• 한국CDE학회논문집
• /
• 제15권2호
• /
• pp.106-114
• /
• 2010

The swept volume, the region of a moving object, is applied in many fields such as valid paths for motions of tools, visualization in robot paths and interference tests for parts assembling or disjointing. The shape of a swept volume depends on an generators computed with normal vectors of an object and velocity vectors of a motion. Although free-from surfaces are widely used to represent geometric models in CAD, computing the generators for a free-form object is a formidable task. Previous approaches exploit the closed form expressions of generators but limited to planer or quadric faces. In this paper, we propose the algorithm to compute swept volumes generated by free-form objects in screw motions. For the algorithm a tracing method is applied to the computation of generators. It considers curvatures of surfaces of an object to increase the computational accuracy. We implemented our algorithm in the CATIA V.5 environment to test the validity of our algorithm and to generate examples.

• 제어로봇시스템학회논문지
• /
• 제15권3호
• /
• pp.300-305
• /
• 2009

This paper describes the intelligent robot's hand with three-axis finger force sensors for an intelligent robot. In order to grasp an unknown object safely, it should measure the mass of the object, and determine the grasping force using the mass, then control the robot's fingers with the grasping force. In this paper, the intelligent robot's hand for an intelligent robot was developed. First, the three-axis finger force sensors were designed and manufactured, second, the intelligent robot's hand with three-axis finger force sensors were designed and fabricated, third, the high-speed control system was designed and manufactured using DSP( digital signal processor), finally, the characteristic test to grasp an unknown object safely was carried out. It was confirmed that the developed intelligent robot's hand could grasp an unknown object safely.

• Journal of Information Processing Systems
• /
• 제7권3호
• /
• pp.519-530
• /
• 2011

A Snake is an active contour for representing object contours. Traditional snake algorithms are often used to represent the contour of a single object. However, if there is more than one object in the image, the snake model must be adaptive to determine the corresponding contour of each object. Also, the previous initialized snake contours risk getting the wrong results when tracking multiple objects in successive frames due to the weak topology changes. To overcome this problem, in this paper, we present a new snake method for efficiently tracking contours of multiple objects. Our proposed algorithm can provide a straightforward approach for snake contour rapid splitting and connection, which usually cannot be gracefully handled by traditional snakes. Experimental results of various test sequence images with multiple objects have shown good performance, which proves that the proposed method is both effective and accurate.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.126-133
• /
• 2017

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

• 한국컴퓨터정보학회논문지
• /
• 제12권5호
• /
• pp.163-170
• /
• 2007

본 논문에서는 압축된 비디오 신호의 움직임 벡터 및 DCT 계수로부터 움직임 객체를 추출하는 새로운 기법을 제시한다. 움직임 객체 추출에 관한 기술은 내용 기반 검색, 타겟트래킹 등 다양한 분야에서 필요로 한다. 움직임 객체 블록의 추출을 위해서 움직임 벡터와 DCT계수 가 선택적으로 이용되는 2-모드 방식의 기법이 제시된다. 또한, 제시된 기법은 DCT 변환 영역상의 계수들만을 이용하기 때문에 완전히 복호화된 정보를 필요로 하지 않는 장점을 갖는다. 제시된 기법을 바탕으로 몇 가지 테스터 영상에 대해 모의 실험을 실시한 결과 양호한 결과를 얻을 수 있었다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2005년도 춘계학술대회 논문집
• /
• pp.106-111
• /
• 2005

LCC(Launch Control Center) in NARO Space Center perform a data monitoring and control through the interface to the external system of launch vehicle. Launch Control function needs a high reliability and processing speed. Hence, LCC's remote control system configure a real time system. An important role of the Simulation system is discovering a risk element and minimize it When developing a launch control system. Also, secure a development technique to solve the risks. Launch Vehicle simulator is composed of various component at characteristic of the Launch Vehicle. To be like this each function component the developer will be able to develop easily in order, it using the LabVIEW which is a Graphical Program and it programs, The LabVIEW GOOP(Graphical Object-orinted Programming) which supports an Object-orinted programming it uses with the Component it develops will have a strong point which reusability and a unit test, maintenance, size of program and individual developments.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.25-33
• /
• 2019

In this paper, we propose an intelligent CCTV technology which is applied to a recent attracted attention real-time object detection technology in a disaster alarm system. Natural disasters are rapidly increasing due to climate change (global warming). Various disaster alarm systems have been developed and operated to solve this problem. In this paper, we detect object through Neuron Network algorithm and test the difference from existing SVM classifier. Experimental results show that the proposed algorithm overcomes the limitations of existing object detection techniques and achieves higher detection performance by about 15%.

• 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.

• 자동차안전학회지
• /
• 제12권4호
• /
• pp.23-30
• /
• 2020

Recently, self-driving research has been actively studied in various institutions. Accurate recognition is important because information about surrounding objects is needed for safe autonomous driving. This study mainly deals with the signal processing of LiDAR among sensors for object recognition. LiDAR is a sensor that is widely used for high recognition accuracy. First, we clustered and tracked objects by predicting relative position and speed of objects. The characteristic points of all objects were extracted using point cloud data of each objects through proposed algorithm. The Classification between vehicle and pedestrians is estimated using number of characteristic points and distances among characteristic points. The algorithm for classifying cars and pedestrians was implemented and verified using test vehicle equipped with LiDAR sensors. The accuracy of proposed object classification algorithm was about 97%. The classification accuracy was improved by about 13.5% compared with deep learning based algorithm.

• Journal of Advanced Marine Engineering and Technology
• /
• 제34권6호
• /
• pp.816-824
• /
• 2010

본 논문에서는 쓰레기 이송관로내의 물체에 작용하는 힘을 분석하고 그 물체의 운동방정식 확립하였다. 그 운동방정식은 1계 비선형 미분방정식이 되며 이것의 일반해를 이용하면 쓰레기 이송관로내 물체의 속도를 구할 수가 있다. 물체의 속도는 엘보우와 같은 쓰레기 이송관로의 곡선부에서 내벽의 충돌속도가 되므로 충돌시 물체의 운동에너지를 계산할 수 있고, 따라서 필요한 내벽의 충격강도를 알 수가 있다. 하나의 예로써 쓰레기 이송관로내 공기의 속도가 30m/sec일 때 물체의 속도를 계산하여 그래프로써 나타내었으며, 이것으로부터 물체가 내벽에 충돌할 때의 운동에너지를 계산할 수 있도록 하였다. 또한 용융주조 현무암 튜브를 철강파이프 내면에 보호벽으로 씌운 복합재료 파이프에 추를 자유낙하시켜 충격을 주는 방식으로 충격시험을 한 결과를 제시하였으며, 그 결과에 의하면 용융 주조 현무암 튜브는 쓰레기 이송관로의 내면 보호벽으로 충분한 충격강도를 가지는 것이 판명되었다.