scholarly journals Hydrographic data inspection and disaster monitoring using shipborne radar small range images with electronic navigation chart

2020 ◽  
Vol 6 ◽  
pp. e290
Author(s):  
Jin Xu ◽  
Baozhu Jia ◽  
Xinxiang Pan ◽  
Ronghui Li ◽  
Liang Cao ◽  
...  
Keyword(s):  
Extraction Methods ◽  
Geometric Feature ◽  
Signal Acquisition ◽  
Small Range ◽  
Hydrographic Data ◽  
Radar Images ◽  
Target Segmentation ◽  
Information Matching ◽  
Disaster Monitoring ◽  
Remote Sensing Image Processing

Shipborne radars cannot only enable navigation and collision avoidance but also play an important role in the fields of hydrographic data inspection and disaster monitoring. In this paper, target extraction methods for oil films, ships and coastlines from original shipborne radar images are proposed. First, the shipborne radar video images are acquired by a signal acquisition card. Second, based on remote sensing image processing technology, the radar images are preprocessed, and the contours of the targets are extracted. Then, the targets identified in the radar images are integrated into an electronic navigation chart (ENC) by a geographic information system. The experiments show that the proposed target segmentation methods of shipborne radar images are effective. Using the geometric feature information of the targets identified in the shipborne radar images, information matching between radar images and ENC can be realized for hydrographic data inspection and disaster monitoring.

Geometric Feature Extraction of Ship in High-resolution Synthetic Aperture Radar Images

2018 ◽  
Vol 47 (1) ◽  
pp. 110001
Author(s):  
熊伟 XIONG Wei ◽  
徐永力 XU Yong-li ◽  
崔亚奇 CUI Ya-qi ◽  
李岳峰 LI Yue-feng
Keyword(s):  
Feature Extraction ◽  
High Resolution ◽  
Synthetic Aperture Radar ◽  
Synthetic Aperture ◽  
Geometric Feature ◽  
Radar Images ◽  
Geometric Feature Extraction ◽  
Aperture Radar

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 5 (1) ◽  
pp. 35 ◽  
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

scholarly journals Review on Active and Passive Remote Sensing Techniques for Road Extraction

2021 ◽  
Vol 13 (21) ◽  
pp. 4235
Author(s):  
Jianxin Jia ◽  
Haibin Sun ◽  
Changhui Jiang ◽  
Kirsi Karila ◽  
Mika Karjalainen ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Data Acquisition ◽  
Remote Sensing Data ◽  
Extraction Methods ◽  
Data Sources ◽  
Road Extraction ◽  
Multiple Sources ◽  
Radar Images ◽  
Combined Application ◽  
Remote Sensing Techniques

Digital maps of road networks are a vital part of digital cities and intelligent transportation. In this paper, we provide a comprehensive review on road extraction based on various remote sensing data sources, including high-resolution images, hyperspectral images, synthetic aperture radar images, and light detection and ranging. This review is divided into three parts. Part 1 provides an overview of the existing data acquisition techniques for road extraction, including data acquisition methods, typical sensors, application status, and prospects. Part 2 underlines the main road extraction methods based on four data sources. In this section, road extraction methods based on different data sources are described and analysed in detail. Part 3 presents the combined application of multisource data for road extraction. Evidently, different data acquisition techniques have unique advantages, and the combination of multiple sources can improve the accuracy of road extraction. The main aim of this review is to provide a comprehensive reference for research on existing road extraction technologies.

scholarly journals Detecting Ephemeral Objects in SAR Time-Series Using Frozen Background-Based Change Detection

2020 ◽  
Vol 12 (11) ◽  
pp. 1720
Author(s):  
Thibault Taillade ◽  
Laetitia Thirion-Lefevre ◽  
Régis Guinvarc’h
Keyword(s):  
Change Detection ◽  
Signal To Noise Ratio ◽  
Open Data ◽  
Ground Truth ◽  
Critical Issue ◽  
Detection Methods ◽  
Reference Image ◽  
Radar Images ◽  
Multi Temporal ◽  
Disaster Monitoring

Change detection (CD) in SAR (Synthethic Aperture Radar) images has been widely studied in recent years and has become increasingly attractive due to the growth of available datasets. The potential of CD has been shown in different fields, including disaster monitoring and military applications. Access to multi-temporal SAR images of the same scene is now possible, and therefore we can improve the performance and the interpretation of CD. Apart from specific SAR campaign measurements, the ground truth of the scene is usually unknown or only partially known when dealing with open data. This is a critical issue when the purpose is to detect targets, such as vehicles or ships. Indeed, typical change detection methods can only provide relative changes; the actual number of targets on each day cannot be determined. Ideally, this change detection should occur between a target-free image and one with the objects of interest. To do so, we propose to benefit from pixels’ intrinsic temporal behavior to compute a frozen background reference (FBR) image and perform change detection from this reference image. We will then consider that the scene consists only of immobile objects (e.g., buildings and trees) and removable objects that can appear and disappear from acquisition to another (e.g., cars and ships). Our FBR images will, therefore, aim to estimate the immobile background of the scene to obtain, after change detection, the exact amount of targets present on each day. This study was conducted first with simulated SAR data for different number of acquisition dates and Signal-to-Noise Ratio (SNR). We presented an application in the region of Singapore to estimate the number of ships in the study area for each acquisition.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35 ◽  
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

New form of Transmission Cross Coefficient for High-Resolution Imaging

1990 ◽  
Vol 48 (1) ◽  
pp. 60-61
Author(s):  
Kazuo Ishizuka
Keyword(s):  
Electron Microscope ◽  
High Resolution ◽  
Transmission Function ◽  
Incident Beam ◽  
Optical Microscope ◽  
Strong Interactions ◽  
Small Range ◽  
Specimen Thickness ◽  
Beam Direction ◽  
Diffracted Waves

It is well known that taking into account spacial and temporal coherency of illumination as well as the wave aberration is important to interpret an image of a high-resolution electron microscope (HREM). This occues, because coherency of incident electrons restricts transmission of image information. Due to its large spherical and chromatic aberrations, the electron microscope requires higher coherency than the optical microscope. On an application of HREM for a strong scattering object, we have to estimate the contribution of the interference between the diffracted waves on an image formation. The contribution of each pair of diffracted waves may be properly represented by the transmission cross coefficients (TCC) between these waves. In this report, we will show an improved form of the TCC including second order derivatives, and compare it with the first order TCC.In the electron microscope the specimen is illuminated by quasi monochromatic electrons having a small range of illumination directions. Thus, the image intensity for each energy and each incident direction should be summed to give an intensity to be observed. However, this is a time consuming process, if the ranges of incident energy and/or illumination direction are large. To avoid this difficulty, we can use the TCC by assuming that a transmission function of the specimen does not depend on the incident beam direction. This is not always true, because dynamical scattering is important owing to strong interactions of electrons with the specimen. However, in the case of HREM, both the specimen thickness and the illumination angle should be small. Therefore we may neglect the dependency of the transmission function on the incident beam direction.

Sign in / Sign up

Export Citation Format

Share Document