• 수산해양기술연구
• /
• 제38권3호
• /
• pp.249-255
• /
• 2002

소형 레이더 신호를 정량적으로 분석하여 해상물표의 운동정보를 실시간으로 추출 및 표시하기 위한 radar target extractor(RTX)를 개발하고, 이 장치를 소형 레이더 장치에 부착시켜 소형 연근해 어선에서도 타선의 진운동정보나 충돌회피정보와 같은 각종의 항해정보를 활용토록 하기 위한 연구를 수행하였다. 본 연구에서 개발한 RTX는 IBM PC 의 ISA bus를 통해 데이터를 입출력할 수 있도록 설계된 신호처리장치로서, 일반 선박용 레이더에서 출력되는 video signal, trigger, antenna bearing pulse, antenna heading mark를 직접 입력할 수 있도록 하였다. 이 장치는 레이더 펄스신호가 해상에 존재하는 물표로부터 반사되어 수신될 때, 그 물표의 신호정보 및 위치좌표정보를 PC 의 CPU 에 의해 처리하지 않고 RTX 자체에 내장된 전용 DSP를 이용하여 실시간으로 처리하도록 하였다. 이 장치에 서 video 신호는 analog devices 사의 AD9042 (12 bit, 40 MHZ monolithic A/D converter)를 이용하여 digital 신호로 변환되고, 그 화상 신호는 CRT에 PPI 방식으로 표시되었다. 이 때 안테나가 회전하면서 탐지한 레이더 물표의 echo 신호는 echo 신호의 강도가 증가하면서 다른 물표의 위치와 구별되면 하나의 물표로서 판정한다. 이 경우, 표적식별 알고리즘은 물표가 미리 설정한 물표포착영역(target acquiring zone)내에 있고, 해당 물표의 크기와 다른 물표와의 거리등에 대한 데이터가 식별기준을 만족하는가에 대한 처리를 수행하도록 개발되었다. 본 연구는 현재 소형어선에 탑재되고 있는 소형레이더의 성능 향상에 크게 기여할 것으로 판단되고, 또한 소형어선용 저가형 ARPA 시스템의 국산화에 필요한 기반기술을 제공할 수 있을 것으로 판단된다.

• 한국연초학회지
• /
• 제36권1호
• /
• pp.26-33
• /
• 2014

Simultaneous determination of crop protection agents(CPAs) in food are done with multi-residue methods, which are composed of sample clean-up, concentration, chromatographic separation and detection. Stir Bar Sorptive Extraction(SBSE) technique is used for sample preparation of various analytes in several fields. The aim of this study was to develop a sensitive and fast method based on SBSE followed by thermal desorption - gas chromatography - mass spectrometry(TD - GC/MS) to determine CPAs in tobacco sample. For the analysis of tobacco sample prior to the SBSE method, solvent extraction or ultrasound-assisted solvent extraction was performed. methanol was used as the extraction solvent. The extract was then diluted with water. Finally, the sample was subjected to SBSE. A method for fast screening of crop protection agents in tobacco using SBSE-TD - GC/MS has been developed. About 17 CPAs including organochlorine, organophosphorous and others were identified and quantified. This method showed good linearity and high sensitivity for most of the target CPAs. The method was applied to the determination of CPAs at ng/mL levels in tobacco sample. This method is simple, rapid and may be applied in detection of other components.

• 대한원격탐사학회지
• /
• 제37권1호
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4476-4491
• /
• 2021

Video service providers tend to face user network problems in the process of transmitting video streams. They strive to provide user with superior video quality in a limited bitrate environment. It is necessary to accurately determine the target bitrate range of the video under different quality requirements. Recently, several schemes have been proposed to meet this requirement. However, they do not take the impact of visual influence into account. In this paper, we propose a new multi-category model to accurately predict the target bitrate range with target visual quality by machine learning. Firstly, a dataset is constructed to generate multi-category models by machine learning. The quality score ladders and the corresponding bitrate-interval categories are defined in the dataset. Secondly, several types of spatial-temporal features related to VMAF evaluation metrics and visual factors are extracted and processed statistically for classification. Finally, bitrate prediction models trained on the dataset by RandomForest classifier can be used to accurately predict the target bitrate of the input videos with target video quality. The classification prediction accuracy of the model reaches 0.705 and the encoded video which is compressed by the bitrate predicted by the model can achieve the target perceptual quality.

• 한국군사과학기술학회지
• /
• 제25권5호
• /
• pp.443-461
• /
• 2022

Target Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.

• 한국멀티미디어학회논문지
• /
• 제19권10호
• /
• pp.1775-1781
• /
• 2016

Generally, in the underwater target recognition, feature vectors are extracted from the target signal utilizing spatial information according to target shape/material characteristics. In addition, various signal processing techniques have been studied to extract feature vectors which are less sensitive to the location of the receiver. In this paper, we synthesized active echo signals using 3-dimensional highlight distribution. Then, Fractional Fourier transform was applied to echo signals to extract signal features. For the performance verification, classification experiments were performed using backpropagation and probabilistic neural network classifiers based on single aspect and multi-aspect method. As a result, we obtained a better recognition result using proposed feature extraction and multi-aspect based method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1387-1389
• /
• 1987

In this paper, we describe not only extraction method of moving object by difference image but also automatic target tracking algorithm. Proposed algorithm track the moving target by the calculation of moving target's center. The results show that this algorithm can apply to practical device such as real time target tracker.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.158.5-158
• /
• 2001

Monopulse active homing radar requires velocity and angle information of target to track fast moving target. Target velocity can be estimated by measuring the frequency shift between transmitted and received frequencies. Angle information is obtained by measuring boresight error. Measurement of doppler frequency component in received signal is done through FFT analysis and interpolation algorithm for fine tuning. Boresight errors in azimuth and elevation axes are proportional to the power of each difference channel relative to sum channel. The target signal power in difference channel is estimated more precisely by measuring the power of FFT result cell of maximum ...

• 한국전자파학회논문지
• /
• 제27권6호
• /
• pp.539-544
• /
• 2016

본 논문에서는 위상비교모노펄스에서 근접한 두 표적의 위치를 추정하는 방법을 제시하였다. 제안한 방법은 Sherman의 기법을 근간으로 하기 때문에 기존 다른 기법들과 달리 단일표적상황에서도 사용할 수 있으며, 오직 단일 펄스만을 사용하여 근접한 두 표적의 위치를 추정하기 때문에 기존 Sherman이 제시한 기법의 단점도 개선할 수 있었다. 제안한 방법의 각도 추정 정확도는 시뮬레이션을 통해 증명하였다.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.148-153
• /
• 2007

In this paper, the evolutionary adaptive wavelet transform(EAWT) is applied to the scattering analysis of radar target. EAWT algorithm uses evolutionary programming for the time-frequency parameter extraction instead of FFT and the bisection search method used in the conventional adaptive wavelet transform(AWT). Therefore, the EAWT has a better performance than the conventional AWT. In the simulation using wire target(Airbus-like), the comparisons with the conventional AWT are presented to show the superiority of the EAWT algorithm in the analysis of scattering phenomenology. The EAWT can be effectively applied to the radar target recognition.