• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.834-837
• /
• 2009

Augmented Reality (AR) is a useful technology for various industrial systems. This paper suggests a new playground system which uses markerless AR technology. We developed a virtual playground system that can learn physics and kinematics from the physical play of people. The virtual playground is a space in which real scenes and CG are mixed. As for the CG objects, physics of the real world is used. This is realized by a physics engine. Therefore it is necessary to analyze information from cameras, so that CG reflects the real world. Various games options are possible using real world images and physics simulation in the virtual playground. We think that the system is effective for education. Because CG behaves according to physics simulation, users can learn physics and kinematics from the system. We think that the system can take its place in the field of education through entertainment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1194-1208
• /
• 2010

As visual surveillance systems gain wider usage in a variety of fields, it is important that they are capable of interpreting scenes automatically, also known as "human motion analysis" (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method that is based on the idea that human beings tend to exhibit erratic motion patterns during abnormal situations. Limb movements are characterized using the statistics of angular and linear displacements. In addition, the method is enhanced via the use of the entropy of the Fourier spectrum to measure the randomness of subject's motions. Various experiments have been conducted and the results indicate that the proposed method has very high classification accuracy in identifying anomalous behavior.

• Journal of Biosystems Engineering
• /
• 제28권6호
• /
• pp.517-524
• /
• 2003

생물생산에 요구되는 다양한 작업들을 생력화하기 위한 연구 개발 노력이 전세계적으로 활발히 추진되어 왔다. 이러한 연구 개발은 주로 노동집약적인 작업, 고부가가치 농산물을 생산하기 위한 작업 그리고 작업자에 유해한 또는 가혹한 환경하의 작업 등에 주안점을 두고 추진되고 있다. 하지만, 생물생산 분야의 생력화를 추진하는데 있어서 다양한 작업성과 강건성이라는 작업성능 측면에서의 기술적인 문제와 고가의 시스템 및 설비 비용에 따른 경제성 문제가 항상 걸림돌이 되어 왔다. 본 연구에서는 언급한 문제점들 외에 기계가동률, 유지보수 등 생물생산분야의 생력화에 있어 내재되고 있는 문제점들을 효율적으로 해결하기 위하여 무선 원격로봇 시스템에 의거한 새로운 생력화 개념을 제안하였다. 새로운 개념의 생력화는 주어진 작업을 성공적으로 수행하기 위하여 작업자(농민), 컴퓨터 그리고 로봇을 위시한 자동화 작업설비를 대상으로 상대적으로 수월성을 갖는 기능을 중심으로 역할을 분담하는 것이다. 또한 시설재배에 요구되는 전정, 관수, 방제, 제초, 수확, 운반 등과 같은 다양한 작업들을 노동 투하정도와 기능적 유사성 측면을 고려하여 일관적으로 작업을 생력화하는 방안을 제시하였고 제안한 개념을 구현할 수 있는 시스템을 개발하였다. 대상 작목으로는 중량으로 인하여 비교적 취급이 어려운 수박을 선택하였다. 개발 시스템은 크게 무선원격 모니터링 및 작업제어 모듈, 무선원격 영상 획득 및 데이터 송수신 모듈, 4자유도 직교좌표형 로봇 암을 장착한 갠트리 장치부, 교체가 가능한 모듈형 선단 작업장치, 수박 운반 적재모듈의 5개 하드웨어 모듈로 구성하였다. 개발한 시스템은 그래픽 사용자 인터페이스를 통하여 터치 스크린 모니터를 이용하여 작업자와 컴퓨터간의 인터페이스를 구현하였으며 무선 원격데이타 송수신과 분산 제어기를 이용하여 작업자와 컴퓨터 그리고 로봇 작업기간의 인터페이스와 시스템 제어를 구현하였다. 개발 시스템의 성능을 시험하여 결과를 제시하였으며 본 논문에서 제안한 새로운 개념의 생력화 시스템은 생물생산분야의 생력화 방향을 새롭게 제시하는 실질적이고 실현 가능한 시스템이라는 것을 보여주었다.

