• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.537-542
• /
• 2011

A mirror neuron is a neuron fires both when an animal acts and when the animal observes the same action performed by another. We propose a method of 3D reconstruction for occluded object motion tracking like Mirror Neuron System to fire in hidden condition. For modeling system that intention recognition through fire effect like Mirror Neuron System, we calculate depth information using stereo image from a stereo camera and reconstruct three dimension data. Movement direction of object is estimated by optical flow with three-dimensional image data created by three dimension reconstruction. For three dimension reconstruction that enables tracing occluded part, first, picture data was get by stereo camera. Result of optical flow is made be robust to noise by the kalman filter estimation algorithm. Image data is saved as history from reconstructed three dimension image through motion tracking of object. When whole or some part of object is disappeared form stereo camera by other objects, it is restored to bring image date form history of saved past image and track motion of object.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.70-78
• /
• 2021

Estimating 3D information from a single image is one of the essential problems in numerous applications. Since a 2D image inherently might originate from an infinite number of different 3D scenes, thus 3D reconstruction from a single image is notoriously challenging. This challenge has been overcame by the advent of recent deep convolutional neural networks (CNNs), by modeling the mapping function between 2D image and 3D information. However, to train such deep CNNs, a massive training data is demanded, but such data is difficult to achieve or even impossible to build. Recent trends thus aim to present deep learning techniques that can be trained in a weakly-supervised manner, with a meta-data without relying on the ground-truth depth data. In this article, we introduce recent developments of weakly-supervised deep learning technique, especially categorized as scene 3D reconstruction and object 3D reconstruction, and discuss limitations and further directions.

• Archives of Plastic Surgery
• /
• v.47 no.1
• /
• pp.33-41
• /
• 2020

Background Closed-suction drains are widely used in expander-based breast reconstruction. These drains are typically removed using a volume-based criterion. The drainage volume affects the hospital stay length and the recovery time. However, few studies have analyzed the factors that influence drainage volume after expander-based breast reconstruction. Methods We retrospectively analyzed data regarding daily drainage from patients who underwent expander-based breast reconstruction between April 2014 and January 2018 (159 patients, 176 expanders). Patient and operative factors were analyzed regarding their influence on total drainage volume and drain placement duration using univariate and multivariate analyses and analysis of variance. Results The mean total drainage volume was 1,210.77±611.44 mL. Univariate analysis showed correlations between total drainage volume and age (B=19.825, P<0.001), body weight (B=17.758, P<0.001), body mass index (B=51.817, P<0.001), and specimen weight (B=1.590, P<0.001). Diabetes history (P<0.001), expander type (P<0.001), and the surgical instrument used (P<0.001) also strongly influenced total drainage. The acellular dermal matrix type used did not affect total drainage (P=0.626). In the multivariate analysis, age (B=11.907, P=0.004), specimen weight (B=0.927, P<0.001), and expander type (B=593.728, P<0.001) were significant predictors of total drainage. Conclusions Our findings suggest that the total drainage and the duration of drain placement needed after expander-based breast reconstruction can be predicted using preoperative and intraoperative data. Patient age, specimen weight, and expander type are important predictors of drainage volume. Older patients, heavier specimens, and use of the Mentor rather than the Allergan expander corresponded to a greater total drainage volume and a longer duration of drain placement.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• Journal of Korea Spatial Information System Society
• /
• v.7 no.3 s.15
• /
• pp.119-130
• /
• 2005

A spatial data warehouse is a system that stores geographical information as a subject oriented, integrated, time-variant, non-volatile collection for efficiently supporting decision. This system consists of a builder and a spatial data warehouse server. A spatial data warehouse server suspends user services, stores transferred data in the data repository and constructs index using stored data for short response time. Existing methods that construct index are bulk-insertion and index transfer methods. The Bulk-insertion method has high clustering cost for constructing index and searching cost. The Index transfer method has improper for the index reconstruction method of a spatial data warehouse where periodic source data are inserted. In this paper, the efficient index reconstruction method using a partial index in a spatial data warehouse is proposed. This method is an efficient reconstruction method that transfers a partial index and stores a partial index with expecting physical location. This method clusters a spatial data making it suitable to construct index and change treated clusters to a partial index and transfers pages that store a partial index. A spatial data warehouse server reserves sequent physical space of a disk and stores a partial index in the reserved space. Through inserting a partial index into constructed index in a spatial data warehouse server, searching, splitting, remodifing costs are reduced to the minimum.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.101-108
• /
• 2010

In this paper, we proposed a new lazy classifier with fuzzy k-nearest neighbors approach and feature selection which is based on reconstruction error. Reconstruction error is the performance index for locally linear reconstruction. When a new query point is given, fuzzy k-nearest neighbors approach defines the local area where the local classifier is available and assigns the weighting values to the data patterns which are involved within the local area. After defining the local area and assigning the weighting value, the feature selection is carried out to reduce the dimension of the feature space. When some features are selected in terms of the reconstruction error, the local classifier which is a sort of polynomial is developed using weighted least square estimation. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods such as standard neural networks, support vector machine, linear discriminant analysis, and C4.5 trees.

