• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2419-2424
• /
• 2013

In a conventional MOG algorithm, a small threshold for background decision causes the background recognition delay in a periodic background and a large threshold makes it recognize passing objects as background in a stationary background. This paper proposes the improved MOG algorithm using adaptive threshold. The proposed algorithm estimates changes of weight in the dominant model of the MOG algorithm both in the short and long terms, classifies backgrounds into the stationary and periodic ones, and assigns proper thresholds to them. The simulation results show that the proposed algorithm decreases the maximum number of frame in background recognition delay from 137 to 4 in the periodic background keeping the equal performance with the conventional algorithm in the stationary background.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.580-585
• /
• 2005

A QRT(Quad-Rotor Type) hovering robot system is developed for quick detection and observation of the circumstances under calamity environment such as indoor fire spots. The UAV(Unmanned Aerial Vehicle) is equipped with four propellers driven by each electric motor, an embedded controller using a DSP, INS(Inertial Navigation System) using 3-axis rate gyros, a CCD camera with wireless communication transmitter for observation, and an ultrasonic range sensor for height control. The developed hovering robot shows stable flying performances under the adoption of RIC(Robust Internal-loop Compensator) based disturbance compensation and the vision based localization method. The UAV can also avoid obstacles using eight IR and four ultrasonic range sensors. The VTOL(Vertical Take-Off and Landing) flying object flies into indoor fire spots and sends the images captured by the CCD camera to the operator. This kind of small-sized UAV can be widely used in various calamity observation fields without danger of human beings under harmful environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.3
• /
• pp.309-314
• /
• 2010

In this paper, an intelligent security camera over internet is proposed. Among ISC methods, watersheds based methods produce a good performance in segmentation accuracy. But traditional watershed transform has been suffered from over-segmentation due to small local minima included in gradient image that is input to the watershed transform. And a zone face candidates of detection using skin-color model. last step, face to check at face of candidate location using SVM method. It is extract of wavelet transform coefficient to the zone face candidated. Therefore, it is likely that it is applicable to read world problem, such as object tracking, surveillance, and human computer interface application etc.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.29-37
• /
• 2019

Since construction sites are exposed to outdoor environments, working conditions are significantly dangerous. Thus, wearing of the personal protective equipments such as safety helmet is very important for worker safety. However, construction workers are often wearing-off the helmet as inconvenient and uncomportable. As a result, a small mistake may lead to serious accident. For this, checking of wearing safety helmet is important task to safety managers in field. However, due to the limited time and manpower, the checking can not be executed for every individual worker spread over a large construction site. Therefore, if an automatic checking system is provided, field safety management should be performed more effectively and efficiently. In this study, applicability of deep learning based computer vision technology is investigated for automatic checking of wearing safety helmet in construction sites. Faster R-CNN deep learning algorithm for object detection and classification is employed to develop the automatic checking model. Digital camera images captured in real construction site are used to validate the proposed model. Based on the results, it is concluded that the proposed model may effectively be used for automatic checking of wearing safety helmet in construction site.

• Journal of Convergence for Information Technology
• /
• v.9 no.9
• /
• pp.20-26
• /
• 2019

With the development of ICT technology and the promotion of smartphone penetration, purchasing services that purchase various products through online market are being activated. In particular, due to advances in storage and delivery technology, sales of short food materials can be purchased online. Therefore, in this paper, we propose an integrated solution that enables advertisement effect, ordering and delivery through a purchase service even if there is no sales knowledge and sales network in a small shopping mall where only offline sales can be performed. The proposed system is able to efficiently view the product information by category through image search for the product that the user desires, so that the seller of the registered product can efficiently sell without any additional advertisement.

• Journal of Conservation Science
• /
• v.37 no.4
• /
• pp.340-356
• /
• 2021

We have tried the experimental research of lost-wax casting to reconstruct Gilt-Bronze Pensive Bodhisattva; preliminary and reconstruction experiment based on ancient texts. Main object to reconstruct is Korean National Treasure No.83, Gilt-Bronze Pensive Bodhisattva (Maitreya), then we measure alloy ratio and casting method based on the scientific analysis. Other impurities were removed from the base metal components(copper : tin : lead) and their ratio was set to 95.5 : 6.5 : 3 where the ratios for tin and lead were increased by 2.5% each. The piece-mold casting method was used, and piece-mold casting experiments were carried out twice in this study but supplementary research on piece-mold casting was necessary. The microstructure was confirmed to be typical cast microstructure and the component analysis result was similar to that of the prior study. Analysis of the chemical composition is confirmed to copper, tin, lead, and zinc, and the chemical composition of the matrix was 87.8%Cu-7.5%Sn-2.7%Pb-2.1%Zn, and similar to previous experimental research. Also resulted in the detection of small impurity in Zn. Analysis of the mould revealed that the mould was fabricated by adding quartz and organic matter for structural stability, fire resistance, and air permeability. We expect that our research will contribute to provide base data for advanced researches in future.

• Current Optics and Photonics
• /
• v.6 no.4
• /
• pp.381-391
• /
• 2022

Two-photon-polymerization additive-manufacturing systems feature high resolution and precision. However, there are few reports on specific methods and possible problems concerning the use of small lasers to independently build such platforms. In this paper, a femtosecond-laser two-photon-polymerization additive-manufacturing system containing an optical unit, control unit, monitoring unit, and testing unit is built using a miniature femtosecond laser, with a detailed building process and corresponding control software that is developed independently. This system has integrated functions of light-spot detection, interface searching, micro-/nanomanufacturing, and performance testing. In addition, possible problems in the processes of platform establishment, resin preparation, and actual polymerization for two-photon-polymerization additive manufacturing are explained specifically, and the causes of these problems analyzed. Moreover, the impacts of different power levels and scanning speeds on the degree of polymerization are compared, and the influence of the magnification of the object lens on the linewidth is analyzed in detail. A qualitative analysis model is established, and the concepts of the threshold broadening and focus narrowing effects are proposed, with their influences and cooperative relation discussed. Besides, a linear structure with micrometer accuracy is manufactured at the millimeter scale.

• Journal of KIBIM
• /
• v.13 no.4
• /
• pp.85-95
• /
• 2023

In the process of creating drawings based on Building Information Modeling (BIM), automatically generated annotations can cause interference issues depending on the drawing type. This study aims to develop an algorithm for repositioning annotations using genetic algorithms to minimize such interferences. To achieve this, the Application Programming Interface (API) of BIM software was used to analyze data extractable from BIM drawing files. The process involved defining drawing data related to annotation repositioning, preprocessing this data, and deriving optimal placement coordinates for the annotations. Furthermore, applying the developed algorithm to the preliminary design drawings of small and medium-sized neighborhood facilities resulted in approximately a 95.37% decrease in annotation interference, indicating that the proposed algorithm can significantly enhance productivity in BIM-based drawing tasks.