• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.382-385
• /
• 2008

MODIS images have a great advantage of high temporal resolution to monitor land cover changes in a large area. The moderate and low spatial resolution satellite images are incomparably economic than high resolution satellite images. As diverse satellite images are provided recently, strategies using satellite images are necessary for continuous, effective and long-term land monitoring. This research purposed to use MODIS images to monitor land cover in Korean peninsula for long-term and continuous change detection. To maximize the advantages of high temporal resolution, the change detection was based on the MODIS temporal profiles of the surface reflectance for one year. In this study as the reflectance patterns of year 2005 were compared with the reflectance patterns of year 2007, the changed pixels could be detected during two years. To set up the threshold value for the decision of change, ASTER images with the higher spatial resolution, 15m, were used for this study. The test area covered the suburban area of metropolitan city, Seoul, where the landcover changes have been frequently happened.

• 한국게임학회 논문지
• /
• 제17권6호
• /
• pp.139-152
• /
• 2017

본 논문에서는 구면 영상에서 영역 분할 정보를 사용하여 바닥 영역을 검출하는 방법을 제시한다. 평면 영상에서의 Watershed 영역 분할 방법을 수정하여 구면 영상의 영역 분할에 적용할 수 있도록 하였다. 영역들을 분할한 뒤 가정된 바닥 영역 픽셀의 색상과 질감을 그 외의 영역들과 비교하여 바닥 영역을 검출한다. 구면 파노라마 영상에서는 구면 왜곡으로 인하여 평면에서의 바닥 검출 방법을 그대로 적용할 수 없다. 구면 왜곡을 고려한 바닥 영역 검출을 위하여 바닥 영역의 외곽선을 검출하는 알고리즘을 설계하였다. 실험에서 지상물이 없는 경우와 있는 경우의 모두에서 적절하게 바닥 영역을 검출할 수 있는 결과를 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권5호
• /
• pp.386-393
• /
• 2010

영상에서 일정 영역의 화소들이 불규칙적인 형태를 이루는 것을 불량이라 하는데 이를 수학적으로 정확히 정의하기 어렵다는 점이 불량 검출을 쉽지 않게 한다. 하지만 주어진 영상이 다수의 반복되는 패턴을 가지고 있다면 불량이 아닌 영역은 그 외의 다른 영역들로 설명되어 될 수 있다는 점을 이용하여 영상내의 불량 영역을 찾아낼 수 있다. 따라서 본 논문은 이러한 특성을 이용하여 다양한 패턴이 반복되는 영상에 존재하는 불량을 검출하는 방법을 제시한다. 제시된 방법은 크게 세 단계로 이루어진다. 첫 번째 단계는 interest point 검출단계이다. 두 번째 단계는 적절한 패치의 크기를 결정하는 단계이다. 마지막으로 세 번째 단계는 불량을 검출하는 단계이다. 제시된 방법은 반도체 wafer를 SEM을 이용하여 촬영한 영상들을 통하여 예증된다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.260-262
• /
• 2006

One of future remote sensing techniques for transportation application is vehicle detection from the space, which could be the basis of measuring traffic volume and recognizing traffic condition in the future. This paper introduces an approach to vehicle detection using image object segmentation approach. The object-oriented image processing is particularly beneficial to high-resolution image classification of urban area, which suffers from noisy components in general. The project site was Dae-Jeon metropolitan area and a set of true color aerial images at 10cm resolution was used for the test. Authors investigated a variety of parameters such as scale, color, and shape and produced a customized solution for vehicle detection, which is based on a knowledge-based hierarchical model in the environment of eCognition. The highest tumbling block of the vehicle detection in the given data sets was to discriminate vehicles in dark color from new black asphalt pavement. Except for the cases, the overall accuracy was over 90%.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.269-275
• /
• 2017

Automatic vehicle detection is a very important function for autonomous vehicles. Conventional vehicle detection approaches are based on visible-light images obtained from cameras mounted on a vehicle in the daytime. However, unlike daytime, a visible-light image is generally dark at night, and the contrast is low, which makes it difficult to recognize a vehicle. As a feature point that can be used even in the low light conditions of nighttime, the rear lamp is virtually unique. However, conventional rear lamp-based detection methods seldom cope with atypical lamps, such as LED lamps, or flashing turn signals. In this paper, we detect atypical lamps by blurring the lamp area with a low pass filter (LPF) to make out the lamp shape. We also propose to detect flickering of the turn signal lamp in a manner such that the lamp area is vertically projected, and the maximum difference of two paired lamps is examined. Experimental results show that the proposed algorithm has a higher F-measure value of 0.24 than the conventional lamp pairing-based detection methods, on average. In addition, the proposed algorithm shows a fast processing time of 6.4 ms per frame, which verifies real-time performance of the proposed algorithm.

