• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.157-167
• /
• 2020

With the recent advancement of computer hardware and the contribution of open source libraries to facilitate access to artificial intelligence technology, the use of machine learning (ML) and deep learning (DL) technologies in various fields of exploration geophysics has increased. In addition, ML researchers have developed complex algorithms to improve the inference accuracy of various tasks such as image, video, voice, and natural language processing, and now they are expanding their interests into the field of automatic machine learning (AutoML). AutoML can be divided into three areas: feature engineering, architecture search, and hyperparameter search. Among them, this paper focuses on hyperparamter search with Bayesian optimization, and applies it to the problem of facies classification using seismic data and well logs. The effectiveness of the Bayesian optimization technique has been demonstrated using Vincent field data by comparing with the results of the random search technique.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.12
• /
• pp.48-54
• /
• 2010

This paper presents a high-performance architecture of integer-pel motion estimation circuit for H.264 video CODEC. Full search algorithm guarantees the best results by examining all candidate blocks. However, the full search algorithm requires a huge amount of computation and data. Many fast search algorithms have been proposed to reduce the computational efforts. The disadvantage of these algorithms is that data access from or to memory is very irregular and data reuse is difficult. In this paper, we propose an efficient integer-pixel motion estimation algorithm and the circuit architecture to improve the processing speed and reduce the external memory bandwidth. The proposed circuit supports seven kinds of variable block sizes and generates 41 motion vectors. We described the proposed high-performance motion estimation circuit at R1L and verified its operation on FPGA board. The circuit synthesized by using l30nm CMOS standard cell library processes 139.8 1080HD ($1,920{\times}1,088$) image frames per second and supports up to H.264 level 5.1.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.1
• /
• pp.46-56
• /
• 1991

In this paper, 16word X 8bit Content Addressable and Reentrant Memory(CARM) is described. This device has 4 operation modes(read, write, match, reentrant). The read and write operation of CARM is like that of static RAM, CARM has the reentrant mode operation where the on chip garbage collection is accomplished conditionally. Thus function can be used for high speed matching unit of dynamic data flow computer. And CARM also can encode matching address sequentially according to therir priority. CARM consists of 8 blocks(CAM cell, Sequential Address Encoder(S.A.E). Reentrant operation. Read/Write control circuit, Data/Mask Register, Sense Amplifier, Encoder. Decoder). Designed DARM can be used in data flow computer, pattern, inspection, table look-up, image processing. The simulation is performed using the QUICKSIM logic simulator and Pspice circuit simulator. Having hierarchical structure, the layout was done using the 3{\;}\mu\textrm{m} n well CMOS technology of the ETRI design rule.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.74-79
• /
• 2008

In this paper, we propose and design a new 0.264/AVC watermarking algorithm for protection of copyright by inserting a watermark after quantization. This invisible watermarking algorithm insets a watermark into chrominance components of I frame such that we can avoid degradation of original images. According to test results we could limit image degradation by 1dB, avoid bit rate increment within 2% and increase processing time by only 2%. The IP is designed by Hynix 0.25 micron technology and the maximum operating frequency of 115MHz is achieved. The PSNR of the embedded watermark is about 35dB according to the test result.

• Journal of IKEEE
• /
• v.14 no.3
• /
• pp.224-231
• /
• 2010

Automatic detection of objects in images has been one of core challenges in the areas such as computer vision and pattern analysis. Especially, with the recent deployment of personal mobile devices such as smart phone, such technology is required to be transported to them. Usually, these smart phone users are equipped with devices such as camera, GPS, and gyroscope and provide various services through user-friendly interface. However, the smart phones fail to give excellent performance due to limited system resources. In this paper, we propose a new scheme to improve object recognition performance based on pre-computation and simple local features. In the pre-processing, we first find several representative parts from similar type objects and classify them. In addition, we extract features from each classified part and train them using regression functions. For a given query image, we first find candidate representative parts and compare them with trained information to recognize objects. Through experiments, we have shown that our proposed scheme can achieve resonable performance.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.3 s.33
• /
• pp.87-94
• /
• 2005

