• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• 패션비즈니스
• /
• 제24권2호
• /
• pp.17-31
• /
• 2020

The concept of municipal police is in contrast to the national police, which is in charge of the overall people. With increased localization, the need for a municipal police system is emphasized in each region. This study is intended to analyze the role of municipal police uniform considering the change in security from the national to the local level based on the introduction of municipal police system. The study investigators developed the concept of centralized national police system and decentralized self-governing municipal police system based on a literature review and Internet research. The investigators analyzed the design of municipal police uniform by reviewing the systems in several other countries. The results revealed specific formative features of municipal police uniform such as representative ambivalence, expression of visual language, manifest visibility, and reflection of regional characteristics. The municipal police uniform is adapted to changes in local government requiring a shift of awareness on to municipal police compared with the existing national police. The creation of a municipal police uniform enhances the efficiency of work by projecting a resident-friendly image, social support and cooperation, which play a huge role in illustrating the exemplary service to promote a stable and peaceful society locally.

• ETRI Journal
• /
• 제37권6호
• /
• pp.1220-1230
• /
• 2015

An autonomous valet parking (AVP) system is designed to locate a vacant parking space and park the vehicle in which it resides on behalf of the driver, once the driver has left the vehicle. In addition, the AVP is able to direct the vehicle to a location desired by the driver when requested. In this paper, for an AVP system, we introduce technology to recognize a parking space using image sensors. The proposed technology is mainly divided into three parts. First, spatial analysis is carried out using a height map that is based on dense motion stereo. Second, modelling of road markings is conducted using a probability map with a new salient-line feature extractor. Finally, parking space recognition is based on a Bayesian classifier. The experimental results show an execution time of up to 10 ms and a recognition rate of over 99%. Also, the performance and properties of the proposed technology were evaluated with a variety of data. Our algorithms, which are part of the proposed technology, are expected to apply to various research areas regarding autonomous vehicles, such as map generation, road marking recognition, localization, and environment recognition.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1305-1316
• /
• 2018

Graphical user interface(GUI) has a very important role to interact with software users. However, designing and coding of GUI are tedious and pain taking processes. In many studies, the researchers are trying to convert GUI elements or widgets to code or describe formally their structures by help of domain knowledge of stochastic methods. In this paper, we propose the GUI elements detection approach based on object detection strategy using deep neural networks(DNN). Object detection with DNN is the approach that integrates localization and classification techniques. From the experimental result, if we selected the appropriate object detection model, the results can be used for automatic code generation from the sketch or capture images. The successful GUI elements detection can describe the objects as hierarchical structures of elements and transform their information to appropriate code by object description translator that will be studied at future.

• Investigative Magnetic Resonance Imaging
• /
• 제6권2호
• /
• pp.166-172
• /
• 2002

목적: 척수경색의 진단에서 현성확산계수 값의 측정을 포함한 확산강조자기공명영상의 유용성을 평가하고자하였다. 대상 및 방법: 척수 경색으로 진단받은 6명의 환자를 대상으로 후향적으로 분석하였다. 경색증상 발현 후 평균 5.4일이 지난 후에 1.5 T 초전도체 자기공명영상 기기를 이용하여 자기공명영상을 얻었다. 확산강조자기공명영상은 고식적인 b값($1000s/\textrm{mm}^2$)으로 하여 multi-shot echo planar imaging 기법을 이용하여 영상을 획득하였으며 개인용 컴퓨터로 옮겨져 현성확산계수 지도를 얻어 정상부위와 병변부위의 현성확산계수 값을 측정하였다. 자기공명영상에서 병변의 위치와 T1 과 T2 강조영상, 그리고 확산강조자기공명영상에서 나타나는 각각의 신호강도를 알아 보았고, 병변부위와 정상부위에서 측정한 현성확산계수 값을 비교하였다. 결과: T1강조영상에서 6예 중 4예에서 등신호강도를, 2예에서 저신호 강도를 보였고, T2강조 영상에서 6예 모두 고신호강도를 보였다. 또한 확산강조자기공명영상에서 6예 모두 고신호강도를 보였다. 현성확산계수 지도는 6예 전예에서 성공적으로 얻을 수 있었다. 현성확산계수 지도에서 6예 모두 정상과 뚜렷한 차이를 보이는 색조변화를 보였으며, 6예 모두 병변부위의 현성확산계수 값은 정상 부위의 현성확산계수의 값보다 더 낮았으며 통계적으로 유의하였다 (p＜0.05 ). 결론: 척수경색 환자에서 척수병변의 확산강조자기공명영상과 현성확산계수 값의 측정이 가능하였다. 따라서 확산강조자기공명영상은 척수경색의 조기진단과 국재화(localization)에 유용하리라 보여진다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.393-407
• /
• 2023

