• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.910-916
• /
• 2021

In modern society, various digital communication equipment is being used due to the influence of the 4th industrial revolution. Accordingly, interest in removing noise generated in a data transmission process is increasing, and research is being conducted to efficiently reconstruct an image. In this paper, we propose a filtering algorithm to remove the AWGN generated in the digital image transmission process. The proposed algorithm classifies pixels with high similarity by selecting regions with similar patterns around the input pixels according to block matching to remove the AWGN that appears strongly in the image. The selected pixel determines the estimated value by applying the weight obtained by the local steering kernel, and obtains the final output by adding or subtracting the input pixel value according to the standard deviation of the center mask. In order to evaluate the proposed algorithm, it was simulated with existing AWGN removal algorithms, and comparative analysis was performed using enlarged images and PSNR.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.654-660
• /
• 2020

Through the output of brain waves during muscle operation, this paper checks whether it is possible to find characteristic vectors of brain waves that are capable of dividing left and right movements by extracting brain waves in specific areas of muscle signal output that include the motion of the left and right muscles or the will of the user within EEG signals, where uncertainties exist considerably. A typical surface EMG and noninvasive brain wave extraction method does not exist to distinguish whether the signal is a motion through the degree of ionization by internal neurotransmitter and the magnitude of electrical conductivity. In the case of joint and motor control through normal robot control systems or electrical signals, signals that can be controlled by the transmission and feedback control of specific signals can be identified. However, the human body lacks evidence to find the exact protocols between the brain and the muscles. Therefore, in this paper, efficiency is verified by utilizing the results of application of CSP (Common Spatial Pattern) filter to verify that the left-hand and right-hand signals can be extracted through brainwave analysis when the subject's behavior is performed. In addition, we propose ways to obtain data through experimental design for verification, to verify the change in results with or without filter application, and to increase the accuracy of the classification.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.665-672
• /
• 2023

Purpose: Underground utility tunnel is facility that is jointly house infrastructure such as electricity, water and gas in city, causing condensation problems due to lack of airflow. This paper aims to prevent electricity leakage fires caused by condensation by detecting whether the control panel door in the underground utility tunnel is open using a deep learning model. Method: YOLO, a deep learning object recognition model, is trained to recognize the opening and closing of the control panel door using video data taken by a robot patrolling the underground utility tunnel. To improve the recognition rate, image augmentation is used. Result: Among the image enhancement techniques, we compared the performance of the YOLO model trained using mosaic with that of the YOLO model without mosaic, and found that the mosaic technique performed better. The mAP for all classes were 0.994, which is high evaluation result. Conclusion: It was able to detect the control panel even when there were lights off or other objects in the underground cavity. This allows you to effectively manage the underground utility tunnel and prevent disasters.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1036-1043
• /
• 2022

This paper discusses about the development of a visual sensor that can be installed in an automatic mooring device to detect the berthing condition of a vessel. Despite controlling the ship's speed and confirming its location to prevent accidents while berthing a vessel, ship collision occurs at the pier every year, causing great economic and environmental damage. Therefore, it is important to develop a visual system that can quickly obtain the information on the speed and location of the vessel to ensure safety of the berthing vessel. In this study, a visual sensor was developed to observe a ship through an image while berthing, and to properly check the ship's status according to the surrounding environment. To obtain the adequacy of the visual sensor to be developed, the sensor characteristics were analyzed in terms of information provided from the existing sensors, that is, detection range, real-timeness, accuracy, and precision. Based on these analysis data, we developed a 3D visual module that can acquire information on objects in real time by conducting conceptual designs of LiDAR (Light Detection And Ranging) type 3D visual system, driving mechanism, and position and force controller for motion tilting system. Finally, performance evaluation of the control system and scan speed test were executed, and the effectiveness of the developed system was confirmed through experiments.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.836-850
• /
• 2009

Human posture recognition has attracted tremendous attention in ubiquitous environment, performing arts and robot control so that, recently, many researchers in pattern recognition and computer vision are working to make efficient posture recognition system. However the most of existing studies is very sensitive to human variations such as the rotation or the translation of body. This is why the feature, which is extracted from the feature extraction part as the first step of general posture recognition system, is influenced by these variations. To alleviate these human variations and improve the posture recognition result, this paper presents 3D Star Skeleton and Principle Component Analysis (PCA) based feature extraction methods in the multi-view environment. The proposed system use the 8 projection maps, a kind of depth map, as an input data. And the projection maps are extracted from the visual hull generation process. Though these data, the system constructs 3D Star Skeleton and extracts the rotation invariant feature using PCA. In experimental result, we extract the feature from the 3D Star Skeleton and recognize the human posture using the feature. Finally we prove that the proposed method is robust to human variations.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.1
• /
• pp.63-70
• /
• 2009

