• 전기학회논문지P
• /
• 제64권3호
• /
• pp.193-198
• /
• 2015

A large number of vision applications rely on matching keypoints across images. Pedestrian detection is under constant pressure to increase both its quality and speed. Such progress allows for new application. A higher speed enables its inclusion into large systems with extensive subsequent processing, and its deployment in computationally constrained scenarios. In this paper, we focus on improving the speed of pedestrian detection using HOG(histogram of oriented gradient) and multi frame operation which is robust to illumination changes in cluttering images. The result of our simulation indicates that the detection rate and speed of the proposed method is much faster than that of conventional HOG and differential images.

• ETRI Journal
• /
• 제29권4호
• /
• pp.411-420
• /
• 2007

The steady evolution of mapping technology is leading to an increasing availability of multi-sensory geo-spatial datasets, such as data acquired by single-head frame cameras, multi-head frame cameras, line cameras, and light detection and ranging systems, at a reasonable cost. The complementary nature of the data collected by these systems makes their integration to obtain a complete description of the object space. However, such integration is only possible after accurate co-registration of the collected data to a common reference frame. The registration can be carried out reliably through a triangulation procedure which considers the characteristics of the involved data. This paper introduces algorithms for a multi-primitive and multi-sensory triangulation environment, which is geared towards taking advantage of the complementary characteristics of spatial data available from the above mentioned sensors. The triangulation procedure ensures the alignment of involved data to a common reference frame. The devised methodologies are tested and proven efficient through experiments using real multi-sensory data.

• Structural Engineering and Mechanics
• /
• 제63권6호
• /
• pp.825-835
• /
• 2017

Significant improvements to methodologies on structural damage detection (SDD) have emerged in recent years. However, many methods are related to inversion computation which is prone to be ill-posed or ill-conditioning, leading to low-computing efficiency or inaccurate results. To explore a more accurate solution with satisfactory efficiency, a PSO-INM algorithm, combining particle swarm optimization (PSO) algorithm and an improved Nelder-Mead method (INM), is proposed to solve multi-sample objective function defined based on Bayesian inference in this study. The PSO-based algorithm, as a heuristic algorithm, is reliable to explore solution to SDD problem converted into a constrained optimization problem in mathematics. And the multi-sample objective function provides a stable pattern under different level of noise. Advantages of multi-sample objective function and its superior over traditional objective function are studied. Numerical simulation results of a two-storey frame structure show that the proposed method is sensitive to multi-damage cases. For further confirming accuracy of the proposed method, the ASCE 4-storey benchmark frame structure subjected to single and multiple damage cases is employed. Different kinds of modal identification methods are utilized to extract structural modal data from noise-contaminating acceleration responses. The illustrated results show that the proposed method is efficient to exact locations and extents of induced damages in structures.

• 한국컴퓨터정보학회논문지
• /
• 제22권3호
• /
• pp.45-51
• /
• 2017

In this paper, we propose a consecutive-frame super-resolution method to tackle a moving object problem. The super-resolution is a method restoring a high resolution image from a low resolution image. The super-resolution is classified into two types, briefly, single-frame super-resolution and consecutive-frame super-resolution. Typically, the consecutive-frame super-resolution recovers a better than the single-frame super-resolution, because it use more information from consecutive frames. However, the consecutive-frame super-resolution failed to recover the moving object. Therefore, we proposed an improved method via moving object detection. Experimental results showed that the proposed method restored both the moving object and the background properly.

• 전자공학회논문지
• /
• 제50권12호
• /
• pp.141-149
• /
• 2013

본 논문은 멀티 코어 프로세서 기반의 영상 감시 시스템을 위한 침입 탐지 처리의 가속화를 제안한다. 침입 탐지 처리의 가속화를 위해 병렬화를 진행하였고, 이를 위해 기존 침입 탐지 알고리즘을 분석하고 데이터 의존성을 고려하여 프레임 단위의 병렬화된 처리 구조를 설계하였다. 병렬화된 침입 탐지 처리의 유효성을 검증하기 위하여 다중 쓰레드 기반의 프로그램으로 구현하여 침입 탐지의 가속화 정도를 측정하였다. 구현한 침입 탐지 처리 프로그램의 탐지 속도는 논리적 쓰레드를 8개까지 구현할 수 있는 환경에서 기존 단일 쓰레드 처리 대비 최대 353.76%가 향상되었다.

