• Ocean Systems Engineering
• /
• 제10권4호
• /
• pp.415-434
• /
• 2020

Detecting objects is important for the safe operation of ships, and enables collision avoidance, risk detection, and autonomous sailing. This study proposes a ship detection method from images and videos taken at sea using one of the state-of-the-art deep neural network-based object detection algorithms. A deep learning model is trained using a public maritime dataset, and results show it can detect all types of floating objects and classify them into ten specific classes that include a ship, speedboat, and buoy. The proposed deep learning model is compared to a universal trained model that detects and classifies objects into general classes, such as a person, dog, car, and boat, and results show that the proposed model outperforms the other in the detection of maritime objects. Different deep neural network structures are then compared to obtain the best detection performance. The proposed model also shows a real-time detection speed of approximately 30 frames per second. Hence, it is expected that the proposed model can be used to detect maritime objects and reduce risks while at sea.

• 융합신호처리학회논문지
• /
• 제11권2호
• /
• pp.143-150
• /
• 2010

무마커 증강현실 시스템은 실내나 옥외 환경에서 자연 물체를 인식하고 매칭하는 기능이 필수적이다. 본 논문에서는 비주얼 서술자와 코드북을 사용하여 특징을 추출하고 자연 물체를 인식하는 기법을 제안한다. 증강현실 응용은 동작 속도와 실시간 성능에 민감하기 때문에, 본 연구에서는 멀티 클래스의 자연 물체 인식에 초점을 두었으며 분류와 특징 추출 시간을 줄이는 것을 포함한다. 훈련과 테스트 과정에서 자연 물체로부터 특징을 추출하기 위해 SIFT와 SURF을 각각 사용하고 그들의 성능을 비교한다. 또한, 클러스터링 알고리즘을 이용하여 다차원의 특징 벡터들로부터 비주얼 코드북을 생성하고 나이브 베이즈 분류기를 이용해 물체를 인식한다.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권6호
• /
• pp.897-906
• /
• 2017

프로젝션 맵핑(공간증강현실)은 현실세계에서 다양한 가상의 환영(幻影)을 만들어내는 것으로 최근에 많은 분야에 사용되고 있다. 기존의 프로젝션 맵핑에서는 사용자와의 자연스러운 상호작용으로서 접히거나 구부러지는 것 과 같은 유연한 물체의 기하학적인 변형 속성(예: 용지)의 움직임을 고려하지 않았다. 또한, 정적 물체에 대한 프로젝션 맵핑에 대한 많은 연구가 있었지만, 유연한 타깃의 움직임을 추적하고 사용자와의 상호작용 측면에서 모양이 변형된 물체에 맵핑을 정확히 하는 다이내믹 프로젝션 맵핑은 여전히 도전해야할 연구 분야이다. 따라서 본 논문에서는 Unity3D와 ARToolkit을 이용한 실험을 통해 단단하지 않은 물체에 대한 견실한 추적과 정확한 맵핑 방법을 제안한다. 제안하는 방법은 큐빅 베지어 곡면 형성, 움직임 변형 값 렌더링 과정, 멀티플 마커 인식과 트래킹 과정, 실시간 웹캠 지속 촬영의 4가지 실험 단계로 구성된다. 사용자는 물체에 변형을 주기 위해 직접 접고, 휘고, 구부리고 비틀 수 있다. 제안 방법은 세 가지 긍정적인 결과를 도출할 수 있다. 첫째, 물체의 형태가 강하게 변형되어 있어도 감지 가능하다. 둘째, 사용자가 직접 물체에 변형을 주는 과정에서 물체의 일부분을 차단하고 있을 때의 Occlusion오류를 줄일 수 있어 정확한 트래킹을 할 수 있다. 셋째, 제안 방법의 견실하고 정확함은 빠른 속도로 물체의 움직임을 감지하게 하므로 실시간으로 결과 값을 물체에 투영할 수 있다.

