• International Journal of Aeronautical and Space Sciences
• /
• v.9 no.2
• /
• pp.114-120
• /
• 2008

In the vision-based recovery phase, a terminal guidance for the blended-wing UAV requires visual information of high accuracy. This paper presents the light source target design and detection algorithm for vision-based UAV recovery. We propose a recovery target design with red and green LEDs. This frame provides the relative position between the target and the UAV. The target detection algorithm includes HSV-based segmentation, morphology, and blob processing. These techniques are employed to give efficient detection results in day and night net recovery operations. The performance of the proposed target design and detection algorithm are evaluated through ground-based experiments.

• Proceedings of the KAIS Fall Conference
• /
• 2000.10a
• /
• pp.121-123
• /
• 2000

섬유의 자동 검사에서는 섬유 패턴과 연관이 있는 결함과 패턴과 연관이 없는 결함의 2 부류를 검사하게 된다 본 논문에서는 이들 결함의 검사를 2 단계에 거쳐서 하게 되는데, 섬유 패턴에 독립적인 결함을 프로파일 분석을 통해 우선 검출하고, 섬유 패턴에 종속적인 결함을 co-occurrence 행렬을 이용해 검출하는 기법을 소개한다. 이렇게 해서 검출된 결함들은 Back-propagation 알고리즘을 사용해 분류된다. 이 기법을 통한 실험에서 백색 유광택 타포린에서 발생하는 이물질유입 및 위사빠짐을 97.1%이상 검출할 수 있었다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.400-404
• /
• 2006

We suggest a method to detect rear car license plate of one more cars by using blobs. First, we try to search all of the blobs from an input image based on the difference between objects and background. Second, we obtain rectangles enclosed the blobs, and rectangle clusters by considering the properties, for example, the number, size, distance, position. Third, the cluster is verified by the Support Vector Machine. Even if we only use the adaptive binarization as the preprocessing, the detection ratio is very high.

• Journal of Satellite, Information and Communications
• /
• v.9 no.1
• /
• pp.57-64
• /
• 2014

Recently, many human-friendly communication methods have been studied for human-machine interface(HMI) without using any physical devices. One of them is the vision-based gesture recognition that this paper deals with. In this paper, we define some gestures for interaction with objects in a predefined virtual world, and propose an efficient method to recognize them. For preprocessing, we detect and track the both hands, and extract their silhouettes from the low-resolution hand images captured by a webcam. We modeled skin color by two Gaussian distributions in RGB color space and use blob-matching method to detect and track the hands. Applying the foodfill algorithm we extracted hand silhouettes and recognize the hand shapes of Thumb-Up, Palm and Cross by detecting and analyzing their modes. Then, with analyzing the context of hand movement, we recognized five predefined one-hand or both-hand gestures. Assuming that one main user shows up for accurate hand detection, the proposed gesture recognition method has been proved its efficiency and accuracy in many real-time demos.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Journal of information and communication convergence engineering
• /
• v.5 no.1
• /
• pp.50-53
• /
• 2007

This paper presents face features detection and a new physiological neuro-fuzzy learning method by using two-dimensional variances based on variation of gray level and by learning for a statistical distribution of the detected face features. This paper reports a method to learn by not using partial face image but using global face image. Face detection process of this method is performed by describing differences of variance change between edge region and stationary region by gray-scale variation of global face having featured regions including nose, mouse, and couple of eyes. To process the learning stage, we use the input layer obtained by statistical distribution of the featured regions for performing the new physiological neuro-fuzzy algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.92-99
• /
• 2004

The formation degree of sustain (ITO pattern) decides quality of PDP (Plasma Display Panel). For this reason, it makes efforts in searching defects more than 30 un as 100%. Now, the existing inspection is dependent upon naked eye or microscope in off-line PDP manufacturing process. In this study developed prototype inspection system of PDP 170 glass is based on line-scan mechanism. Developed system creates information that detects and sorts kinds of defect automatically. Designed inspection technology adopts multi-vision method by slip-beam formation for the minimum of inspection time and detection algorithm is embodied in detection ability of developed system. Designed algorithm had to make good use of kernel matrix that draws up an approach to geometry. A characteristic of defects, as pin hole, substance, protrusion, are extracted from blob analysis method. Defects, as open, short, spots and et al, are distinguished by line type inspection algorithm. In experiment, we could have ensured ability of inspection that can be detected with reliability of up to 95% in about 60 seconds.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.3
• /
• pp.18-23
• /
• 2006

The formation degree of sustain (ITO pattern) determines the quality of a PDP (Plasma Display Panel). Thus, in the present study, we attempt to detect 100% of the defects that are larger than $30{\mu}m$. Currently, the inspection method in the PDP manufacturing process is dependent upon the naked eye or a microscope in off-line mode. In this study, a prototype inspection system for PDP ITO patterned glass is developed. The developed system, which is based on a line-scan mechanism, obtains information on the defects and sorts the defects by type automatically. The developed inspection system adopts a multi-vision method using slit-beam formation for minimum inspection time and the detection algorithm is embodied in the detection ability. Characteristic defects such as pin holes, substances, and protrusions are extracted using the blob analysis method. Defects such as open, short, spots and others are distinguished by the line type inspection algorithm. It was experimentally verified that the developed inspection system can detect defects with reliability of up to 95% in about 60 seconds for the 42-inch PDP panel.

• Journal of Biosystems Engineering
• /
• v.28 no.1
• /
• pp.45-52
• /
• 2003

Red ginsengs are inspected manually by examining those in the dark room with back light illumination. Manual inspection is often influenced by physical condition of inspectors. Sometimes. the best grade, heaven. has some inner holes though it was inspected by a specialist. In order to resolve this problem, this study was performed to develop image processing algorithm to detect the inner holes in the x-ray image of ginseng. Because of little gray value difference between background and ginseng in the image. simple thresholding method was not appropriate. Modified watershed algorithm was used to differentiate the inner holes from background and normal ginseng body. Inner hole edge region detected by watershed algorithm consists of many number of blobs including normal portions. With line profile analysis with scanning one line at a time beginning the starting point. it shelved two peaks both ends representing extracting each blobs. in which setting threshold value as of lower peak value enabled us to obtain inner hole image. Once this procedure has to be done till the finishing point it is completing inner hole detection for one blob. Thus. conducting ail blobs by this procedure is completing inner detection of one whole ginseng. Detection results of the inner holes fer various size of red ginsengs were good even though there was small detection variation. 6.2%. according to position of x-rat tube.

• Journal of Advanced Navigation Technology
• /
• v.17 no.1
• /
• pp.98-106
• /
• 2013

In this paper, we propose a moving object detection and tracking method for multi-view camera environment. Based on the similarity and characteristics of motion vectors and coding block modes extracted from compressed bitstreams, validation of moving blocks, labeling of the validated blocks, and merging of neighboring blobs are performed. To continuously track objects for temporary stop, crossing, and overlapping events, a window based object updating algorithm is proposed for single- and multi-view environments. Object detection and tracking could be performed with an acceptable level of performance without decoding of video bitstreams for normal, temporary stop, crossing, and overlapping cases. The rates of detection and tracking are over 89% and 84% in multi-view environment, respectively. The rates for multi-view environment are improved by 6% and 7% compared to those of single-view environment.