• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.173-180
• /
• 2011

This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.10
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.3
• /
• pp.172-179
• /
• 2015

Because of the development of computers and high-technology applications, all devices that we use have become more intelligent. In recent years, security and surveillance systems have become more complicated as well. Before new technologies included video surveillance systems, security cameras were used only for recording events as they occurred, and a human had to analyze the recorded data. Nowadays, computers are used for video analytics, and video surveillance systems have become more autonomous and automated. The types of security cameras have also changed, and the market offers different kinds of cameras with integrated software. Even though there is a variety of hardware, their capabilities leave a lot to be desired. Therefore, this drawback is trying to compensate by dint of computer program solutions. Image processing is a very important part of video surveillance and security systems. Capturing an image exactly as it appears in the real world is difficult if not impossible. There is always noise to deal with. This is caused by the graininess of the emulsion, low resolution of the camera sensors, motion blur caused by movements and drag, focus problems, depth-of-field issues, or the imperfect nature of the camera lens. This paper reviews image processing, pattern recognition, and image digitization techniques, which will be useful in security services, to analyze bio-images, for image restoration, and for object classification.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.3
• /
• pp.250-255
• /
• 2012

Face recognition has wide applications in security and surveillance systems as well as in robot vision and machine interfaces. Conventional challenges in face recognition include pose, illumination, and expression, and face recognition at a distance involves additional challenges because long-distance images are often degraded due to poor focusing and motion blurring. This study investigates the effectiveness of applying photon-counting linear discriminant analysis (Pc-LDA) to face recognition in harsh environments. A related technique, Fisher linear discriminant analysis, has been found to be optimal, but it often suffers from the singularity problem because the number of available training images is generally much smaller than the number of pixels. Pc-LDA, on the other hand, realizes the Fisher criterion in high-dimensional space without any dimensionality reduction. Therefore, it provides more invariant solutions to image recognition under distortion and degradation. Two decision rules are employed: one is based on Euclidean distance; the other, on normalized correlation. In the experiments, the asymptotic equivalence of the photon-counting method to the Fisher method is verified with simulated data. Degraded facial images are employed to demonstrate the robustness of the photon-counting classifier in harsh environments. Four types of blurring point spread functions are applied to the test images in order to simulate long-distance acquisition. The results are compared with those of conventional Eigen face and Fisher face methods. The results indicate that Pc-LDA is better than conventional facial recognition techniques.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.728-735
• /
• 2022

Roofers get exposed to increased risk of knee musculoskeletal disorders (MSDs) at different phases of a sloped shingle installation task. As different phases are associated with different risk levels, this study explored the application of machine learning for automated classification of seven phases in a shingle installation task using knee kinematics and roof slope information. An optical motion capture system was used to collect knee kinematics data from nine subjects who mimicked shingle installation on a slope-adjustable wooden platform. Four features were used in building a phase classification model. They were three knee joint rotation angles (i.e., flexion, abduction-adduction, and internal-external rotation) of the subjects, and the roof slope at which they operated. Three ensemble machine learning algorithms (i.e., random forests, decision trees, and k-nearest neighbors) were used for training and prediction. The simulations indicate that the k-nearest neighbor classifier provided the best performance, with an overall accuracy of 92.62%, demonstrating the considerable potential of machine learning methods in detecting shingle installation phases from workers knee joint rotation and roof slope information. This knowledge, with further investigation, may facilitate knee MSD risk identification among roofers and intervention development.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.77-84
• /
• 2012

Face classification has wide applications in intelligent video surveillance, content retrieval, robot vision, and human-machine interface. Pose and expression changes, and arbitrary illumination are typical problems for face recognition. When the face is captured at a distance, the image quality is often degraded by blurring and noise corruption. This paper investigates the efficacy of multi-classifier decision level fusion for face classification based on the photon-counting linear discriminant analysis with two different cost functions: Euclidean distance and negative normalized correlation. Decision level fusion comprises three stages: cost normalization, cost validation, and fusion rules. First, the costs are normalized into the uniform range and then, candidate costs are selected during validation. Three fusion rules are employed: minimum, average, and majority-voting rules. In the experiments, unfocusing and motion blurs are rendered to simulate the effects of the long distance environments. It will be shown that the decision-level fusion scheme provides better results than the single classifier.

