• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.305-319
• /
• 2021

The overseas calibration sites such as Mongolia used for Korea Multi-purpose Satellite (KOMPSAT-5 or K5), have a disadvantage in that maintenance and repair costs are high and immediate response is difficult when an unexpected problem occurs. Accordingly, the necessity of establishing a domestic SAR calibration site was suggested, but the progress of related research is insignificant. In this paper, we investigated what conditions should be satisfied in terms of backscattering characteristics to construct a site for SAR satellite image quality evaluation and calibration. First of all, it was selected first by applying general indicators such as accessibility and availability among places recommended as satellite image calibration candidate sitesin Korea. Next, three places, site A (Goheung-gun, Jeollanam-do), site B (Jeonju-si, Jeollabuk-do), and site C (Daedeok Research Complex, Daejeon), were selected as the final candidates because they are relatively wide and easy to install AT or CR. Site A, located in Goheung-gun, Jeollanam-do, was best considered in terms of slope measurements, minimum site area to obtain ISLR, uniformity of DN values and backscatter coefficients, interference by strong reflectors, and backscatter clutter level.

• Journal of the Korea Institute of Construction Safety
• /
• v.2 no.1
• /
• pp.36-44
• /
• 2019

$21^{st}$ century is digitally civilized era. Technologies such as AI, Iot, Big Data, Mobile and etc makes this era digitally advanced. These advancement of the technology greatly impacted detection range of the radar. Human's eye sight can see about 20Km and hear 20 ~ 20000 Hz. These limitations can be overcome using radar. This radar technology is used in military, aircraft, ship, vehicle and etc. to replace human eye. However, radar technology is capable of making False Alarm Rate. This document will propose the fix of these problems. Radar's distortion includes beam refraction, diffraction and reflection. These inaccurate data result in deterioration of human judgements and my cause various casualties and damages. Radar goes through annual testing to test how many false alarm is being produced. Normal radar usually makes 10 to 20 False alarms. In emergency situation, if operator were to follow this false alarm, this might result in following false object or take 12 more seconds to follow the right object. This problem can be overcome by using different radar data from different places and angles. This helps reduces False Alarm rate and track the object twice as fast.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.