The document summarizes the development of a non-contact extensometer system called MTVS (Mobile Tensile Video System) to measure displacement during tensile and compression tests on a materials testing machine. The system uses a microscopic camera mounted on the testing machine's crossbar to optically track displacement of 0.0018 mm or more. It was designed to provide more accurate readings than the existing system in the materials lab at a lower cost than commercially available extensometers. The MTVS software interface allows calibrating the system, viewing displacement readings over time, and comparing its results to the existing system. Validation tests showed the MTVS readings varied more but generally matched the existing system, warranting further investigation.
Modelling of ntc thermistor using artificial neural network for non linearity...ieijjournal
This paper investigates modelling of NTC thermistors using Steinhart-Hart equation for generic model
generation and then parsing the same through the linearization algorithm based on Levenberg–Marquart
back propagation technique with sigmoid activation function. The entire modelling and scripting of the
linearization algorithm has been accomplished in the MATLAB paradigm. The results showcase small
linearity error optimal in the chebyshev norms. The reported technique has a potential for linearization of
other impedance based non-linear sensors as well. Further work is in progress to integrate the algorithm
as a soft IP core in a full custom or semi-custom ASIC wherein thermistors are employed as sensors.
Modelling of ntc thermistor using artificial neural network for non linearity...ieijjournal
This paper investigates modelling of NTC thermistors using Steinhart-Hart equation for generic model
generation and then parsing the same through the linearization algorithm based on Levenberg–Marquart
back propagation technique with sigmoid activation function. The entire modelling and scripting of the
linearization algorithm has been accomplished in the MATLAB paradigm. The results showcase small
linearity error optimal in the chebyshev norms. The reported technique has a potential for linearization of
other impedance based non-linear sensors as well. Further work is in progress to integrate the algorithm
as a soft IP core in a full custom or semi-custom ASIC wherein thermistors are employed as sensors.
AUTOMATIC THEFT SECURITY SYSTEM (SMART SURVEILLANCE CAMERA)csandit
The proposed work aims to create a smart application camera, with the intention of eliminating
the need for a human presence to detect any unwanted sinister activities, such as theft in this
case. Spread among the campus, are certain valuable biometric identification systems at
arbitrary locations. The application monitosr these systems (hereafter referred to as “object”)
using our smart camera system based on an OpenCV platform.
By using OpenCV Haar Training, employing the Viola-Jones algorithm implementation in
OpenCV, we teach the machine to identify the object in environmental conditions. An added
feature of face recognition is based on Principal Component Analysis (PCA) to generate Eigen
Faces and the test images are verified by using distance based algorithm against the eigenfaces,
like Euclidean distance algorithm or Mahalanobis Algorithm.
If the object is misplaced, or an unauthorized user is in the extreme vicinity of the object, an
alarm signal is raised.
Overview of behavioural understanding system with filtered vision sensor (Sua...Karel Van Isacker
Overview of behavioural understanding system with filtered vision sensor (Suad Albawendi, Kofi Appiah, Heather Powell and Ahmad Lotfi)
Interactive Technologies and Games (ITAG) Conference 2015
Health, Disability and EducationDates: Thursday 22 October 2015 - Friday 23 October 2015 Location: The Council House, NG1 2DT
A Flexible Scheme for Transmission Line Fault Identification Using Image Proc...IJEEE
This paper describes a methodology that aims to find and diagnosing faults in transmission lines exploitation image process technique. The image processing techniques have been widely used to solve problem in process of all areas. In this paper, the methodology conjointly uses a digital image process Wavelet Shrinkage function to fault identification and diagnosis. In other words, the purpose is to extract the faulty image from the source with the separation and the co-ordinates of the transmission lines. The segmentation objective is the image division its set of parts and objects, which distinguishes it among others in the scene, are the key to have an improved result in identification of faults.The experimental results indicate that the proposed method provides promising results and is advantageous both in terms of PSNR and in visual quality.