• The Journal of Korean Physical Therapy
• /
• v.14 no.4
• /
• pp.172-182
• /
• 2002

Objectives: We did research in the cause of the Pitchers' injury and their recovery process to make a detailed injury list for the purpose of finding the cause of the Korean professional pitchers' injury and its classification. We drew the conclusion through the results as following. Methods: We posed a question to the 80 pitchers playing in the first team of the eight Korean professional baseball team and analyzed the 62 pieces of question paper except the paper having a mistake. We used SAS/PC statistical package in analyzing the data. Results: In the frequency of the pitchers' shoulder injury in the last three years, the injured of all the players were 61.3$\%$ and the injury free players were 28.7$\%$. The cause of the injury was 45.2$\%$ wrong pitching motion, which was the highest value. For the shape of a pain when injured, the reverberation ache feeling when he is hit in the weight commanded an absolute majority as 19.4$\%$. Those who had muscular pain were 17.7$\%$, which was felt mostly at the pitching motion. The most trouble name of the injured shoulder was bicepstendinitis as 16.1$\%$ while the injury of shoulder joint was the lowest as 1.6$\%$. As the most widely used treatment, 25.8 percent of all the players had taken an electronical thraphy after injury. 14.5 percent of the players who had an injury to the shoulder told that they have an operation and 85 percent of them didn't. As a sort of the operation, a repairing of labrum was 44.4 percent, which is the highest value and the 77.8 percent pitchers are performing a normal pitching through rehabilitation after the operation and 22.2 percent of them are undergoing rehabilitation training. Conclusion: The research have shown that the main cause of the injury, concerning the Korean professional pitchers throwing lots of ball in both matches and practices, is overuse syndrome, bad mechanism, muscle weakness and instability of balance. I think that the role of trainer, physical therapy, and team physician taking charge of the players' injury must learn physical test method by heart exactly to check up the state of the injury definitely at the initial phase. Moreover, when the cause of the injury part after a close examination is discovered, the scientific and good surgery is essential to the rehabilitation success and making a classification of shoulder instability is useful to make a operation plan as well as the players' rehabilitation, treatment.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.7
• /
• pp.540-549
• /
• 2018

Classifying the front body of the missile and debris of a high-speed missile in intercepting a high-speed missile is an important issue. The motion of the front body of the missile is characterized by precession, but the motion of the debris in the boosting part separation phase is characterized by tumbling. There are periodic patterns caused by the precession or tumbling motion on the dynamic radar cross section (RCS). In addition, there are statistical properties caused by the change pattern of the dynamic RCS. A method is proposed to classify the front body of the missile and debris using periodic and statistical properties of the dynamic RCS. Three kinds of feature vector are extracted from the periodic and statistical properties of the dynamic RCS. The front body of the missiles and debris was classified using a support vector machine.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.103-114
• /
• 2014

This study intends to make a proposal the direction classification to develop the independent study of e-book's visualization. For this, we research into the e-book of Disney animation which achieved recognition in the literary value and amusement First of all, We grasp the meaning of the concept of e-book's aerial-image and perceptual principle. Next, We found the subject that starts the movement, and then observed the factor of the presentation to be possible to experience the actual spatial experience by the motion-produced cues. Through analysis process, We can classify the appearance elements, media, camera, and the readers' motion-produced cues into 13 parts and define as the codes. As we analysis the frequency of use of the analysis object, We separated it into the 46 combination exercises. According to the combination with the independent exercise, We separated them into 4 groups. There are the actual spatial experience, narrative spatial experience, the experience of characters. The basis for these, we can analyze the characteristics of the motion-produced cues. This study has the meaning of the expansion of e-book into the film language system by separating the e-book's narrative visualization type.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.163-168
• /
• 2003

In transmitting compressed video bit-stream over Internet, packet loss causes error propagation in both spatial and temporal domain, which in turn leads to severe degradation in image quality. In this paper, a new approach for the recovery of lost or erroneous Motion Vector(MV)s by classifying the movements of neighboring blocks by their homogeneity is proposed. MVs of neighboring blocks are classified according to the direction of MVs and a representative value for each class is determined to obtain the candidate MV set. By computing the distortion of the candidates, a MV with the minimum distortion is selected. Experimental results show that the proposed algorithm exhibits better performance in many cases than existing methods.