• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.344-358
• /
• 2019

Surveillance cameras have installed in many places because security and safety is becoming important in modern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now, the need for research to analyze surveillance videos is growing. This study proposes an algorithm to track multiple persons using SURF and background subtraction. While the SURF algorithm, as a person-tracking algorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with sudden changes in videos. To resolve such tracking errors, we combined SURF with a background subtraction algorithm and showed that the proposed approach increased the tracking accuracy. In addition, the background subtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detected persons, and thus the proposed algorithm can automatically detect the enter/exit of persons.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.67-70
• /
• 2018

Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.76-83
• /
• 2019

In this paper, we propose the beamforming algorithm for the performance improvement of MIMO MC-CDMA system. The proposed multibeamforming of MIMO MC-CDMA structure having the same number of beamformer as the number of transmit antenna is derived by calculating the error signals between the coded pilot symbols and the corresponding received signals from the multiple transmitters of the desired user in the frequency domain, transforming the frequency-domain error signals into time-domain error signals, and updating the weights of the multibeamformer in the time-domain in the direction minimizing the mean squared error (MSE). The proposed approach can track each direction of arrival (DOA) of the signals from multi-antennas of a desired user. The performance improvement is investigated through computer simulation by applying the proposed approach to MIMO MC-CDMA system in a multipath fading channel with multiusers.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.53.3-53.3
• /
• 2019

Recent work by Ravanbakhsh et al. (2017), Mathuriya et al. (2018) showed that convolutional neural networks (CNN) can be trained to predict cosmological parameters from the visual shape of the large scale structure, i.e. the filaments, clusters and voids of the cosmic density field. These preliminary works used the dark matter density field at redshift zero. We build upon these works by considering realistic mock galaxy catalogues that mimic true observations. We construct light-cones that span the redshift range appropriate for current and near future cosmological surveys such as LSST, EUCLID, WFIRST etc. In summary, we propose a novel multi-image input CNN to track the evolution in the morphology of large scale structures over cosmic time to constrain cosmology and the expansion history of the Universe.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.32.2-32.2
• /
• 2021

Radio relics, Mpc-size elongated diffuse radio emissions found at galaxy cluster outskirts, are known as the result of shock acceleration during the cluster merger. Theories have claimed that low Mach number shocks are too inefficient to create the observed properties of radio relics. Alternative scenarios such as fossil cosmic ray electrons (CRes) from AGNs are required to explain the observations. However, how exactly the fossil CRes from AGNs can supply the Mpc-size radio relic is still an open question. In this study, we present our recent uGMRT radio observation results of the merging galaxy cluster Abell 514. We found three remarkable AGN jet tails that may have undergone multiple reorientations and extend nearly 800 kpc. Using multi-frequency data, we have performed spectral analysis along the AGN tails and track how the tails lose or gain energy as they propagate in the intracluster medium. We will discuss whether these AGN jets can provide sufficient seed CRes to radio relics.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.2_2
• /
• pp.319-324
• /
• 2024

In this paper, the Artificial Intelligence Space(AI-Space) for human-robot interface is presented, which can enable human-computer interfacing, networked camera conferencing, industrial monitoring, service and training applications. We present a method for representing, tracking, and objects(human, robot, chair) following by fusing distributed multiple vision systems in AI-Space. The article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguous conditions. We propose to track the moving objects(human, robot, chair) by generating hypotheses not in the image plane but on the top-view reconstruction of the scene.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.87-92
• /
• 2024

The rapid development of artificial intelligence technology in recent years is evident, from the emergence of ChatGPT to innovations like Midjourney, Stable Diffution, and the upcoming SORA text-to-video technology by OPENai. Animation capture technology, driven by the AI technology trend, is undergoing significant advancements, accelerating the progress of the animation industry. Through an analysis of the current application of DEEPMOTION, this paper explores the development direction of AI motion capture technology, analyzes issues such as errors in multi-person object motion capture, and examines the vast prospects. With the continuous advancement of AI technology, the ability to recognize and track complex movements and expressions faster and more accurately, reduce human errors, enhance processing speed and efficiency. This advancement lowers technological barriers and accelerates the fusion of virtual and real worlds.

• Applied Science and Convergence Technology
• /
• v.24 no.5
• /
• pp.136-141
• /
• 2015

We studied the compact anode design to develop 100 kW rotating anode X-ray tube with large focal spot 1.2 mm, small focal spot 0.6 mm and tube voltage 150 kV for large hospital digital radiography using computer thermal simulation. The larger thermal radiation effect in a high vacuum can reduce the temperature of anode so the method to increase the surface area of anode is investigated. The anode has the multi-tier shape at the back side of TZM body of anode and also bigger diameter of anode. The number of multi-tiers was varied from 6 to 15 and the diameter of anode was also varied from ${\Phi}74$ to ${\Phi}82$. From ANSYS transient thermal simulation result, we could obtain $1056.4^{\circ}C$ anode maximum temperature when applying 100 kW input power at 0.1 second on target focal track which is less than $1091^{\circ}C$ of the conventional 75 kW X-ray tube with reduced anode weight by 15.5% than the conventional anode. The compact anode of reduced anode weight is able to improve the unwanted noise when the rotor is rotating at high-speed and also reduce the rotational torque which the cost effective stator-coil is possible. It is believed that the anode with 15 ea multi-tiers using ${\Phi}82$ can satisfy with the specification of the anode heat capacity. From the results of this paper, it has been confirmed that the proposed compact anode can be used as the anode of 100 kW rotating anode X-ray tube for digital radiography.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.12
• /
• pp.1275-1283
• /
• 2014

Characteristics of PCM(Pulse Code Modulation) waveform are suitable for target tracking. Especially in terms of dwell time, it is desirable to detect and track a moving target with the single PCM waveform for a MFR(Multi-Function Radar) which carries out multiple tasks. General PCM waveform processing includes Doppler filter bank caused by the characteristics of ambiguity function, to detect target and estimate Doppler frequency, which induces hardware burden and computational complexity. We propose a ML(Maximum Likelihood) based Doppler estimator for a PCM waveform, which is the closed form suboptimal solution and computationally efficient to estimate Doppler frequency and detect a moving target.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.6
• /
• pp.899-905
• /
• 2013

In this paper, we focus on how to calibrate multi-cameras easily and how to efficiently detect quad-copters with small-numbered particles. Each particle is a six dimensional vector that is composed of 3D position and 3D orientation of a quad-copter in the space. Due to curse of dimensionality, that leads to explosive computational costs with a large amount of high-dimensioned particles. To detect efficiently, we need to put more particles in very promising spaces and few particles in other spaces. Though computational cost is lowered by minimizing particles, in order to track a quad-copter with multiple cameras in real-time, multiple images from the cameras should be synchronized and analyzed. Therefore, lots of the computations still need to be done. Because of this, GPGPU(General-Purpose computing on Graphics Processing Units) is implemented for parallel computing. This method has been successfully tested and gives accurate results in practical situations.