• IEIE Transactions on Smart Processing and Computing
• /
• 제5권6호
• /
• pp.375-382
• /
• 2016

This paper realizes control of the motion of a swimming robot fish in order to implement an underwater robot fish aquarium. And it implements positional control of a two-axis trajectory path of the robot fish in the aquarium. The performance of the robot was verified though certified field tests. It provided excellent performance in driving force, durability, and water resistance in experimental results. It can control robot motion, that is, it recognizes an object by using an optical flow object-detecting algorithm, which uses a video camera rather than image-detecting sensors inside the robot fish. It is possible to find the robot's position and control the motion of the robot fish using a radio frequency (RF) modem controlled via personal computer. This paper proposes realization of robot fish motion-tracking control using the optical flow object-detecting algorithm. It was verified via performance tests of lead-lag action control of robot fish in the aquarium.

• 반도체디스플레이기술학회지
• /
• 제14권3호
• /
• pp.67-72
• /
• 2015

This paper proposes an object tracking system based on keypoints using homography in mobile environments. The proposed system is based on markerless tracking, and there are four modules which are recognition, tracking, detecting and learning module. Recognition module detects and identifies an object to be matched on current frame correspond to the database using LSH through SURF, and then this module generates a standard object information. Tracking module tracks an object using homography information that generate by being matched on the learned object keypoints to the current object keypoints. Then update the window included the object for defining object's pose. Detecting module finds out the object based on having the best possible knowledge available among the learned objects information, when the system fails to track. The experimental results show that the proposed system is able to recognize and track objects with updating object's pose for the use of mobile platform.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.227-232
• /
• 2018

In this paper, we propose a faster object detection and tracking method using Deep Learning, UAV(unmanned aerial vehicle), Kalman filter and YOLO(You Only Look Once)v3 algorithms. The performance of the object tracking system is decided by the performance and the accuracy of object detecting and tracking algorithms. So we applied to the YOLOv3 algorithm which is the best detection algorithm now at our proposed detecting system and also used the Kalman Filter algorithm that uses a variable detection area as the tracking system. In the experiment result, we could find the proposed system is an excellent result more than a fixed area detection system.

• 반도체디스플레이기술학회지
• /
• 제14권3호
• /
• pp.73-77
• /
• 2015

This paper proposes an object tracking system according to reliability assessment of learning in mobile environments. The proposed system is based on markerless tracking, and there are four modules which are recognition, tracking, detecting and learning module. Recognition module detects and identifies an object to be matched on current frame correspond to the database using LSH through SURF, and then this module generates a standard object information that has the best reliability of learning. The standard object information is used for evaluating and learning the object that is successful tracking in tracking module. Detecting module finds out the object based on having the best possible knowledge available among the learned objects information, when the system fails to track. The experimental results show that the proposed system is able to recognize and track the reliable objects with reliability assessment of learning for the use of mobile platform.

• International Journal of Contents
• /
• 제2권1호
• /
• pp.5-8
• /
• 2006

This paper describes a new mechanism of detecting object of interest from a noisy image, without using any a-priori knowledge about the target. It employs a parallel set of filters inspired upon biological findings of mammalian vision. In our proposed system, several basic features are extracted directly from original input visual stimuli, and these features are integrated based on their local competitive relations and statistical information. Through integration process, unnecessary features for detecting the target are spontaneously decreased, while useful features are enhanced. Experiments have been performed on a set of computer generated and real images corrupted with noise.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1996년도 추계학술대회 논문집
• /
• pp.101-104
• /
• 1996

A new detecting system for moving objects of coastal region has been designed by directional antenna and driving circuits. The designed system has been investigated by CAD for linear and planar antenna arrays of various radiating elements for antenna simulations and by P-spice of device simulations. For detecting the displacement of moving objects, we constructed four wideband dipole antenna, diode switching circuit, mixer, filter and amplifier. The results of antenna receiver were shown a possibility of distance measuring system through phase difference of radiation patterns in antenna simulation

• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.46-50
• /
• 2016

Recently, Depending on expectancy effect and ripple effect of augmented reality, the convergence between augmented reality and culture & arts are being actively conducted. This paper proposes a learning method for effective object tracking in 3D storytelling augmented reality in cultural properties. The proposed system is based on marker-less tracking, and there are four modules that are recognition, tracking, detecting and learning module. Recognition module is composed of SURF and LSH, and then this module generates standard object information. Tracking module tracks an object using object tracking based on reliability. This information is stored in Learning module along with learned time information. Detecting module finds out the object based on having the best possible knowledge available among the learned objects information, when the system fails to track. Also, it proposes a method for robustly implementing a 3D storytelling augmented reality in cultural properties in the future.

• 디지털콘텐츠학회 논문지
• /
• 제14권4호
• /
• pp.455-462
• /
• 2013

CCTV를 이용하여 획득한 영상 내에서 다중 객체의 위험한 행위를 판단하여 사전에 미리 경고 및 긴급대책을 세워주는 감지 시스템을 제안한다. 위험한 행위의 판단여부를 위해 관심지역 및 관심지역 내에 위험지역을 설정한 후, 위험 행동 객체를 검출하여 객체의 위험지역 침범 범위에 따라 안전, 경고, 긴급 등의 위험도를 판단한다. 특히 본 연구는 위험 행동 중 교량에서 투신하는 행위를 감지하는 것을 목표로 하며 기존의 연구에서 단일객체의 행동검출에만 제한했던 연구를 여러 보행자 속에서 투신 행동하는 객체를 감지하는 것까지 확대하여 구현한다. 한 객체의 위험지역 침범의 정도에 따라 안전, 경고 및 긴급 상태로 분류하고 상황에 따라 긴급 상태로 판단되면 통합관제 센터에 즉시 알려 위험행위를 사전에 예방 할 수 있도록 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.5-7
• /
• 1996

We propose a triangulation method based on stereo vision angles. We setup stereo vision systems which extract the depth information to a moving object by detecting a moving object using difference image method and obtaining the depth information by the triangulation method based on stereo vision angles. The feature point of a moving object is used the geometrical center of the moving object, and the proposed vision system has the accuracy of 0.2mm in the range of 400mm.

• 한국지능시스템학회논문지
• /
• 제19권5호
• /
• pp.609-614
• /
• 2009

본 논문에서는 내부 운전자에게 위협이 될 수 있는 실시간 금속 물체 탐지 시스템을 제안한다. 제안된 시스템은 퍼지 이론를 이용하여 금속 물체를 탐지할 수 있는 색상 필터를 설계하는 알고리즘과 차량안의 특정 영역 내에서 FSCF(Fuzzy Skin Color Filter)를 이용하여 운전자의 얼굴 영역을 탐지하는 알고리즘을 제안한다. 또한, 탐지된 동승자의 손 영역을 기점으로 색상기반 원형탐색 기법을 사용하여 최종적으로 위협을 가할 수 있는 금속물체의 후보영역을 설정하고, 제안된 금속 물체 필터를 적용하여 최종적인 금속물체영역을 탐지 한다. 마지막으로 제안된 방법은 여러 실험을 통해 내부 운전자 보호를 위한 금속물체 탐지 시스템의 우수성을 증명한다.