• 대한기계학회논문집A
• /
• 제35권7호
• /
• pp.737-743
• /
• 2011

서비스 로봇은 비전 카메라, 초음파 센서, 레이저 스캐너, 마이크로폰 등과 같은 다양한 센서를 장착하고 있다. 이들 센서들은 이들 각각의 고유한 기능을 가지고 있기도 하지만, 몇몇을 조합하여 사용함으로써 더욱 복잡한 기능을 수행할 수 있다. 음성영상 융합은 서로가 서로를 상호보완 해주는 대표적이면서도 강력한 조합이다. 사람의 경우에 있어서도, 일상생활에 있어 주로 시각과 청각 정보에 의존한다. 본 발표에서는, 음성영상 융합에 관한 두 가지 연구를 소개한다. 하나는 음원 방향 검지 성능의 향상에 관한 것이고, 나머지 하나는 음원 방향 검지와 얼굴 검출을 이용한 로봇 어텐션에 관한 것이다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.273-276
• /
• 2002

Pulse-Coupled Neural Network (PCNN), which can explain the synchronous burst of neurons in a cat visual cortex, is a fundamental model for the biomimetic vision. The PCNN is a kind of pulse coded neural network models. In order to get deep understanding of the visual information Processing, it is important to simulate the visual system through such biologically plausible neural network model. In this paper, we construct the motion detection model based on the PCNN with the receptive field models of neurons in the lateral geniculate nucleus and the primary visual cortex. Then it is shown that this motion detection model can detect the movements and the direction of motion effectively.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.177-181
• /
• 2001

This paper presents an strategy algorithm of a soccer robot. We simply classified strategy of soccer robot as attack and defense. We use DC-motor in our Soccer Robot. We use the vision system made by MIRO team of Kaist and Soty team for image processing. Host computer is made by Pentium III. The RF module is used for the communication between each robot and the host computer. Fuzzy logic is applied to the path planning of our robot. We improve strategy algorithm of soccer robot. Here we explain improvement of strategy algorithm and fault of the our soccer robot system.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1015-1033
• /
• 2020

With promising results and enormous capability, deep learning technology has attracted more and more attention to both theoretical research and applications for a variety of image processing and computer vision tasks. In this paper, we investigate 32 research contributions that apply deep learning techniques to the agriculture domain. Different types of deep neural network architectures in agriculture are surveyed and the current state-of-the-art methods are summarized. This paper ends with a discussion of the advantages and disadvantages of deep learning and future research topics. The survey shows that deep learning-based research has superior performance in terms of accuracy, which is beyond the standard machine learning techniques nowadays.

• 한국정보통신학회논문지
• /
• 제24권1호
• /
• pp.141-144
• /
• 2020

Convolutional neural networks (CNNs) show high performance in computer vision tasks including object detection, but a lot of weight storage and computation is required. In this paper, a pruning scheme is applied to CNNs for object detection, which can remove much amount of weights with a negligible performance degradation. Contrary to the previous ones, the pruning scheme applied in this paper considers the base accelerator architecture. With the consideration, the pruned CNNs can be efficiently performed on an ASIC or FPGA accelerator. Even with the constrained pruning, the resulting CNN shows a negligible degradation of detection performance, less-than-1% point degradation of mAP on VOD0712 test set. With the proposed scheme, CNNs can be applied to objection dtection efficiently.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.226-233
• /
• 2022

Video surveillance is widely used in security surveillance, military navigation, intelligent transportation, etc. Its main research fields are pattern recognition, computer vision and artificial intelligence. This article uses OpenCV to detect and track vehicles, and monitors by establishing an adaptive model on a stationary background. Compared with traditional vehicle detection, it not only has the advantages of low price, convenient installation and maintenance, and wide monitoring range, but also can be used on the road. The intelligent analysis and processing of the scene image using CAMSHIFT tracking algorithm can collect all kinds of traffic flow parameters (including the number of vehicles in a period of time) and the specific position of vehicles at the same time, so as to solve the vehicle offset. It is reliable in operation and has high practical value.

• 한국정보통신학회논문지
• /
• 제26권2호
• /
• pp.325-328
• /
• 2022

A convolutional neural network(CNN) is widely used in the computer vision tasks, but its computing power requirement needs a design of a special circuit. Most of the computations in a CNN can be implemented efficiently in a digital circuit, but the SoftMax layer has operations unsuitable for circuit implementation, which are exponential and logarithmic functions. This paper proposes a new method to integrate the exponential and logarithmic tables of the conventional circuits into a single table. The proposed structure accesses a look-up table (LUT) only with a few maximum values, and the LUT has the result value directly. Our proposed method significantly reduces the space complexity of the SoftMax layer circuit implementation. But our resulting circuit is comparable to the original baseline with small degradation in precision.