Application of feature descriptors to low-pixel-count persistent surveillance tracking systems

2013 ◽  
Author(s):  
Jason Edelberg ◽  
Christopher Miller ◽  
Michael Wilson
Keyword(s):  
Tracking Systems ◽  
Feature Descriptors

GPS and GSM Based Tracking System for Objects Moving over Wide Geographical Areas

2018 ◽  
Vol 2 (1) ◽  
Author(s):  
Fatima Ameen ◽  
Ziad Mohammed ◽  
Abdulrahman Siddiq
Keyword(s):  
Global Positioning System ◽  
Mobile Communications ◽  
Moving Objects ◽  
Tracking System ◽  
Geographical Area ◽  
Tracking Systems ◽  
Acceptable Result ◽  
Internet Service ◽  
Global Positioning ◽  
Tracking Objects

Tracking systems of moving objects provide a useful means to better control, manage and secure them. Tracking systems are used in different scales of applications such as indoors, outdoors and even used to track vehicles, ships and air planes moving over the globe. This paper presents the design and implementation of a system for tracking objects moving over a wide geographical area. The system depends on the Global Positioning System (GPS) and Global System for Mobile Communications (GSM) technologies without requiring the Internet service. The implemented system uses the freely available GPS service to determine the position of the moving objects. The tests of the implemented system in different regions and conditions show that the maximum uncertainty in the obtained positions is a circle with radius of about 16 m, which is an acceptable result for tracking the movement of objects in wide and open environments.

Decoupling of high gain multivariable tracking systems

1983 ◽  
Author(s):  
D. RIDGELY ◽  
S. BANDA ◽  
J. DAZZO
Keyword(s):  
High Gain ◽  
Tracking Systems

Analysis and Simulation of Altimeter Performance for the Production of Ice Sheet Topographic Maps

1986 ◽  
Vol 8 ◽  
pp. 141-145 ◽  
Author(s):  
K.C. Partington ◽  
C.G. Rapley
Keyword(s):  
High Precision ◽  
Systems Analysis ◽  
Ice Sheets ◽  
Ice Sheet ◽  
Data Interpretation ◽  
Topographic Maps ◽  
Error Signal ◽  
Tracking Systems ◽  
Tracking Mode ◽  
Non Linear

Satellite-borne, radar altimeters have already demonstrated an ability to produce high-precision, topographic maps of the ice sheets. Seasat operated in a tracking mode, designed for use over oceans, but successfully tracked much of the flatter regions of the ice sheet to ± 72° latitude. ERS-1 will extend coverage to ± 82° latitude and will be equipped with an ocean mode similar to that of Seasat and an ice mode designed to permit tracking of the steeper, peripheral regions. The ocean mode will be used over the flatter regions, because of its greater precision.Altimeter performance over the ice sheets has been investigated through a study of Seasat tracking behaviour and the use of an altimeter performance simulator, with a view to assessing the likely performance of ERS-1 and the design of improved tracking systems. Analysis of Seasat data shows that lock was frequently lost, as a result of possessing a non-linear height error signal over the width of the range window. Having lost lock, the tracker frequently failed to transfer rapidly and effectively to track mode. Use of the altimeter performance simulator confirms many of the findings from Seasat data and it is being used to facilitate data interpretation and mapping, through the modelling of waveform sequence.

A Study on Multi Class Classification from Breast Cancer Images using Ensemble Network and Transfer Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Feature Descriptors ◽  
Histopathological Images ◽  
Viable Approach ◽  
Multi Class Classification

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.

Sign in / Sign up

Export Citation Format

Share Document