• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.829-836
• /
• 2018

This study attempts to detect a shot boundary in films(or dramas) based on the length of a sequence. As films or dramas use scene change effects a lot, the issues regarding the effects are more diverse than those used in surveillance cameras, sports videos, medical care and security. Visual techniques used in films are focused on the human sense of aesthetic therefore, it is difficult to solve the errors in shot boundary detection with the method employed in surveillance cameras. In order to define the errors arisen from the scene change effects between the images and resolve those issues, the mixed algorithm based upon color histogram, edge histogram, and optical flow was implemented. The shot boundary data from this study will be used when analysing the configuration of meaningful shots in sequences in the future.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.297-299
• /
• 2006

Searching the region of interest on the Hough transform domain is done to determine the real road boundary on the high speed way. The mathematical morphology is employed to obtain the gradient image which is utilized in Hough transform. Many possible candidates of lines could appear on the ordinary road environment and simple selection of the strongest line segments likely to be fault boundary lines. To solve such problem, the search area for the candidates of the road boundary which is called the region of interest is limited on the Hough space. The effectiveness of the proposed algorithm has been shown with experimental results.

• The Journal of the Acoustical Society of Korea
• /
• 제26권1E호
• /
• pp.21-26
• /
• 2007

In this paper, we propose a modified Viterbi algorithm to compensate for endpoint detection error during the decoding phase of an isolated word recognition task. Since the conventional Viterbi algorithm explores only the search space whose boundaries are fixed to the endpoints of the segmented utterance by the endpoint detector, the recognition performance is highly dependent on the accuracy level of endpoint detection. Inaccurately segmented word boundaries lead directly to recognition error. In order to relax the degradation of recognition accuracy due to endpoint detection error, we describe an unconstrained search of word boundaries and present an algorithm to explore the search space with efficiency. The proposed algorithm was evaluated by performing a variety of simulated endpoint detection error cases on an isolated word recognition task. The proposed algorithm reduced the Word Error Rate (WER) considerably, from 84.4% to 10.6%, while consuming only a little more computation power.

• ETRI Journal
• /
• 제46권2호
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• 전자공학회논문지
• /
• 제51권2호
• /
• pp.76-84
• /
• 2014

최근 고화질 영상의 증가와 더불어 대용량 영상 데이터의 처리는 높은 연산이 요구되어 병렬 처리 설계가 선택되고 있다. 영상 처리에서 나타나는 많은 단순 연산이 병렬처리 가능한 경우, CPU 기반 병렬처리보다는 GPU 기반 병렬처리를 적용하는 것이 계산문제의 시간과 공간 계산 복잡도를 줄일 수 있다. 본 논문은 영상에서 샷 경계 탐지 알고리즘의 병렬 설계와 구현을 연구하였다. 제안하는 샷 경계 탐지 알고리즘은 프레임 간 지역 화소 밝기 비교와 전역 히스토그램 정보를 이용하는데, 이들 데이터의 계산은 대량의 데이터에 대한 높은 병렬성을 갖는다. 이들 연산의 병렬처리를 최대화하기 위해 화소 밝기와 히스토그램의 계산을 NVIDIA GPU에서 병렬 설계 하였다. GPU 기반 샷 탐지 방법은 국가기록원에서 선택된 10개의 비디오 데이터에 대한 성능 테스트를 수행하였다. 테스트에서 GPU 기반 알고리즘의 탐지율은 CPU 기반 알고리즘과 유사하였으나 약 10배의 연산 속도가 개선되었다.

• 한국전자통신학회논문지
• /
• 제13권5호
• /
• pp.1051-1058
• /
• 2018

지하철 스크린도어(PSD)에서 발생할 수 있는 안전사고 예방을 위한 영상처리 알고리듬을 제안한다. 우선 지하철 스크린도어 영상에 대해 에지를 검출 하고, 사람의 스크린도어 접근 여부를 판단하기 위해 호프변환을 이용하여 직선을 검출한다. 이를 위해 스크린도어 경계면에 일직선을 긋고 이 직선의 끊김 여부로 사람의 접근을 판단한다. 일반적으로 에지는 영상의 가장 기본적인 특징을 나타내며, 에지 검출은 영상처리 및 컴퓨터 비전 분야에서 매우 중요하다. 에지 검출 방법에는 로버츠, 소벨, 프리윗, 라플라시안 등 고정된 값의 마스크를 사용하는 방법과 영상을 형태학적 관점에서 접근하여 처리하는 모폴로지 방법 및 캐니에지 검출 방법 등이 있다. 본 논문에서는 캐니에지 검출방법과 호프변환을 이용하여 지하철 스크린도어에서 사람의 접근 여부에 대한 감지 알고리듬을 제안하고 실제 그 결과를 컴퓨터 시뮬레이션으로 나타내었다.

• 전자공학회논문지B
• /
• 제29B권11호
• /
• pp.111-119
• /
• 1992

In this paper, we propose an edge detection scheme for noisy images based on the co-occurrence matrix. In the proposed scheme based on the step edge model, the gray level information is simply converted into a bit-map, i.e., the uniform and boundary regions of an image are transformed into a binary pattern by using the local mean. In this binary bit-map pattern, 0 and 1 densely distributed near the boundary region while they are randomly distributed in the uniform region. To detect the boundary region, the co-occurrence matrix on the bit-map is introduced. The effectiveness of the proposed scheme is shown via a quantitative performance comparison to the conventional edge detection methods and the simulation results for noisy images are also presented.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.3-5
• /
• 2005

Vessel boundary detection and modeling is a difficult but a necessary task in analyzing the mechanics of inflammation and the structure of the microvasculature. In this paper we present a method of analyzing the structure by means of an active contour model(using GVF Snake) for vessel boundary detection and 3D reconstruction. For this purpose we used a virtual vessel model and produced a phantom model. From these phantom images we obtained the contours of the vessel by GVF Snake and then reconstructed a 3D structure by using the coordinates of snakes.

• 전자공학회논문지B
• /
• 제30B권2호
• /
• pp.59-68
• /
• 1993

The motion vector estimation and motion boundary detection have been briskly studied since they are an important clue for analysis of object structure and 3-d motion. The purpose of this researches is more exact estimation, but there are two main causes to make inaccurate. The one is the erroneous measurement of gradients in brightness values and the other is the blurring of motion boundries which is caused by the smoothness constraint. In this paper, we analyze the gradient measurement error of conventional methods and propose new technique based on it. When the proposed method is applied to the motion boundary detection in Schunck and motion vector estimation in Horn & Schunck, it is shown to have much better performance than conventional method is some artificial and real image sequences.

• Journal of Mechanical Science and Technology
• /
• 제14권10호
• /
• pp.1104-1113
• /
• 2000

This paper proposes an efficient reverse engineering technique for compound surfaces using a boundary detection method. This approach consists in extracting geometric edge information using a vision system, which can be used in order to drastically reduce geometric errors in the vicinity of compound surface boundaries. Through the image-processing technique and the interpolation process, boundaries are reconstructed by either analytic curves (e. g. circle, ellipse, line) or parametric curves (B-spline curve). In other regions, except boundaries, geometric data are acquired on CMM as points inspected using a touch type probe, and then they are interpolated on several surfaces using a B-spline skinning method. Finally, the boundary edge and the skinned surfaces are combined to reconstruct the final compound surface. Through simulations and experimental works, the effectiveness of the proposed method is confirmed.