To assess structural condition in a non-destructive manner, computer vision-based structural health monitoring (SHM) has become a focus. Compared to traditional contact-type sensors, the advantages of computer vision-based measurement systems include lower installation costs and broader measurement areas. In this study, we propose a novel computer vision-based vibration measurement and coarse-to-fine damage assessment method for truss bridges. First, a deep learning model FairMOT is introduced to track the regions of interest (ROIs) that include joints to enhance the automation performance compared with traditional target tracking algorithms. To calculate the displacement of the tracked ROIs accurately, a normalized cross-correlation method is adopted to fine-tune the offset, while the Harris corner matching is utilized to correct the vibration displacement errors caused by the non-parallel between the truss plane and the image plane. Then, based on the advantages of the stochastic damage locating vector (SDLV) and Bayesian inference-based stochastic model updating (BI-SMU), they are combined to achieve the coarse-to-fine localization of the truss bridge's damaged elements. Finally, the severity quantification of the damaged components is performed by the BI-SMU. The experiment results show that the proposed method can accurately recognize the vibration displacement and evaluate the structural damage.

• 한국지능시스템학회논문지
• /
• 제25권5호
• /
• pp.444-450
• /
• 2015

소형 및 저가형 CCD 카메라의 성능은 소형 쿼드콥터의 정밀 추적기능을 구현하는데 있어서 충분한 성능을 갖추고 있지 못하는데 본 연구에서는 덜 정확한 GPS 보다 CCD 카메라를 이용한 보행자와 같은 대상물의 상공에서 강건한 호버링을 유지시키기 위한 방법을 제시하였다. 기존의 연구 대상이었던 고정된 물체가 아닌 보행자를 타깃으로 이용한 UAV의 절대 위치를 추정하는 방법을 제시하였다. 이는 UAV가 산악이나 사람들이 붐비는 공공지역에서 이동할 때 UAV의 절대위치를 인식할 수 있는 방법이 없을 경우 UAV 주변에서 움직이는 물체의 정보를 활용하여 UAV의 절대위치를 보정하는 방법으로 매우 유용하다. 연구를 위해서 보행자의 위치를 알고 있는 것으로 가정하나 실제적인 상황 속에서는 영상매칭을 통하여 그 정보를 수신하는 것으로 해석한다. 본 연구를 위하여 UAV의 위치 추정 불확실성을 정량적으로 나타내었으며, 좌표계 변환을 통한 영상기반의 기하학적 구속 식을 유도하여, 칼만 필터를 적용하여 로봇의 위치를 보정하여 위치 추정 불확실성을 줄일 수 있음을 보였다.

• ETRI Journal
• /
• 제27권3호
• /
• pp.294-303
• /
• 2005

In this paper, a supervised algorithm for the evaluation of geophysical sites using a multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. ML-CNN is a stochastic image processing technique based on template optimization using neighborhood relationships of the pixels. The separation/enhancement and border detection performance of the proposed method is evaluated by various interesting real applications. A genetic algorithm is used in the optimization of CNN templates. The first application is concerned with the separation of potential field data of the Dumluca chromite region, which is one of the rich reserves of Turkey; in this context, the classical approach to the gravity anomaly separation method is one of the main problems in geophysics. The other application is the border detection of archeological ruins of the Hittite Empire in Turkey. The Hittite civilization sites located at the Sivas-Altinyayla region of Turkey are among the most important archeological sites in history, one reason among others being that written documentation was first produced by this civilization.

• 한국군사과학기술학회지
• /
• 제17권6호
• /
• pp.810-820
• /
• 2014

Recently many studies of Radar systems mounted on ground vehicles for autonomous driving, SLAM (Simultaneous localization and mapping) and collision avoidance are reported. In near field, several hits per an object are generated after signal processing of Radar data. Hence, clustering is an essential technique to estimate their shapes and positions precisely. This paper proposes a method of grouping hits in range-doppler domains into clusters which represent each object, according to the pre-defined rules. The rules are based on the perceptual cues to separate hits by object. The morphological connectedness between hits and the characteristics of SNR distribution of hits are adopted as the perceptual cues for clustering. In various simulations for the performance assessment, the proposed method yielded more effective performance than other techniques.

• Smart Structures and Systems
• /
• 제22권3호
• /
• pp.291-302
• /
• 2018

This paper presents a flexibility based method for damage identification from static measurements in beam-type structures. The response of the beam at the Damaged State is decomposed into the response at the Reference State plus the response at an Incremental State, which represents the effect of damage. The damage is localized by detecting slope discontinuities in the deflection of the structure at the Incremental State. A denoising filtering technique is applied to reduce the effect of experimental noise. The extent of the damage is estimated through comparing the experimental flexural stiffness of the damaged cross-sections with the corresponding values provided by analytical models of cracked beams. The paper illustrates the method by showing a numerical example with two cracks and an experimental case study of a simply supported steel beam with one artificially introduced notch type crack at three damage levels. A Digital Image Correlation system was used to accurately measure the deflections of the beam at a dense measurement grid under a set of point loads. The results indicate that the method can successfully detect and quantify a small damage from the experimental data.