-second molar widths decreased significantly with similar amounts (2.2 mm, P<0.05; 2.3 mm, P<0.01; 2.3 mm, P<0.001). The molar depth decreased (6.7 mm, P<0.001) but canine depth did not change. Conclusion: A new 3D-indirect superimposition of the mandibular dentitions using best-fit method and 3D-bite information can present a guideline for virtual treatment planning in terms of tooth position and arch dimension.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.2
• /
• pp.126-131
• /
• 2017

In this paper, we propose a method to extract meaningful motion among various kinds of hand gestures on giving commands to robots using hand gestures. On giving a command to the robot, the hand gestures of people can be divided into a preparation one, a main one, and a finishing one. The main motion is a meaningful one for transmitting a command to the robot in this process, and the other operation is a meaningless auxiliary operation to do the main motion. Therefore, it is necessary to extract only the main motion from the continuous hand gestures. In addition, people can move their hands unconsciously. These actions must also be judged by the robot with meaningless ones. In this study, we extract human skeleton data from a depth image obtained by using a Kinect v2 sensor and extract location data of hands data from them. By using the Kalman filter, we track the location of the hand and distinguish whether hand motion is meaningful or meaningless to recognize the hand gesture by using the hidden markov model.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.108-118
• /
• 2013

Recently the 3D modeling techniques were developed rapidly due to rapid development of computer vision, computer graphics with the excellent performance of hardware. With the advent of a variety of 3D contents, 3D modeling technology becomes more in demand and it's quality is increased. 3D face models can be applied widely to such contents with high usability. In this paper, a 3D face modeling is attempted from a given single 2D frontal face image. To achieve the goal, we thereafter the feature points using AAM are extracted from the input frontal face image. With the extracted feature points we deform the 3D general model by 2-pass mesh warping, and also the depth extraction based on intensity values is attempted to. Throughout those processes, a universal 3D face modeling method with less expense and less restrictions to application environment was implemented and it's validity was shown through experiments.

• Ocean Systems Engineering
• /
• v.4 no.4
• /
• pp.263-278
• /
• 2014

The spudcan requires the suitable design considering the soil, platform, and environmental conditions. Its shape needs to be designed to secure sufficient reaction of soil so that it can prevent overturning accidents. Its shape also has to minimize the installation and extraction time. Even in the same soil condition, the reaction of soil may be different depending on the shape of spud can, mainly the slope of top and bottom plates. Therefore, in this study, the relation between the slope of plates and the reaction of soil with and without water jetting is analyzed to better understand their interactions and correlations. For the investigation, a wind turbine installation jack-up rig (WTIJ) is selected as the target platform and the Gulf of Mexico is considered as the target site. A multi layered (sand overlying two clays) soil profile is applied as the assumed soil condition and the soil-structure interaction (SSI) analysis is performed by using ANSYS to analyze the effect of the slope change of the bottom plate and water jetting on the reaction of soil. This kind of investigation and simulation is needed to develop optimal and smart spudcan with water-jetting control in the future.

• Journal of Information Processing Systems
• /
• v.9 no.2
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.589-592
• /
• 2005

Gravity characteristics and Moho undulations are investigated in the Korean peninsula by using satellite gravity data. According to the development of satellite geodesy, gravity potential models which have high accuracy and resolution were released. Using the EIGEN-CGOIC model based on low orbit satellite data such as CHAMP and GRACE, geoid and gravity anomaly were calculated by spherical harmonic analysis. The study area is located at $123^{\circ}\sim132^{\circ}E, 33^{\circ}\sim43^{\circ}$N including Korea. Free-air anomalies, which show the effect of terrain, have the values between $-37\sim724 mgal. After Bouguer correction, the range of simple Bouguer anomalies is $-221\sim246$ mgal. Complete Bouguer anomalies after terrain correction increase from continent to marine. This phenomenon is related rise of Moho discontinuity. The cut-frequency for extraction of Moho undulation was determined by power spectrum analysis, and then 3D inversion modeling was implemented. The mean, maximum, minimum, and standard deviation of Moho depth undulation are -26, -36, -8, and 4.9 krn, respectively.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.5
• /
• pp.517-522
• /
• 2010

The riffle and pool play an important role for composing river front, but very little information was used for river restoration considering flood control. In this paper extensive field investigation was carried out to estimate hydraulic processes in the pool. Furthermore diurnal stratification model was developed and applied to assess flow change in pool. The physical mechanism of water flow including diurnal processes was well simulated, the results show that diurnal variation of water flow in the pool about 2 m depth is governed by the level of mixing due to density flow. These effort will be useful to guide field data collection work and to understand primary production.

• Transactions on Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.17-20
• /
• 2024

This paper presents a novel lightweight object detection model tailored for low-powered edge devices, addressing the limitations of traditional resource-intensive computer vision models. Our proposed detector, inspired by the Single Shot Detector (SSD), employs a compact yet robust network design. Crucially, it integrates an 'enhancer block' that significantly boosts its efficiency in detecting smaller objects. The model comprises two primary components: the Light_Block for efficient feature extraction using Depth-wise and Pointwise Convolution layers, and the Enhancer_Block for enhanced detection of tiny objects. Trained from scratch on the Udacity Annotated Dataset with image dimensions of 300x480, our model eschews the need for pre-trained classification weights. Weighing only 5.5MB with approximately 0.43M parameters, our detector achieved a mean average precision (mAP) of 27.7% and processed at 140 FPS, outperforming conventional models in both precision and efficiency. This research underscores the potential of lightweight designs in advancing object detection for edge devices without compromising accuracy.