http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Precise Detection of Car License Plates by Locating Main Characters
이대호,최진혁 한국광학회 2010 Current Optics and Photonics Vol.14 No.4
We propose a novel method to precisely detect car license plates by locating main characters, which are printed with large font size. The regions of the main characters are directly detected without detecting the plate region boundaries, so that license regions can be detected more precisely than by other existing methods. To generate a binary image, multiple thresholds are applied, and segmented regions are selected from multiple binarized images by a criterion of size and compactness. We do not employ any character matching methods, so that many candidates for main character groups are detected; thus, we use a neural network to reject non-main character groups from the candidates. The relation of the character regions and the intensity statistics are used as the input to the neural network for classification. The detection performance has been investigated on real images captured under various illumination conditions for 1000vehicles. 980 plates were correctly detected, and almost all non-detected plates were so stained that their characters could not be isolated for character recognition. In addition, the processing time is fast enough for a commercial automatic license plate recognition system. Therefore, the proposed method can be used for recognition systems with high performance and fast processing.
교통 영상에서 은닉 마르코프 모델을 이용한 차량 분할 및 추적
이대호,박영태 경희대학교 레이저공학연구소 2005 레이저공학 Vol.16 No.-
This paper presents a novel method for real-time segmenting and tracking of vehicles in traffic sequence. Hidden Markov model (HMM) is used to segment vehicles, and the inputs of HMM are gradient direction and statistical features. And, the template matching is utilized for tracking of detected vehicles. Because we use the information of gradient direction, the accuracy of segmentation is robust under the various weather conditions such as shadow, rainy and snowy, therefore vehicles that are difficult to distinguish from background are segmented correctly. Since only local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized without using dedicated parallel processors, while ensuring detection performance robust to the variation of weather conditions, shadows and traffic load. Thus, this method may be appropriate to improve vehicle detection performance in traffic monitoring systems.
이대호,박기서,박영태 慶熙大學校 레이저 工學硏究所 2007 레이저공학 Vol.18 No.-
본 논문은 지하철 영상에서 승객을 검출하는 새로운 기법을 제안한다. 열차의 존재 유무에 따라서 승객의 검출은 달라져야 하므로,열차의 상태를 진입(IN),정차(ON), 출차(OUT)와 없음(OFF)으로 구분한다. 이와 같은 열차의 상태는 열차의 큰 움직임으로 판별할 수 있으므로 프레임 차이에 의해 판별한다. 또한 기본적으로 승객의 검출은 배경 영상과의 차이를 이용하며,사람의 모델을 이용하여 머리,몸과 하체를 판단하여 완성된 사람의 영역을 찾는다. 이전에 검출된 사람은 영역 기반 추적 기법을 이용하여 추적한다. 두 곳의 지하철역에서 각각 50분 동안 촬영된 영상열에서 실험한 결과는 움직이는 승객을 거의 모두 검출한 수 있었다. 또한 더욱 정밀한 인체의 모델을 이용하여 승객을 검출하고 추적한다면, 지하철의 위험 영역에 존재하는 사람을 검출하는 기법으로 사용될 수 있을 것이다.
Polygonal Approximation of Digital Curves to Preserve Original Shapes
이대호,이승관 한국전자통신연구원 2010 ETRI Journal Vol.32 No.4
In this letter, we propose a novel polygonal approximation of digital curves that preserve original shapes. The proposed method first detects break points, which have two different consecutive vectors, and sets an initial dominant point set. The approximation is then performed iteratively by deleting a dominant point using a novel distance, which can measure both the distance and the angle acuteness. The experimental results show that the proposed method can preserve original shapes and is appropriate for various shapes, including slab-sided shapes.
이대호,박영태 대한전자공학회 2006 電子工學會論文誌-TC (Telecommunications) Vol.43 No.9
A number of researches on vision-based traffic monitoring system have been carried out. Most of traffic monitoring schemes belong to one of two categories: analyzing of entire traffic scene and examining of local region. However, the proposed methods suffer from severe performance deterioration when applied in different operating conditions because of the loss of robustness. This paper is aimed at surveying various methods proposed and analyzing the advantages and disadvantages of these methods. Also we propose and investigate appropriate approaches to solve the problems in specific applications. 영상 정보를 이용한 교통 모니터링 시스템에 관한 많은 연구가 이루어졌다. 대부분의 교통 모니터링 기술은 전체 영상을 분석하는 기법과 국부 영역을 검사하는 기법으로 구분된다. 하지만, 제안된 대부분의 기법들은 동작 환경이 변화할 경우 강건성의 결여로 인해 성능이 급격히 저하하는 문제점을 갖고 있다. 본 논문에서는 기존의 논문에서 제안되었던 다양한 기법들의 특성을 조사하고, 장점과 단점을 분석한다. 또한 각 응용 분야마다 영상 처리를 이용하는 기법들이 가지고 있는 문제점들을 해결할 수 있는 적절한 방법을 고찰한다.
Vision-Based Finger Action Recognition by Angle Detection and Contour Analysis
이대호,SeungGwan Lee 한국전자통신연구원 2011 ETRI Journal Vol.33 No.3
In this paper, we present a novel vision-based method of recognizing finger actions for use in electronic appliance interfaces. Human skin is first detected by color and consecutive motion information. Then, fingertips are detected by a novel scale-invariant angle detection based on a variable k-cosine. Fingertip tracking is implemented by detected region-based tracking. By analyzing the contour of the tracked fingertip, fingertip parameters, such as position, thickness, and direction, are calculated. Finger actions, such as moving, clicking, and pointing, are recognized by analyzing these fingertip parameters. Experimental results show that the proposed angle detection can correctly detect fingertips, and that the recognized actions can be used for the interface with electronic appliances.