• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.1
• /
• pp.30-44
• /
• 2022

The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.493-497
• /
• 2015

This study was started with concern about problem of increasing physical and personal injury caused by traffic accidents, despite of technological advances in transportation. As the vehicles, which is currently produced, informs the driver only detecting the proximity of an object by the front and rear sensor, this study implemented the color detection algorithm, the circular shape recognition algorithm, and the distance recognition algorithm and built the accident prevention beyond accident perception, which commends to avoid the object or to stop the robot, if object was detected by algorithms. For the simulation, we made the Arduino vehicle robot equipped with compact wireless communication camera and confirmed that the robot successfully avoids an object or stops itself in simulated driving.

• Progress in Superconductivity
• /
• v.9 no.2
• /
• pp.162-166
• /
• 2008

We are developing a sensitive gamma ray spectrometer based on superconducting transition edge sensors. The detector consists of a small piece of high purity Sn as an absorber and a Ti/Au bilayer as a temperature sensor. It is designed to measure the thermal signal caused by absorption of gamma rays. The mechanical support and the thermal contact between the absorber and the thermometer were made with Stycast epoxy. The bilayer was formed by e-beam evaporation and patterned by wet etching on top of a $SiN_X$ membrane. A sharp superconducting transition of the film was measured near 100 mK. When the film was biased to the edge of the transition, signals were observed due to single photon absorption emitted from an $^{241}Am$ source. The measured spectrum showed several characteristic peaks of the source including 59.5 keV gamma line. The full with at half maximum was about 900 eV for the 59.5 keV gamma line. The background was low enough to resolve low energy lines. Considerations to improve the energy resolution of the gamma ray spectrometer are also discussed.

• Industrial Engineering and Management Systems
• /
• v.15 no.1
• /
• pp.92-98
• /
• 2016

Due to the large scale of Antarctic science, scientific collaboration is required for conducting scientific research. In this study, we attempted to investigate collaboration network and the role of research station in Antarctic science based on bibliometric data from 1995 to 2014. We confirmed that geographical proximity tends to be important for scientific collaboration by employing community detection in the network. This result raises the question about what the role of research station in Antarctica is. We tried to reveal its role by focusing on five countries, Belgium, China, Czech Republic, India, and Korea that constructed new research stations during the last decade. Relative growth rate, a value to measure the growth of publications, didn't differ much around the construction period compared to those in other periods for these countries except Belgium. However, we found geographical keywords emerged around the construction for all five countries. These keywords were utilized to observe national research activities in Antarctica. They show where countries started to be concerned about after the construction.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.277-283
• /
• 2023

Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.

• Journal of Advanced Navigation Technology
• /
• v.24 no.3
• /
• pp.192-197
• /
• 2020

Recently, the technologies related to autonomous drive has studying the goal for safe operation and prevent accidents of vehicles. There is radar and camera technologies has used to detect obstacles in these autonomous vehicle research. Now a day, the method for using LiDAR sensor has considering to detect nearby objects and accurately measure the separation distance in the autonomous navigation. It is calculates the distance by recognizing the time differences between the reflected beams and it allows precise distance measurements. But it also has the disadvantage that the recognition rate of object in the atmospheric environment can be reduced. In this paper, point cloud data by triangular functions and Line Regression model are used to implement measurement algorithm, that has improved detecting objects in real time and reduce the error of measuring separation distances based on improved reliability of raw data from LiDAR sensor. It has verified that the range of object detection errors can be improved by using the Python imaging library.

• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1128-1141
• /
• 2010

This paper proposes a method of moving object detection in crowded scene using clustered trajectory. Unlike previous appearance based approaches, the proposed method employes motion information only to isolate moving objects. In the proposed method, feature points are extracted from input frames first and then feature tracking is followed to create feature trajectories. Based on an assumption that feature points originated from the same objects shows similar motion as the object moves, the proposed method detects moving objects by clustering trajectories of similar motions. For this purpose an energy function based on spatial proximity, motion coherence, and temporal continuity is defined to measure the similarity between two trajectories and the clustering is achieved by minimizing the energy function in CRFs (conditional random fields). Compared to previous methods, which are unable to separate falsely merged trajectories during the clustering process, the proposed method is able to rearrange the falsely merged trajectories during iteration because the clustering is solved my energy minimization in CRFs. Experiment results with three different crowded scenes show about 94% detection rate with 7% false alarm rate.

• Journal of Energy Engineering
• /
• v.13 no.2
• /
• pp.93-100
• /
• 2004

The smear media possible to sampling and radiation detection was prepared and evaluated for the surface contamination using indirect method. The films were made by impregnating Cerium Activated Yttrium Silicate (CAYS) in a polysulfone membrane. The membranes used solution as a dimethylformamide (DMF) and methylene chloride (MC), polysulfone as a polymer matrix and CAYS as a inorganic scintillator. The proximity membranes were prepared with single- and double-layered structure. The solidified methods were immersion to the nonsolvent bath such at water and ethanol and solvent evaporation. The measurement of the photon produced by interaction with radiation and inorganic scintillator used a photomultiflier tube (PMT), amplifier, and counter. In the comparison with the low background alpha/beta counter, the counter rate using inorganic scintillator proximity membrane for the $\^$14/C surface contamination was about 50%. Also. the $^3$H counting results revealed that the prepared membranes were efficient to monitor the surface contaminated with the low energy be-ray emitter nuclides.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.8
• /
• pp.1825-1830
• /
• 2015

In some cases, despite the pedestrian jaywalking pedestrian traffic lights to red, or even wait for the walk signal to stand down in the driveway. If this is the case may be liable to lead to a traffic accident. Thus, using an infrared sensor wateuna adopted the approach that the warning announcement when a pedestrian enters the driveway, curved pedestrian crossing the intersection in this case, it is difficult to install. In this paper, we propose a Fitness referral system utilizes a built-in sensor of the Android mobile devices. For this purpose, the sensor is a proximity sensor using an acceleration sensor. The proximity sensor has a number of disadvantages compared to the high precision battery power, the acceleration sensor accuracy, fast response time, on the other hand, the disadvantage is the lower. Close to reduce battery consumption of the sensor, BMI of the user sensor control mechanism and increase the accuracy of the acceleration sensor (Body Mass Index) obtained after the index was applied to the recommendation algorithm, which like the movement mechanism.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.3
• /
• pp.200-206
• /
• 2010

In ultrasound-excited thermography, the injected ultrasound to an object is transformed to heat and the appearance of defects can be visualized by thermography camera. The advantage of this technology is selectively sensitive to thermally active defects. Despite the apparent simplicity of the scheme, there are a number of experimental considerations that can complicate the implementation of ultrasound excitation thermography inspection. Factors including acoustic horn location, horn-crack proximity, horn-sample coupling, and effective detection range all significantly affect the detect ability of this technology. As conclusions, the influence of coupling pressures between ultrasound exciter and specimen was analyzed, which was dominant factor in frictional heating model.