• Journal of Communications and Networks
• /
• 제18권3호
• /
• pp.502-512
• /
• 2016

The wireless carrier sense multiple access with collision detection (WCSMA/CD) and carrier sense multiple access with collision resolution (CSMA/CR) protocols are considered representative distributed collision detection protocols for fully connected dense wireless local area networks. These protocols identify collisions through additional short-sensing within a collision detection (CD) period after the start of data transmission. In this study, we analyze their throughput numerically and show that the throughput has a trade-off that accords with the length of the CD period. Consequently, we obtain the optimal length of the CD period that maximizes the throughput as a closed-form solution. Analysis and simulation results show that the throughput of distributed collision detection protocols is considerably improved when the optimal CD period is allocated according to the number of stations and the length of the transmitted packet.

• 한국정보통신학회논문지
• /
• 제12권5호
• /
• pp.843-848
• /
• 2008

얼굴 검출은 대부분 얼굴의 움직임 정보를 이용한다. 기존에 얼굴 검출 방법은 프레임간의 차를 이용하여 움직임을 검출하는 방법이 사용되어 왔으나 대부분이 실시간을 고려하지 않은 수학적 접근법을 사용하거나 알고리즘이 지나치게 복잡하여 실시간 구현에 용이하지 않았다. 본 논문에서는 실시간 얼굴검출을 위하여 감시카메라에서 입력된 RGB 영상을 YCbCr 영상으로 변환한 후 연속된 두 영상의 차를 구하고 Glassfire 라벨링을 실시했다. 라벨링 결과 가장 넓은 구역의 면적과 Area 임계치 값을 비교하여 임계값 이상의 면적이면 동작변환으로 인식하고 영상을 추출하였다. 이렇게 추출된 동작변환 영상을 대상으로 얼굴 검출을 실시하였다. 얼굴 검출에 필요한 특징을 추출하기 위해 AdaBoost 알고리즘을 사용하였다.

• 한국컴퓨터정보학회논문지
• /
• 제23권1호
• /
• pp.25-32
• /
• 2018

In this paper, we propose an edge detection algorithm for auto focus of infrared camera. We designed and implemented the edge detection of infrared image by using a spatial filter on FPGA. The infrared camera should be designed to minimize the image processing time and usage of hardware resource because these days surveillance systems should have the fast response and be low size, weight and power. we applied the $3{\times}3$ mask filter which has an advantage of minimizing the usage of memory and the propagation delay to process filtering. When we applied Laplacian filter to extract contour data from an image, not only edge components but also noise components of the image were extracted by the filter. These noise components make it difficult to determine the focus state. Also a bad pixel of infrared detector causes a problem in detecting the edge components. So we propose an adaptive edge detection filter that is a method to extract only edge components except noise components of an image by analyzing a variance of pixel data in $3{\times}3$ memory area. And we can detect the bad pixel and replace it with neighboring normal pixel value when we store a pixel in $3{\times}3$ memory area for filtering calculation. The experimental result proves that the proposed method is effective to implement the edge detection for auto focus in infrared camera.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.243-248
• /
• 2007

This study proposed a procedure to improve the error defection of attached cadastral maps using digital map data. In addition, this study also provided the direction for the accuracy improvement of attached cadastral maps by comparing analysis methods. - such as centroid, Lee Sallee shape index, and area index. The analysis is performed as follows. First, by using centroid measurement, the center point of cadastral maps and attached cadastral maps are compared. Secondly by using Lee Sallee shape measurement, the location accuracy of range area is investigated. Thirdly, by using area measurement, the range area within allowable error scope is verified. Based on analysis, the discrepancy between cadastral maps and the attacked cadastral maps are detected as follows; 98.2% from Lee Sallee shape index, 41.8% from centroid, 15.4% from area index in the whole error.