• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1917-1920
• /
• 2003

Automatic tracking of a moving object such as a person is a demanding technique especially in surveillance. This paper describes an experimental system for tracking a moving object on the ground by using a visually controlled aerial robot. A blimp is used as the aerial robot in the proposed system because of its locality in motion and its silent nature. The developed blimp is equipped with a camera for taking downward images and four rotors for controlling the progression. Once a camera takes an image of a specified moving object on the ground, the blimp is controlled so that it follows the object by the employment of the visual information. Experimental results show satisfactory performance of the system. Advantages of the present system include that images from the air often enable us to avoid occlusion among objects on the ground and that blimp’s progression is much less restricted in the air than, e.g., a mobile robot running on the ground.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.145-156
• /
• 2022

Nowadays, the complexity of object tracking models among hardware applications has become a more in-demand duty to complete in various indeterminable environment tracking situations with multifunctional algorithm skills. In this paper, we propose a virtual city environment using AirSim (Aerial Informatics and Robotics Simulation - AirSim, CityEnvironment) and use the DQN (Deep Q-Learning) model of deep reinforcement learning model in the virtual environment. The proposed object tracking DQN network observes the environment using a deep reinforcement learning model that receives continuous images taken by a virtual environment simulation system as input to control the operation of a virtual drone. The deep reinforcement learning model is pre-trained using various existing continuous image sets. Since the existing various continuous image sets are image data of real environments and objects, it is implemented in 3D to track virtual environments and moving objects in them.

• International Journal of Computer Science & Network Security
• /
• 제21권5호
• /
• pp.31-34
• /
• 2021

The article considers the possibilities of increasing the accuracy of estimates of the parameters of the trajectory of the target with the provision of a given probability of stable support of the air object, in particular, during its maneuver. The aim of the work is to develop a filtration algorithm that provides a given probability of stable tracking of the air object by determining the regular components of filtration errors, in particular, when maneuvering the air object, and their compensation with appropriate correction of filter parameters and estimates of air object trajectory parameters.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.163-169
• /
• 2021

In this paper, we implemented a deep learning-based automatic object tracking and handy motion control drone system and analyzed the performance of the proposed system. The drone system automatically detects and tracks targets by analyzing images obtained from the drone's camera using deep learning algorithms, consisting of the YOLO, the MobileNet, and the deepSORT. Such deep learning-based detection and tracking algorithms have both higher target detection accuracy and processing speed than the conventional color-based algorithm, the CAMShift. In addition, in order to facilitate the drone control by hand from the ground control station, we classified handy motions and generated flight control commands through motion recognition using the YOLO algorithm. It was confirmed that such a deep learning-based target tracking and drone handy motion control system stably track the target and can easily control the drone.

• 한국디지털정책학회:학술대회논문집
• /
• 한국디지털정책학회 2004년도 International Conference on Digital Policy & Management
• /
• pp.185-202
• /
• 2004

Recent development in wireless computing and GPS technology cause the active development in the application system of location information in real-time environment such as transportation vehicle management, air traffic control and location based system. Especially, study about vehicle location tracking system, which monitors the vehicle's position in a control center, is appeared to be a representative application system. However, the current vehicle location tracking system can not provide vehicle position information that is not stored in a database at a specific time to users. We designed a vehicle location tracking system that could track vehicle location using mobile interface such as PDA. The proposed system consist of a vehicle location retrieving server and a mobile interface. It is provide not only the moving vehicle's current location but also the position at a past and future time which is not stored in database for users.

• 전기학회논문지
• /
• 제66권8호
• /
• pp.1250-1256
• /
• 2017

In this research, a high-performance ultrasonic positioning system is proposed to track the positions of an indoor mobile object. Composed of an ultrasonic sender (mobile object) and a receiver (anchor), the system employs three ultrasonic time-off-flights (TOFs) and trilateration to estimate the positions of the object with an accuracy of sub-centimeter. On the other hand, because ultrasonic waves are interfered by temperature, wind and various obstacles obstructing the propagation while propagating in air, ultrasonic pulse debounce technique and Kalman filter were applied to TOF and position calculation, respectively, to compensate for the interference and to obtain more accurate moving object position. To perform tasks in real time, ultrasonic signals are processed full-digitally with a Zynq SoC, and as a software design tool, Vivado IDE(integrated design environment) is used to design the whole signal processing system in hierarchical block diagrams. And, a hardware/software co-design is implemented, where the digital circuit portion is designed in the Zynq's fpga and the software portion is c-coded in the Zynq's processors by using the baremetal multiprocessing scheme in which the c-codes are distributed to dual-core processors, cpu0 and cpu1. To verify the usefulness of the proposed system, experiments were performed and the results were analyzed, and it was confirmed that the moving object could be tracked with accuracy of sub-cm.