• Archives of Plastic Surgery
• /
• v.34 no.4
• /
• pp.448-454
• /
• 2007

Purpose: The objective of this study was to evaluate the outcomes of using the free flap in the reconstruction of maxillary defects. Methods: 27 consecutive cases of maxillary reconstruction with free flap were reviewed. All clinical data were analyzed, including ideal selection of flap, time of reconstruction, recurrence of cancer, postoperative complications, flap design, and follow-up results. The main operative functional items, including speech, oral diet, mastication, eye globe position and function, respiration, and aesthetic results were evaluated. Results: Among the 24 patients who underwent maxillary reconstruction with the free flap, 14 patients underwent immediate reconstruction after maxillary cancer ablation, and 10 patients underwent delayed reconstruction. There occurred 1 flap loss. Recurrences of the cancer after the reconstruction happened in 2 cases. Postoperative complications were 3 cases of gravitational ptosis of the flap, 2 cases of the nasal obstruction, and 1 case of fistula formation. Out of 27 free flaps, there were 15 latissimus dorsi myocutaneous flaps, 5 radial forearm, 4 rectus abdominis myocutaneous flaps, 1 scapular flap, 2 fibula osteocutaneous flap, respectively. Flaps were designed such as 1 lobe in 9 cases, 2 lobes in 9 cases, and 3 lobes in 5 cases. Among the 14 patients who had intraoral defect or who had palatal resection surgery, 2 patients complained the inaccuracy of the pronunciation due to the ptosis of the flap. It was corrected by the reconstruction of the maxillary buttress and hung the sling to the upper direction. All of the 14 patients were able to take unrestricted diets. In 6 patients who had reconstruction of inferior orbital wall with rib bone graft, they preserved normal vision. Aesthetically, most of the patients were satisfied with the result. Conclusion: LD free flap is suggested in uni-maxilla defect as the 1st choice, and fibular osteocutaneous flap and calvarial bone graft to cover the larger defect in bi-maxilla defect.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.42-47
• /
• 2005

In this papcr, we address the 3D reconstruction of the indoor circumstance using what the data is extracted by a pall of image from Stereo Camera. Generally sucaking, there arc three methods to extract 3-Dimensional data using IR sensor, Laser sensor and Stereo camera sensor. The best is stereo camera sensor which can show a high performance at a reasonable price. We used 'Window Correlation Matching Method' to extract 3-Dimensional data in stereo image. We proposed new Method to reduce error data, said 'Histogram Weighted Hough Transform'. Owing to this mettled, we reduced error data in each stereo image. So reconstruction is well done. 3-Dimensional Reconstruction is accomplished by using the DirectX that is well known as 3D-Game development tool. We show that the stereo camera can be not only used to extract 3-dimensional data but also applied to reconstruct the 3-Dimensional circumstance. And we try to reduce the error data using various method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.179-187
• /
• 2014

As an Accident data recorder (ADR) is a system to record a vehicle's status and dynamics information on the before and after of accident, Traffic accident investigation agencies and parts developers have a lot of interest to analyze an accident objectively and develop automotive safety devices by using real accident data, This study is to analyze an accident objectively and scientifically on the basis of traffic accident reconstruction with the use of output data of an event data recorder. This study is conducted double lane change test six times and slalom test one time as a field driving test and simulation. Based on the vehicle speed, the longitudinal and transverse acceleration, steering angle, driving path, and other kinds of information obtained from the field driving test, this study performed a simulation with PC-Crash program of reenacting and analyzing a traffic accident. The simulation was performed twice in the acceleration-steering angle input method and in the acceleration-driving path input method. By comparing the result of the field driving test with the results of the two simulations, we drew an analysis method with the optimal path reconstruction.

• Journal of Biomedical Engineering Research
• /
• v.35 no.5
• /
• pp.132-141
• /
• 2014

In an ordinary CT scan, a large number of projections with full field-of-view (FFOV) are necessary to reconstruct high resolution images. However, excessive x-ray dosage is a great concern in FFOV scan. Region-of-interest (ROI) CT or sparse-view CT is considered to be a solution to reduce x-ray dosage in CT scanning, but it suffers from bright-band artifacts or streak artifacts giving contrast anomaly in the reconstructed image. In this study, we propose an image reconstruction method to eliminate the bright-band artifacts and the streak artifacts simultaneously. In addition to the ROI scan for the interior projection data with relatively high sampling rate in the view direction, we get sparse-view exterior projection data with much lower sampling rate. Then, we reconstruct images by solving a constrained total variation (TV) minimization problem for the interior projection data, which is assisted by the exterior projection data in the compressed sensing (CS) framework. For the interior image reconstruction assisted by the exterior projection data, we implemented the proposed method which enforces dual data fidelity terms and a TV term. The proposed method has effectively suppressed the bright-band artifacts around the ROI boundary and the streak artifacts in the ROI image. We expect the proposed method can be used for low-dose CT scans based on limited x-ray exposure to a small ROI in the human body.