• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.32.5-32
• /
• 2001

There has been many teleoperation systems handling the micro object. However, the stability problem for these systems has not been mentioned yet. Historically, Lawrence[1] proposed the Transparency-Optimized Architecture and passivity theorem for stability analysis of bilateral teleoperation. He claimed that unless the task(or environment) impedance contains significance inertial behavior, Passivity condition for Transparency-optimized architecture is not satisfied. In this paper we propose one method which satisfies passivity condition for the micro-teleoperation system handling a insignificant inertial object and is based on the structure of Lawrence and Hashtrudi-Zaad[2] and velocity-force scaling.

• 전자공학회지
• /
• 제39권2호
• /
• pp.45-54
• /
• 2012

Object detection is a fundamental task for many high-level computer vision applications such as image retrieval, scene understanding, activity recognition, visual surveillance and many others. Although object detection is one of the most popular problems in computer vision and various algorithms have been proposed thus far, it is also notoriously difficult, mainly due to lack of proper models for object representation, that handle large variations of object structure and appearance. In this article, we review a branch of object detection algorithms based on Support Vector Machines (SVMs), a well-known max-margin technique to minimize classification error. We introduce a few variations of SVMs-Structural SVMs and Latent SVMs-and discuss their applications to object detection and localization.

• 대한원격탐사학회지
• /
• 제24권5호
• /
• pp.473-481
• /
• 2008

This paper presents an approach to Back-propagation and Radial Basis Function neural network method with various training set for automatic vehicle detection from aerial images. The initial extraction of candidate object is based on Mean-shift algorithm with symmetric property of a vehicle structure. By fusing the density and the symmetry, the method can remove the ambiguous objects and reduce the cost of processing in the next stage. To extract features from the detected object, we describe the object as a log-polar shape histogram using edge strengths of object and represent the orientation and distance from its center. The spatial histogram is used for calculating the momentum of object and compensating the direction of object. BPNN and RBFNN are applied to verify the object as a vehicle using a variety of non-car training sets. The proposed algorithm shows the results which are according to the training data. By comparing the training sets, advantages and disadvantages of them have been discussed.

• 한국통신학회논문지
• /
• 제17권12호
• /
• pp.1412-1422
• /
• 1992

본 논문은 이 기종 문서처리 시스템간에 문서교환을 위해 국제 표준으로 재정된 ODA에 따른 문서 클래스(class) 에디터 설계 및 구현에 대하여 기술하였다. ODA에서처럼 문서구조를 공통 논리구조와 배치구조로 분리하여 처리하였으며, 문서 프로화일을 작성 할 수 있도록 설계하였다. 문서가 정확하게 작성되었는지를 객체(object) 단위로 확인할 수 있는 유틸리티(utility)를 구현하였다. 또한 그 문서의 ODIF 스트림(stream) 데이타가 정확한지를 확인하였다. 본 에디터는 국제 문서 응용 프로화일 (DAP : Document Application Profile)인 DAP 단계 2의 제안에 따라 설계하였으며, UNIX 운영체제의 SUN 워크스테이션상에서 이식성이 좋고 일관된 사용자 인터페이스(interface)를 제공하는 X 윈도우 및 Motif 환경하에서 구현하였다. 본 연구를 통하여 구현된 에디터는 특정 문서구조를 갖는 실제 ODA 문서를 작성시 이용될 수 있다.

• 한국멀티미디어학회논문지
• /
• 제2권3호
• /
• pp.252-264
• /
• 1999

비디오 데이터 자체가 시간적 구조와 공간적 구조로 이루어져 있기 때문에 비디오 데이터에 대한 내용 기반 검색은 두 관계를 중섬으로 이루어 질 수 있다. 본 논문에서는 비디오 데이터 구조가 시간의 흐름에 따라 논리적 계충 구조로 표현 가능하며, 각각의 계층은 각기 시간의 흐름에 따라 시간 관계성을 지닌다는 특성을 반영한 검색 기능을 설계하였다 그리고 비디오 데이터의 시간적 관계를 계승, 캡슐화, 함수 중복 등의 객체 지향 특성을 이용하여 객체 관계 DBMS로 구현하였다 기존의 제한적인 시간 함수가 아닌 본 논문에서 제시한 다양한 비디오 데이터의 시간 관계성에 따른 좀 더 확장되고 다양한 시간 함수를 제공함으로 써, 사용하기 편리한 인터페이스와, 여러 가지 시간 질의어를 제공한다.

• 한국멀티미디어학회논문지
• /
• 제20권7호
• /
• pp.986-993
• /
• 2017

Object Tracking is a technique for tracking moving objects over time in a video image. Using object tracking technique, many research are conducted such a detecting dangerous situation and recognizing the movement of nearby objects in a smart car. However, it still remains a challenging task such as occlusion, deformation, background clutter, illumination variation, etc. In this paper, we propose a novel deep visual object tracking method that can be operated in robust to many challenging task. For the robust visual object tracking, we proposed a Convolutional Neural Network(CNN) which shares weight of the convolutional layers. Input of the CNN is a three; first frame object image, object image in a previous frame, and current search frame containing the object movement. Also we propose a method to consider the motion of the object when determining the current search area to search for the location of the object. Extensive experimental results on a authorized resource database showed that the proposed method outperformed than the conventional methods.

• 한국전산유체공학회지
• /
• 제9권2호
• /
• pp.1-10
• /
• 2004

In the present study, a post-processing program is developed for 3D data visualization and analysis. Because the graphical user interface(GUI) of the program is based on Qt-library while all the graphic rendering is performed with OpenGL library, the program runs on not only MS Windows but also UNU and Linux systems without modifying source code. The structure of the program is designed according to the object-oriented programming(OOP) concept so that it has extensibility, reusability, and easiness compared to those by procedural programming. The program is organized as modules by classes, and these classes are made to function through inheritance and cooperation which is an important and valuable concept of object-oriented programming. The major functions realized so far which include mesh plot, contour plot, vector plot, streamline plot, and boundary plot are demonstrated and the relevant algorithms are described.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권3호
• /
• pp.181-187
• /
• 2003

For the moving objects with environmental sensors such as object tracking moving robot with audio and video sensors, environmental information acquired from sensors keep changing according to movements of objects. In such case, due to lack of adaptability and system complexity, conventional control schemes show limitations on control performance, and therefore, sensory-motor systems, which can intuitively respond to various types of environmental information, are desirable. And also, to improve the system robustness, it is desirable to fuse more than two types of sensory information simultaneously. In this paper, based on Braitenberg's model, we propose a sensory-motor based fusion system, which can trace the moving objects adaptively to environmental changes. With the nature of direct connecting structure, sensory-motor based fusion system can control each motor simultaneously, and the neural networks are used to fuse information from various types of sensors. And also, even if the system receives noisy information from one sensor, the system still robustly works with information from other sensors which compensates the noisy information through sensor fusion. In order to examine the performance, sensory-motor based fusion model is applied to object-tracking four-foot robot equipped with audio and video sensors. The experimental results show that the sensory-motor based fusion system can tract moving objects robustly with simpler control mechanism than model-based control approaches.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.