• 한국컴퓨터그래픽스학회논문지
• /
• 제25권5호
• /
• pp.11-20
• /
• 2019

딥러닝 기술의 발전으로 가상 현실이나 증강 현실 응용에서 사용하기 적절한 사용자 친화적 인터페이스에 관한 연구가 활발히 이뤄지고 있다. 본 논문은 사용자의 손을 이용한 인터페이스를 지원하기 위하여 손 끝 좌표를 추적하여 가상의 객체를 선택하거나, 공중에 글씨나 그림을 작성하는 행위가 가능하도록 딥러닝 기반 손 끝 객체 탐지 방법을 제안한다. 입력 영상에서 Grad-CAM으로 해당 손 끝 객체의 대략적인 부분을 잘라낸 후, 잘라낸 영상에 대하여 Atrous Convolution을 이용한 합성곱 신경망을 수행하여 손 끝의 위치를 찾는다. 본 방법은 객체의 주석 전처리 과정을 별도로 요구하지 않으면서 기존 객체 탐지 알고리즘 보다 간단하고 구현하기에 쉽다. 본 방법을 검증하기 위하여 Air-Writing 응용을 구현한 결과 평균 81%의 인식률과 76 ms 속도로 허공에서 지연 시간 없이 부드럽게 글씨 작성이 가능하여 실시간으로 활용 가능함을 알 수 있었다.

• 대한인간공학회지
• /
• 제16권2호
• /
• pp.83-100
• /
• 1997

The Human Sensory Feedback Laboratory, park of the Armstrong Laboratory at Wright-Patterson Air Force Base, Ohio, is involved in the development and evaluation of systems that provide sensory feedback to the human operator in telerobotic and virtual environment applications. Specific projects underway in the laboratory are primarily concerned with the information provided by force and vibrotactile feedback to the operator in dextrous manipulation tasks. Four specific research projects are described in the present report. These include : 1) experiments evaluating a 30-element fingertip display, which employs a titanium-nickel shape memory alloy actuator design to provide vibrotactile feedback about object shape and surface texture ; 2) of a fingertip force-feedback display for 3-dimensional information about object shape and suface texture ; 3) use of a force- feedback joystic to provide "force tunnel" information in pilot pursuit tracking tasks ; and 4) evaluations of a 7 degree-of-freedom exoskeleton used to control a robotic arm. Both basic and applied research questions are discussed.

• 정보처리학회논문지D
• /
• 제9D권6호
• /
• pp.1071-1082
• /
• 2002

무선 컴퓨팅 기술 및 이동 객체의 위치를 정확하게 추적할 수 있는 GPS 기술의 발달로 인하여 물류 차량 관리, 항공 교통 통제, 위치 기반 서비스 등과 같은 실시간 환경의 위치 정보 응용 시스템의 개발이 활발해지고 있다. 특히, 차량의 위치를 관제 센터에서 실시간으로 파악하는 차량 위치 추적 시스템에 관한 연구가 대표적인 응용 시스템으로 등장하였다. 그런데 기존의 차량 위치 추적 시스템은 데이터베이스에 저장되지 않은 특정 시간의 차량 위치 정보를 사용자에게 제공하지 못하는 문제점을 갖는다. 따라서 이 논문에서는 PDA와 같은 모바일 인터페이스를 통하여 실시간으로 차량의 위치 추적이 가능한 시스템을 설계한다. 제안 시스템은 차량 위치 검색 서버와 모바일 인터페이스로 구성되며, 이동 차량의 현재 위치뿐만 아니라 데이터베이스에 저장되지 않은 과거 및 미래 위치 정보까지 사용자에게 제공하는 장점을 갖는다.

• 한국항행학회논문지
• /
• 제27권3호
• /
• pp.306-313
• /
• 2023

실사 및 그래픽 기반 가상현실 콘텐츠는 360도 영상을 기반으로 하며, 시청자의 의도나 자동 추천 기능을 통한 뷰포트 추출이 필수적이다. 본 논문은 360도 영상에서 다중 객체 추적 기반의 뷰포트 추출 시스템을 설계하고, 다중 뷰포트 추출에 필요한 병렬화된 연산 구조를 제안한다. 360도 영상에서 뷰포트 추출 과정을 ERP 좌표의 3D 구 표면 좌표 변환과 3D 구 표면 좌표의 뷰포트 내 2D 좌표 변환 과정을 순서대로 픽셀 단위의 스레드로 구성하여 연산을 병렬화하였다. 제안 구조는 항공 360도 영상 시퀀스들에 대하여 최대 30개의 뷰포트 추출 과정에 대한 연산 시간이 평가되었으며, 뷰포트 수에 정비례하는 CPU 기반 연산 시간에 비해 최대 5240배 가속화됨을 확인하였다. ERP 프레임 I/O 시간을 줄일 수 있는 고속의 I/O나 메모리 버퍼를 사용 시 뷰포트 추출 시간을 7.82배 추가 가속화가 가능하다. 제안하는 뷰포트 추출 병렬화 구조는 360도 비디오나 가상현실 콘텐츠들에 대한 동시 다중 접속 서비스나 사용자별 영상 요약 서비스 등에 활용될 수 있다.