Quaternion Based Omnidirectional Machine Condition Monitoring SystemCSCJournals
Thermal monitoring is useful for revealing some serious electrical problems in a factory that often go undetected until a serious breakdown occurs. In factories, there are various types of functioning machines to be monitored. When there is any malfunctioning of a machine, extra heat will be generated which can be picked up by thermal camera for image processing and identification purpose. In this paper, a new and effective omnidirectional machine condition monitoring system applying log-polar mapper, quaternion based thermal image correlator and max-product fuzzy neural network classifier is proposed for monitoring machine condition in an omnidirectional view. With this monitoring system, it is convenient to detect and monitor the conditions of (overheat or not) of more than one machines in an omnidirectional view captured by using a single thermal camera. Log-polar mapping technique is used to unwarp omnidirectional thermal image into panoramic form. Two classification characteristics namely: peak to sidelobe ratio (PSR) and real to complex ratio of the discrete quaternion correlation output (p-value) are applied in the proposed machine condition monitoring system. Large PSR and p-value observe in a good match among correlation of the input thermal image with a particular reference image, while small PSR and p-value observe in a bad/not match among correlation of the input thermal image with a particular reference image. Simulation results also show that the proposed system is an efficient omnidirectional machine monitoring system with accuracy more than 97%.
A Survey on Object Detection Methods in Visual Sensor Networks ijassn
Object detection is one of the major challenges in visual sensor networks (VSNs) which is set up in the
monitoring applications. Many approaches proposed to solve the object detection problem in VSNs,
considering diverse metrics such as reliability, energy consumption, detection accuracy and being realtime.
In this paper, a survey on the object detection methods in visual sensor networks is presented for the
first time. Furthermore, this paper classified the methods precisely. Two main object detection categories
in VSNs that explored in this paper are conventional object detection methods and object detection
approaches with the camera nodes involvement. To be more precise, presented survey promotes an
overview of recent object detection methods' literature with their performance evaluation. Also, this
research is challenging and the object detection issue in the visual sensor networks is open caused by
differences in estimations and performance metrics. Therefore, the survey concludes with open research
challenges.
A Study of Motion Detection Method for Smart Home SystemAM Publications
Motion detection surveillance technology give ease for time-consuming reviewing process that a normal video
surveillance system offers. By using motion detection, it save the monitoring time and cost. It has gained a lot of interests
over the past few years. In this paper, a proposed motion detection surveillance system, through the study and evaluation
of currently available different methods. The proposed system is efficient and convenient for both office and home uses as
a smart home security system technology.
A Solution to Partial Observability in Extended Kalman Filter Mobile Robot Na...TELKOMNIKA JOURNAL
Partial observability in EKF based mobile robot navigation is investigated in this paper to find a
solution that can prevent erroneous estimation. By only considering certain landmarks in an environment,
the computational cost in mobile robot can be reduced but with an increase of uncertainties to the system.
This is known as suboptimal condition of the system. Fuzzy Logic technique is proposed to ensure that the
estimation achieved desired performance even though some of the landmarks were excluded for
references. The Fuzzy Logic is applied to the measurement innovation of Kalman Filter to correct the
positions of both mobile robot and any observed landmarks during observations. The simulation results
shown that the proposed method is capable to secure reliable estimation results even a number of
landmarks being excluded from Kalman Filter update process in both Gaussian and non-Gaussian noise
conditions.
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...aciijournal
Forward Collision Avoidance (FCA) systems in automobiles is an essential part of Advanced Driver Assistance System (ADAS) and autonomous vehicles. These devices currently use, radars as the main sensor. The increasing resolution of camera sensors, processing capability of hardware chipsets and advances in image processing algorithms, have been pushing the camera based features recently. Monocular cameras face the challenge of accurate scale estimation which limits it use as a stand-alone sensor for this application. This paper proposes an efficient system which can perform multi scale object
detection which is being patent granted and efficient 3D reconstruction using structure from motion (SFM)
framework. While the algorithms need to be accurate it also needs to operate real time in low cost
embedded hardware. The focus of the paper is to discuss how the proposed algorithms are designed in such
a way that it can be provide real time performance on low cost embedded CPU’s which makes use of only Digital Signal processors (DSP) and vector processing cores.
Automated Traffic sign board classification system is one of the key technologies of Intelligent
Transportation Systems (ITS). Traffic Surveillance System is being more and important with improving
urban scale and increasing number of vehicles. This Paper presents an intelligent sign board
classification method based on blob analysis in traffic surveillance. Processing is done by three main
steps: moving object segmentation, blob analysis, and classifying. A Sign board is modelled as a
rectangular patch and classified via blob analysis. By processing the blob of sign boards, the meaningful
features are extracted. Tracking moving targets is achieved by comparing the extracted features with
training data. After classifying the sign boards the system will intimate to user in the form of alarms,
sound waves. The experimental results show that the proposed system can provide real-time and useful
information for traffic surveillance.