Recently, in the security token based authentication system, there is an increasing trend of using fingerprint for the token holder verification, instead of passwords. However, the security of the fingerprint data is particularly important as the possible compromise of the data will be permanent. In this paper, we propose an approach for secure fingerprint verification by distributing both the secret and the computation based on the fuzzy vault(a cryptographic construct which has been proposed for crypto-biometric systems). That is, a user fingerprint template which is applied to the fuzzy vault is divided into two parts, and each part is stored into a security token and a server, respectively. At distributing the fingerprint template, we consider both the security level and the verification accuracy. Then, the geometric hashing technique is applied to solve the fingerprint alignment problem, and this computation is also distributed over the combination of the security token and the server in the form of the challenge-response. Finally, the polynomial can be reconstructed from the accumulated real points from both the security token and the server. Based on the experimental results, we confirm that our proposed approach can perform the fuzzy vault-based fingerprint verification more securely on a combination of a security token and a server without significant degradation of the verification accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.157-166
• /
• 2024

The Army TIGER System, which is being deployed to implement a future combat system, is expected to bring innovative changes to the army's combat methods and comabt execution capability such as mobility, networking and intelligence. To this end, the Army will introduce various systems using drones, robots, unmanned vehicles, AI(Artificial Intelligence), etc. and utilize them in combat. The use of various unmanned vehicles and AI is expected to result in the introduction of equipment with new technologies into the army and an increase in various types of transmitted information, i.e. data. However, currently in the military, there is an acceleration in research and combat experimentations on warfigthing options using Army TIGER forces system for specific functions. On the other hand, the current reality is that research on cyber threats measures targeting information systems related to the increasing number of unmanned systems, data production, and transmission from unmanned systems, as well as the establishment of cloud centers and AI command and control center driven by the new force systems, is not being pursued. Accordingly this paper analyzes the structure and characteristics of the Army TIGER force integration system and makes suggestions for necessity of building, available cyber defense solutions and Army TIGER integrated cyber protections system that can respond to cyber threats in the future.

• Journal of Bio-Environment Control
• /
• v.22 no.3
• /
• pp.284-290
• /
• 2013

This study analyzed the geometric, compressive, cutting and friction properties of oriental melons in order to design a gripper capable of soft handling and a cutter for cutting oriental melon vine among the end effector of oriental melon as a preliminary step for developing the end effector of the robot capable of harvesting oriental melons in protected cultivation. As a result, the average length, diameter at the midpoint, weight, volume and roundness of the oriental melons were 108 mm, 70 mm, 188 g, 333 mL and 3.8 mm. Nonlinear regression analysis was performed on the equation $W=L^a{\times}D_2^b$ with variation of the length (L) and diameter (D2) of the weight (W) of the oriental melons. As a result, it was shown that there was a correlation between a of 2.0279 and b of -0.9998 as a constant value. The average diameter of the oriental melon vine was 3.8 mm, and most vines were distributed within a radius of 5 mm from the center. The average yield value, compressive strength and hardness of the oriental melons were $36.5N/cm^2$, $185.7N/cm^2$ and $636.7N/cm^2$, respectively. The average cutting force and shear strength of the oriental melon vines were $2.87{\times}10^{-2}\;N$ and $5.60N/cm^2$, respectively. The maximum friction coefficient of the oriental melons was rubber of 0.609, followed by aluminium of 0.393, stainless steel of 0.177 and teflon of 0.079. It was considered possible to apply it to the size of the gripper and cutter, turning radius, dynamics of drive motor and selection of materials and their quality in light of the position error and safety factor according to the movement when designing end effector based on the analyzed data.

• Journal of Sensor Science and Technology
• /
• v.7 no.2
• /
• pp.124-130
• /
• 1998

High-speed 3D vision systems are essential for autonomous robot or vehicle control applications. In our study, a stereo vision process has been developed. It consists of three steps : extraction of edges in right and left images, matching corresponding edges and calculation of the 3D map. This process is implemented in a VME 150/40 Imaging Technology vision system. It is a modular system composed by a display, an acquisition, a four Mbytes image frame memory, and three computational cards. Programmable accelerator computational modules are running at 40 MHz and are based on TMS320C31 DSP with a $64{\times}32$ bit instruction cache and two $1024{\times}32$ bit internal RAMs. Each is equipped with 512 Kbytes static RAM, 4 Mbytes image memory, 1 Mbytes flash EEPROM and a serial port. Data transfers and communications between modules are provided by three 8 bit global video bus, and three local configurable pipeline 8 bit video bus. The VME bus is dedicated to system management. Tasks between DSPs are distributed as follows: two DSPs are used to edges detection, one for the right image and the other for the left one. The last processor computes the matching process and the 3D calculation. With $512{\times}512$ pixels images, this sensor generates dense 3D maps at a rate of about 1 Hz depending of the scene complexity. Results can surely be improved by using a special suited multiprocessors cards.