3D positional information of lane can be automatically calculated tv combining GPS data, IMU data if coordinates of lane centers are given. The Road Safety Survey and Analysis Vehicle(RoSSAV) is currently under development to analyze three dimensional safety and stability of roads. RoSSAV has GPS and IMU sensors to get positional information of the vehicle and two road-facing CCD cameras for extraction of lane coordinates. In this paper, we develop technology that automatically detects centers of lanes from the road-facing cameras of RoSSAV. The proposed algorithm defines line-support regions by grouping pixels with similar edge orientation and magnitude together and extracts a line from each line support region by planar fitting. Then if extracted lines and the region in-between satisfy the criteria of brightness and width, we decide this region as lane. The proposed algorithm was more precise and stable than the previously proposed algorithm based on brightness threshold method. Experiments with real road scenes confirmed that lane was effectively extracted by the proposed algorithm.

• The Research Journal of the Costume Culture
• /
• v.18 no.6
• /
• pp.1194-1210
• /
• 2010

The influence of digital media according to environmental change of multi-media came to have significance more than what we imagine. In accordance with high resolution of HDTV in digital media era, the cautious awareness is required for skin color by the immediate color such as replica of TV color, lighting and clothing. As for the broadcasting makeup expression technique caused by a change in broadcasting environment in the digital media era, the first, There is necessity for natural makeup technique, and for expressing the whole makeup evenly and very delicately. The makeup work gets much more delicate. For the delicate expression, more time is being required than the existing makeup time. Second, Lots of time and manpower are required for elaborate real-object processing on all the production fields such as background set, stage properties, and makeup. Third, Realistic expression is available on the screen. Importance of basic makeup is highlighted. Thus, even the skin care shop came to be prevalent. Development in only HD cosmetics is needed for foundation with fine particle in new material and with diverse colors hereafter. The video-media field is a method that is ignored a sense of distance through vehicles such as camera, picture tube, and several kinds of broadcasting machinery and equipment and that is delivered vividly to viewers through screen, unlike the stage makeup, thereby being needed the makeup technology proper for HDTV according to the changing broadcasting environment and media. The video machinery and equipment are proceeding with being gradually high-tech and precise. Thus, an expert in makeup needs to know common sense on the video machinery and equipment before makeup, and needs to make an effort according to it. And, a follow-up research can be said to be necessary on the advance in makeup method and on more diverse dedicated cosmetics along with a research on color tone proper for HDTV.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.171-179
• /
• 2013

Recognition and image processing technology depends on illumination variation. One of the most important factors is the parameters of algorithms. When it comes to select these values, the system has different types of recognition accuracy. In this paper, we propose performance improvement of the eye tracking system that depends on some environments such as, people, location, and illumination. Optimized threshold parameter was decided by using reinforcement learning. When the system accuracy goes down, reinforcement learning used to train the value of parameters. According to the experimental results, the performance of eye tracking system can be improved from 3% to 14% by using reinforcement learning. The improved eye tracking system can be effectively used for human-computer interaction.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1079-1085
• /
• 2012

For precise motion control, S-curve velocity profile is generally used but it has disadvantage of relatively long calculation time for floating-point arithmetics. In this paper, we present a new generating method for velocity profile to reduce delay time of profile generation so that it overcomes such disadvantage and enhances the efficiency of precise motion control. In this approach, the velocity profile is designed based on the gamma correction expression that is generally used in image processing to obtain a smoother movement without any critical jerk. The proposed velocity profile is designed to support both T-curve and S-curve velocity profile. It can generate precise profile by adding an offset to the velocity profile with decimals under floating point that are not counted during gamma correction arithmetic operation. As a result, the operation time is saved and the efficiency is improved. The proposed method is compared with the existing method that generates velocity profile using ring buffer on a 8-bit low-cost MCU. The result shows that the proposed method has no delay in generating driving profile with good accuracy of each cycle velocity. The significance of the proposed method lies in reduction of the operation time without degrading the motion accuracy. Generated driving signal also shows to verify effectiveness of the proposed method.