AUTOMATIC THEFT SECURITY SYSTEM (SMART SURVEILLANCE CAMERA)csandit
The proposed work aims to create a smart application camera, with the intention of eliminating
the need for a human presence to detect any unwanted sinister activities, such as theft in this
case. Spread among the campus, are certain valuable biometric identification systems at
arbitrary locations. The application monitosr these systems (hereafter referred to as “object”)
using our smart camera system based on an OpenCV platform.
By using OpenCV Haar Training, employing the Viola-Jones algorithm implementation in
OpenCV, we teach the machine to identify the object in environmental conditions. An added
feature of face recognition is based on Principal Component Analysis (PCA) to generate Eigen
Faces and the test images are verified by using distance based algorithm against the eigenfaces,
like Euclidean distance algorithm or Mahalanobis Algorithm.
If the object is misplaced, or an unauthorized user is in the extreme vicinity of the object, an
alarm signal is raised.
Overview of behavioural understanding system with filtered vision sensor (Sua...Karel Van Isacker
Overview of behavioural understanding system with filtered vision sensor (Suad Albawendi, Kofi Appiah, Heather Powell and Ahmad Lotfi)
Interactive Technologies and Games (ITAG) Conference 2015
Health, Disability and EducationDates: Thursday 22 October 2015 - Friday 23 October 2015 Location: The Council House, NG1 2DT
A Flexible Scheme for Transmission Line Fault Identification Using Image Proc...IJEEE
This paper describes a methodology that aims to find and diagnosing faults in transmission lines exploitation image process technique. The image processing techniques have been widely used to solve problem in process of all areas. In this paper, the methodology conjointly uses a digital image process Wavelet Shrinkage function to fault identification and diagnosis. In other words, the purpose is to extract the faulty image from the source with the separation and the co-ordinates of the transmission lines. The segmentation objective is the image division its set of parts and objects, which distinguishes it among others in the scene, are the key to have an improved result in identification of faults.The experimental results indicate that the proposed method provides promising results and is advantageous both in terms of PSNR and in visual quality.
Quaternion Based Omnidirectional Machine Condition Monitoring SystemCSCJournals
Thermal monitoring is useful for revealing some serious electrical problems in a factory that often go undetected until a serious breakdown occurs. In factories, there are various types of functioning machines to be monitored. When there is any malfunctioning of a machine, extra heat will be generated which can be picked up by thermal camera for image processing and identification purpose. In this paper, a new and effective omnidirectional machine condition monitoring system applying log-polar mapper, quaternion based thermal image correlator and max-product fuzzy neural network classifier is proposed for monitoring machine condition in an omnidirectional view. With this monitoring system, it is convenient to detect and monitor the conditions of (overheat or not) of more than one machines in an omnidirectional view captured by using a single thermal camera. Log-polar mapping technique is used to unwarp omnidirectional thermal image into panoramic form. Two classification characteristics namely: peak to sidelobe ratio (PSR) and real to complex ratio of the discrete quaternion correlation output (p-value) are applied in the proposed machine condition monitoring system. Large PSR and p-value observe in a good match among correlation of the input thermal image with a particular reference image, while small PSR and p-value observe in a bad/not match among correlation of the input thermal image with a particular reference image. Simulation results also show that the proposed system is an efficient omnidirectional machine monitoring system with accuracy more than 97%.
A Survey on Object Detection Methods in Visual Sensor Networks ijassn
Object detection is one of the major challenges in visual sensor networks (VSNs) which is set up in the
monitoring applications. Many approaches proposed to solve the object detection problem in VSNs,
considering diverse metrics such as reliability, energy consumption, detection accuracy and being realtime.
In this paper, a survey on the object detection methods in visual sensor networks is presented for the
first time. Furthermore, this paper classified the methods precisely. Two main object detection categories
in VSNs that explored in this paper are conventional object detection methods and object detection
approaches with the camera nodes involvement. To be more precise, presented survey promotes an
overview of recent object detection methods' literature with their performance evaluation. Also, this
research is challenging and the object detection issue in the visual sensor networks is open caused by
differences in estimations and performance metrics. Therefore, the survey concludes with open research
challenges.
A Study of Motion Detection Method for Smart Home SystemAM Publications
Motion detection surveillance technology give ease for time-consuming reviewing process that a normal video
surveillance system offers. By using motion detection, it save the monitoring time and cost. It has gained a lot of interests
over the past few years. In this paper, a proposed motion detection surveillance system, through the study and evaluation
of currently available different methods. The proposed system is efficient and convenient for both office and home uses as
a smart home security system technology.