• 한국위성정보통신학회논문지
• /
• 제10권2호
• /
• pp.109-114
• /
• 2015

프레임 동기화는 전송 프레임 헤더에 주기적으로 삽입되는 프리엠블(preamble) 패턴과 수신 심볼 간의 상관 연산을 통해 이루어지며 프레임의 시작점 및 구조 검출을 하는 것이 목적이다. 본 논문은 위성 기반 DVB-S2 시스템 요구사항에 부합하는 프레임 구조 획득 방법에 대해 기술하였다. DVB-S2 수신 신호는 매우 낮은 신호 대 잡음비를 가지며 심볼 속도 대비 20%에 상응하는 주파수 오프셋 성분이 포함되어 있다. 또한 규격은 프레임 당 심볼 수가 상이한 16가지의 프레임 구조를 지원하고 있다. 본 논문에서는 위의 환경에서 정확하고 빠른 프레임 동기화를 위해 프레임 헤더의 SOF와 PLSC 정보를 이용하여 상관 열을 발생시키고 상관 값 누적을 통해 프레임 동기 및 구조 검출을 실시하였다 마지막으로 컴퓨터 모의실험을 통해 평균 획득 시간(mean acquisition time), 프레임 구조 검출 오류율에 대한 성능평가를 실시하였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권8호
• /
• pp.91-97
• /
• 2012

본 논문에서는 각 프레임에서의 음성신호 및 비음성신호 구간을 검출하는 음성인식 알고리즘을 제안한다. 그리고 음성신호 및 비음성신호 구간의 검출에 따라서 각 프레임에서 잡음을 제거하는 멀티밴드필터에 의한 환경잡음억압 알고리즘을 제안한다. 이 알고리즘은 음성으로부터 특징 파라미터를 추출하여 필터뱅크의 서브밴드 영역에서 잡음을 제거하는 방법이다. 본 실험에서는 환경잡음억압 알고리즘의 성능을 멀티밴드필터를 사용하여 각 프레임에서 잡음을 제거하는 실험결과를 나타낸다. 잡음에 의하여 오염된 음성에 대하여 스펙트럴 왜곡률을 사용하여 본 알고리즘이 유효하다는 것을 확인한다.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.439-449
• /
• 2023

This paper deals with a resource efficient artificial intelligence (AI) service architecture for multi-channel video streams. As an AI service, we consider the object detection model, which is the most representative for video applications. Since most object detection models are basically designed for a single channel video stream, the utilization of the additional resource for multi-channel video stream processing is inevitable. Therefore, we propose a resource efficient AI service framework, which can be associated with various AI service models. Our framework is designed based on the modular architecture, which consists of adaptive frame control (AFC) Manager, multiplexer (MUX), adaptive channel selector (ACS), and YOLO interface units. In order to run only a single YOLO process without regard to the number of channels, we propose a novel approach efficiently dealing with multi-channel input streams. Through the experiment, it is shown that the framework is capable of performing object detection service with minimum resource utilization even in the circumstance of multi-channel streams. In addition, each service can be guaranteed within a deadline.

• Earthquakes and Structures
• /
• 제17권1호
• /
• pp.63-73
• /
• 2019

This paper studies damage detection as an optimization problem. A new objective function based on changes in natural frequencies, and Natural Frequency Vector Assurance Criterion (NFVAC) was developed. Due to their easy and fast acquisition, natural frequencies were utilized to detect structural damages. Moreover, they are sensitive to stiffness reduction. The method presented here consists of two stages. Firstly, Finite Element Model (FEM) is updated. Secondly, damage severities and locations are determined. To minimize the proposed objective function, a new bio-inspired optimization algorithm called salp swarm was employed. Efficiency of the method presented here is validated by three experimental examples. The first example relates to three-story shear frame with two single damage cases in the first story. The second relates to a five-story shear frame with single and multiple damage cases in the first and third stories. The last one relates to a large-scale eight-story shear frame with minor damage case in the first and third stories. Moreover, the performance of Salp Swarm Algorithm (SSA) was compared with Particle Swarm Optimization (PSO). The results show that better accuracy is obtained using SSA than using PSO. The obtained results clearly indicate that the proposed method can be used to determine accurately and efficiently both damage location and severity in multi-story shear frames.

• 한국멀티미디어학회논문지
• /
• 제24권5호
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.