• 전자공학회논문지C
• /
• 제34C권10호
• /
• pp.67-75
• /
• 1997

A design for a system to perform rapid recognition of three dimensional objects is presented, focusing on efficient indexing. In order to retrieve the best matched models without exploring all possible object matches, we have employed a bayesian framework. A decision-theoretic measure of the discriminatory power of a feature for a model object is defined in terms of posterior probability. Detectability of a featrue defined as a function of the feature itselt, viewpoint, sensor charcteristics, nd the feature detection algorithm(s) is also considered in the computation of discribminatory power. In order to speed up the indexing or selection of correct objects, we generate and verify the object hypotheses for rfeatures detected in a scene in the order of the discriminatory power of these features for model objects.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.308-313
• /
• 2015

This paper describes a technique for complete identification of a two-dimensional scattering object and multiple objects immersed in air using microwaves where the scatterers are assumed to be a homogenous dielectric medium. The employed technique consists of initially retrieving the shape and position of the scattering object using a linear sampling method and then determining the electric permittivity and conductivity of the scatterer using adjoint sensitivity analysis. Incident waves are assumed to be TM (Transverse Magnetic) plane waves. This inversion algorithm results in high computational speed and efficiency, and it can be generalized for any scatterer structure. Also, this method is robust with respect to noise. The numerical results clearly show that this hybrid approach provides accurate reconstructions of various objects.

• 한국CDE학회논문집
• /
• 제5권1호
• /
• pp.95-101
• /
• 2000

For last two decades numerous automatic mesh generation algorithms for various two dimensional objects have been introduced continuously and among them triangular mesh generation schemes have been majority because of efficiency and controllability. In our study, an existing triangular mesh generation algorithm developed by Lo is totally modified to more improve node distribution, element shape, and objects shape independency. ft is composed of node generation part and element generation part. In order to find a suitable node position within geometry, the suggested algorithm searches desirable positions of points within boundary and optimizes node position to generate comparatively well-shaped elements. More over, the suggested algorithm handles various complex two dimensional objects and its meshing speed shows superiority to those of the existing triangulation mesh generation algorithms. It is fully automated in a sense of constructing object boundary and hence can be directly used as an independent meshing software.

• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• pp.109-116
• /
• 2023

This paper presents a network-based automation system for the detection of metallic objects in food and livestock. A metal detector is a core equipment used for the inspection required by HACCP. Since the existing metal detectors are manufactured as a single-body equipment, it is difficult to take into account various user requirements for the system. In order to overcome the drawback, this study presents a network-based automation system for metal detector utilizing an industrial fieldbus and modular components. The proposed system can effectively consider the various customer requirements and control schemes. The proposed system can also achieve the improvement in speed and success rate of detecting metallic objects. The effectiveness of the proposed system is demonstrated through a various experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2179-2182
• /
• 2005

Recently, optical 3D scanners are frequently used for inspection of parts, assembly and manufacturing tooling. One of the advantages is being able to measure a large area fast and accurately. Owing to recent advances in high-resolution image sensing technology, high power illumination technology, and high speed microprocessors, the accuracy and resolution of optical 3D scanners are being improved rapidly. In order to measure the entire geometry of objects, multiple scans have to be performed in various setups by moving either the objects or the scanner. This paper introduces novel methods to measure the entire geometry of objects by automatically changing the setups and then aligning the scanned data in a single coordinate system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1097-1100
• /
• 1998

In this paper, the PLL(Phase-Locked Loops) for low voltage and high speed operation is described. In other to obtaining above objects, new CMOS circuit technologies have been used in the each block circuit of PLL. It operates with a lock range from 110 up to 700 MHz and has a peak to peak jitter of 50 ps at operating frequency of 250 MHz. It was fabricated in a $0.6\mu\textrm{m}$ CMOS technology and dissipated 45 mW from a single 3.3V.

• International journal of advanced smart convergence
• /
• 제2권1호
• /
• pp.32-35
• /
• 2013

In this paper we proposed a PTZ camera system which automatically detect and track moving objects in the image. Once a moving object is detected the PTZ camera traces it in real-time. We proposed the control system which does not depend on camera focusing functionality but uses the object's center, moving direction, distance and speed. We implemented the system with the TI DM6446 DSP chip. The experimental result shows that the system has excellent performance for high speed vehicles.