• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.273-280
• /
• 2013

This paper presents novel OCS-LBP (Oriented Center Symmetric Local Binary Patterns) based on orientation of pixel gradient and image retrieval system based on BoF (Bag-of-Feature) and random forest classifier. Feature vectors extracted from training data are clustered into code book and each feature is transformed new BoF feature using code book. BoF features are applied to random forest for training and random forest having N classes is constructed by combining several decision trees. For testing, the same OCS-LBP feature is extracted from a query image and BoF is applied to trained random forest classifier. In contrast to conventional retrieval system, query image selects similar K-nearest neighbor (K-NN) classes after random forest is performed. Then, Top K similar images are retrieved from database images that are only labeled K-NN classes. Compared with other retrieval algorithms, the proposed method shows both fast processing time and improved retrieval performance.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.501-510
• /
• 2001

Generally, it is essential to estimate exact disparity for the 3D modeling from stereo images. Because existing methods calculate disparities from a whole image, they require too much cimputational time and bring about the mismatching problem. In this article, using the characteristic that the disparity vectors in stereo images are distributed not equally in a whole image but only exist about the background and obhect, we do a wavelet transformation on stereo images and estimate coarse disparity fields from the reduced lowpass field using area-based method at first-step. From these coarse disparity vectors, we generate disparity histogram and then separate object from background area using it. Afterwards, we restore only object area to the original image and estimate dense and accurate disparity by our two-step pixel-based method which does not use pixel brightness but use second gradient. We also extract feature points from the separated object area and estimate depth information by applying disparity vectors and camera parameters. Finally, we generate 3D model using both feature points and their z coordinates. By using our proposed, we can considerably reduce the computation time and estimate the precise disparity through the additional pixel-based method using LOG filter. Furthermore, our proposed foreground/background method can solve the mismatching problem of existing Delaunay triangulation and generate accurate 3D model.

• Radiation Oncology Journal
• /
• v.11 no.2
• /
• pp.431-437
• /
• 1993

An important problem in radiosurgery is the utilization of the proper beam parameters, to which dose shape is sensitive. Streotactic radiosurgery techniques for a linear accelerator typically, use circular radiation fields with multiple arcs to produce an spherical radiation distribution. Target volumes are irregular in shape for a certain case, and spherical distributions can irradiate normal tissues to high dose as well as the target region. The current improvement to dose distribution utilizes treating multiple isocenters or weighting various arcs to change treatment volume shape. in this paper another promising study relies upon dynamically shaping the treatment beam to fit the beam's eye view of the target. This conformal irradiation technique was evaluated by means of visual three dimensional dose distribution, dose volume histograms to the target volume and surrounding normal brain. It is shown that using even less arcs than multiple isocenter irradiation technique, the conformal therapy yields comparable dose gradients and superior homogeneity of dose within the target volume.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.323-330
• /
• 2023

The development of an analysis model that reflects the microstructure characteristics of polyvinyl alcohol (PVA) fiber-reinforced cementitious composites, which have a highly complex microstructure, enables synergy between efficient material design and real experiments. PVA fiber orientations are an important factor that influences the mechanical behavior of PVA fiber-reinforced cementitious composites. Owing to the difficulty in distinguishing the gray level value obtained from micro-CT images of PVA fibers from adjacent phases, fiber segmentation is time-consuming work. In this study, a micro-CT test with a voxel size of 0.65 ㎛³ was performed to investigate the three-dimensional distribution of fibers. To segment the fibers and generate training data, histogram, morphology, and gradient-based phase-segmentation methods were used. A U-net model was proposed to segment fibers from micro-CT images of PVA fiber-reinforced cementitious composites. Data augmentation was applied to increase the accuracy of the training, using a total of 1024 images as training data. The performance of the model was evaluated using accuracy, precision, recall, and F1 score. The trained model achieved a high fiber segmentation performance and efficiency, and the approach can be applied to other specimens as well.

• Progress in Medical Physics
• /
• v.21 no.2
• /
• pp.165-173
• /
• 2010

In this paper, we evaluated the performance of 3D CRT, IMRT and three kind of RA plannings to investigate the clinical effect of RA with liver cancer case. The patient undergoing liver cancer of small volume and somewhat constant motion were selected. We performed 3D CRT, IMRT and RA plannings such as 2RA, limited triple arcs (3RA) and 3MRA with Eclipse version 8.6.15. The same dose volume objectives were defined for only CTV, PTV and body except heart, liver and partial body in IMRT and RA plannings. The steepness of dose gradient around tumor was determined by the Normal Tissue Objective function with the same parameters in place of respective definitions of dose volume objectives for the normal organs. The approach between the defined dose constraints and the practical DVH of CTV, PTV and Body was the best in 3MRA and the worst in IMRT. The DVHs were almost the same among RAs. Plans were evaluated using Conformity Index (CI), Homogeneity Index (HI) and Quality of coverage (QoC) by RTOG after prescription with dose level surrounding 98% of PTV in the respective plans. As a result, 3MRA planning showed the better favorable indices than that of the others and achieved the lowest MUs. In this study, RA planning is a technique that is possible to obtain the faster and better dose distribution than 3D CRT or IMRT techniques. Our result suggest that 3MRA planning is able to reduce the MUs further, keeping a similar or better targer dose homogeneity, conformity and sparing normal tissue than 2RA or 3RA.