• Journal of the Korea Convergence Society
• /
• 제10권11호
• /
• pp.79-84
• /
• 2019

Video image based technology is being used in various fields with continuous development. The demand for vision system technology that analyzes and discriminates image objects acquired through cameras is rapidly increasing. Image processing is one of the core technologies of vision systems, and is used for defect inspection in the semiconductor manufacturing field, object recognition inspection such as the number of tire surfaces and symbols. In addition, research into license plate recognition is ongoing, and it is necessary to recognize objects quickly and accurately. In this paper, propose a recognition model through the rotational alignment of objects after checking the angle value of the tilt of the object in the input video image for the recognition of inclined objects such as numbers or symbols marked on the surface. The proposed model can perform object recognition of the rotationally sorted image after extracting the object region and calculating the angle of the object based on the contour algorithm. The proposed model extracts the object region based on the contour algorithm, calculates the angle of the object, and then performs object recognition on the rotationally aligned image. In future research, it is necessary to study template matching through machine learning.

• Journal of IKEEE
• /
• 제22권1호
• /
• pp.46-52
• /
• 2018

The problem of traffic light detection and recognition has recently become one of the most important topics in various researches on autonomous driving. Most algorithms are based on colors to detect and recognize traffic light signals. These methods have disadvantage in that the recognition rate is lowered due to the change of the color of the traffic light, the influence of the angle, distance, and surrounding illumination environment of the image. In this paper, we propose machine learning based detection and recognition algorithm using shape information to solve these problems. Unlike the existing algorithms, the proposed algorithm detects and recognizes the traffic signals based on the morphological characteristics of the traffic lights, which is advantageous in that it is robust against the influence from the surrounding environments. Experimental results show that the recognition rate of the signal is higher than those of other color-based algorithms.

• Journal of the Korea Computer Graphics Society
• /
• 제26권4호
• /
• pp.1-8
• /
• 2020

Motion synthesis using physics-based controllers can generate a character animation that interacts naturally with the given environment and other characters. Recently, various methods using deep neural networks have improved the quality of motions generated by physics-based controllers. In this paper, we present a control policy learned by deep reinforcement learning (DRL) that enables Luxo, the mascot character of Pixar animation studio, to run towards a random goal location while imitating a reference motion and maintaining its balance. Instead of directly training our DRL network to make Luxo reach a goal location, we use a reference motion that is generated to keep Luxo animation's jumping style. The reference motion is generated by linearly interpolating predetermined poses, which are defined with Luxo character's each joint angle. By applying our method, we could confirm a better Luxo policy compared to the one without any reference motions.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• 제36권7호
• /
• pp.666-673
• /
• 2008

To construct the accurate radio satellite navigation system, the efficient communication each satellite with the ground station is very important. Throughout the communication, the orbit of each satellite can be corrected, and those information will be used to analyze the satellite satus by the operator. Since there are limited resources of ground station, the schedule of antenna's azimuth and elevation angle should be optimized. On the other hand, the satellite in the medium earth orbit does not pass the same point of the earth surface due to the rotation of the earth. Therefore, the antenna pass schedule must be updated at the proper moment. In this study, Q learning approach which is a form of model-free reinforcement learning and genetic algorithm are considered to find the optimal antenna schedule. To verify the optimality of the solution, numerical simulations are conducted.

• Journal of Korean Physical Therapy Science
• /
• 제19권3호
• /
• pp.23-30
• /
• 2012

The purpose of this study was to apply treadmill training through motor learning to cerebral palsy children and examine its effects on their Gross Motor Functions. The subjects of this study were 13 spastic diplegia children who had difficulty in independent gait, and GMFCS level III, IV. We performed treadmill gait training using the principle of weight bearing, based on 4times a week for 30 minutes before and after each session physical therapy we gave weight bearing treadmill training 5 to 10 minutes, during 7 weeks(April 9, 2012~May 26, 2012) fittingly for the children's gait characteristics. In order to test how the weight bearing treadmill training affects spastic diplegia children's gross motor functions, we measured body mobility with Gross Motor Function Measure (GMFM). These data were collected before and after the experiment and analyzed through comparison. Data collected from the 13 spastic diplegia children the results were as follows. For evaluating with regard to change in body mobility, significant difference was observed between before and after the experiment in measured gross motor functions, which were crawling, kneeling, standing, walking, jumping and running(p<0.05). According to the results of this study, when gait training through motor learning was applied to spastic cerebral palsy children, it made significant changes in their body mobility. Accordingly, for the effective application of gait training through motor learning to cerebral palsy children, it is considered necessary to make research from different angle on how such training affects children's mobility, activity of muscles in the lower limbs, and gait characteristics.

• Journal of Drive and Control
• /
• 제20권4호
• /
• pp.1-8
• /
• 2023

In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

• The Journal of the Convergence on Culture Technology
• /
• 제10권2호
• /
• pp.511-516
• /
• 2024

The recently enacted detailed guidelines on the performance evaluation of track facilities presented the necessary requirements regarding the evaluation procedures and implementation methods of track performance evaluation. However, the grade of rail surface damage is determined by external inspection (visual inspection), and there is no choice but to rely only on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we attempted to develop a diagnostic application that can diagnose rail internal defects using rail surface damage. In the field investigation, rail surface damage was investigated and patterns were analyzed. Additionally, in the indoor test, SEM testing was used to construct image data of rail internal damage, and crack length, depth, and angle were quantified. In this study, a deep learning model (Fast R-CNN) using image data constructed from field surveys and indoor tests was applied to the application. A rail surface damage diagnosis application (App) using a deep learning model that can be used on smart devices was developed. We developed a smart diagnosis system for rail surface damage that can be used in future track diagnosis and performance evaluation work.

• Korean Journal of Remote Sensing
• /
• 제35권6_1호
• /
• pp.999-1009
• /
• 2019

The importance of high-resolution sea ice maps of the Arctic Ocean is increasing due to the possibility of pioneering North Pole Routes and the necessity of precise climate prediction models. In this study,sea ice classification algorithms for two deep learning models were examined using Sentinel-1 A/B SAR data to generate high-resolution sea ice classification maps. Based on current ice charts, three classes (Open Water, First Year Ice, Multi Year Ice) of training data sets were generated by Arctic sea ice and remote sensing experts. Ten sea ice classification algorithms were generated by combing two deep learning models (i.e. Simple CNN and Resnet50) and five cases of input bands including incident angles and thermal noise corrected HV bands. For the ten algorithms, analyses were performed by comparing classification results with ground truth points. A confusion matrix and Cohen's kappa coefficient were produced for the case that showed best result. Furthermore, the classification result with the Maximum Likelihood Classifier that has been traditionally employed to classify sea ice. In conclusion, the Convolutional Neural Network case, which has two convolution layers and two max pooling layers, with HV and incident angle input bands shows classification accuracy of 96.66%, and Cohen's kappa coefficient of 0.9499. All deep learning cases shows better classification accuracy than the classification result of the Maximum Likelihood Classifier.

• Journal of IKEEE
• /
• 제27권4호
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1711-1716
• /
• 2004

This paper presents identification and control of a 10-m antenna via accelerometers and angle encoder data. Artificial Neural Networks can be used effectively for the identification and control of nonlinear dynamical system such as a large flexible antenna. Some identification results are shown and compared with the results of conventional prediction error method. And we use a neural network inverse model for control the large flexible antenna. In the neural network inverse model, a neural network is trained, using supervised learning, to develop an inverse model of the antenna. The network input is the process output, and the network output is the corresponding process input. The control results show the validation of the ANN approach for identification and control of the 10-m flexible antenna.