A Solution to Partial Observability in Extended Kalman Filter Mobile Robot Na...TELKOMNIKA JOURNAL
Partial observability in EKF based mobile robot navigation is investigated in this paper to find a
solution that can prevent erroneous estimation. By only considering certain landmarks in an environment,
the computational cost in mobile robot can be reduced but with an increase of uncertainties to the system.
This is known as suboptimal condition of the system. Fuzzy Logic technique is proposed to ensure that the
estimation achieved desired performance even though some of the landmarks were excluded for
references. The Fuzzy Logic is applied to the measurement innovation of Kalman Filter to correct the
positions of both mobile robot and any observed landmarks during observations. The simulation results
shown that the proposed method is capable to secure reliable estimation results even a number of
landmarks being excluded from Kalman Filter update process in both Gaussian and non-Gaussian noise
conditions.
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...aciijournal
Forward Collision Avoidance (FCA) systems in automobiles is an essential part of Advanced Driver Assistance System (ADAS) and autonomous vehicles. These devices currently use, radars as the main sensor. The increasing resolution of camera sensors, processing capability of hardware chipsets and advances in image processing algorithms, have been pushing the camera based features recently. Monocular cameras face the challenge of accurate scale estimation which limits it use as a stand-alone sensor for this application. This paper proposes an efficient system which can perform multi scale object
detection which is being patent granted and efficient 3D reconstruction using structure from motion (SFM)
framework. While the algorithms need to be accurate it also needs to operate real time in low cost
embedded hardware. The focus of the paper is to discuss how the proposed algorithms are designed in such
a way that it can be provide real time performance on low cost embedded CPU’s which makes use of only Digital Signal processors (DSP) and vector processing cores.
Automated Traffic sign board classification system is one of the key technologies of Intelligent
Transportation Systems (ITS). Traffic Surveillance System is being more and important with improving
urban scale and increasing number of vehicles. This Paper presents an intelligent sign board
classification method based on blob analysis in traffic surveillance. Processing is done by three main
steps: moving object segmentation, blob analysis, and classifying. A Sign board is modelled as a
rectangular patch and classified via blob analysis. By processing the blob of sign boards, the meaningful
features are extracted. Tracking moving targets is achieved by comparing the extracted features with
training data. After classifying the sign boards the system will intimate to user in the form of alarms,
sound waves. The experimental results show that the proposed system can provide real-time and useful
information for traffic surveillance.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
International Journal of Engineering Inventions (IJEI) provides a multidisciplinary passage for researchers, managers, professionals, practitioners and students around the globe to publish high quality, peer-reviewed articles on all theoretical and empirical aspects of Engineering and Science.
Towards Rapid Implementation of Adaptive Robotic SystemsMeshDynamics
Current automation design practice produces expensive one-of-a-kind installations where the system cannot be easily modified to
meet changing demands or advancements in technology. It is imperative that we design robot systems to be modular, portable and
easily re-configurable in order to reduce the design lead times and life cycle costs of providing automation alternatives.
The Unified Tele-robotics Architecture Program (UTAP) was developed under the sponsorship of the US Air Force Robotics and
Automation Center of Excellence. A goal of the program was to define and develop prototypes of commonly used software building
blocks for sensor guided real time embedded control of telerobotic devices. Standard building blocks and a non-proprietary
communication protocols would provide the Air Force and specifically the Logistic Centers with a support infrastructure designed to
rapidly and efficiently build and maintain mission critical automation systems.
IRJET- Traffic Sign Classification and Detection using Deep Learning
MTVS Poster
1. The error was statistically assessed:
N = number of tests
X = difference in reading
Y = Length of test piece post test
𝑥
𝑛
=
5.044
8
= x = 0.6305
𝑦
𝑛
=
626.491
8
= y
= 78.3114
y
x
= 0.00805 = 0.805 % 𝑒𝑟𝑟𝑜𝑟
Developing the ProgramDeveloping the Solution
Morven Gannon, 3rd Year, Automation Engineering - DT003/A
Abstract & Objectives
Read displacement at an extremely high resolution during a tensile or compression test, data logs the results and acts as a mobile microscope
Present transmission of the displacement information
Objective 1 Define the systems present deficiencies, the operation and procedure of a tensile test
using D.I.T’s Lloyd LR30K, and the test samples used.
Objective 2 Compare the contact and non-contact extensometer systems on the market, and assess
an ideal solution
Objective 3 Upon determining an alternative, investigate its properties and applications.
Objective 4 Design and build a fully functional non-contact extensometer for D.I.T’s tensile test
machine at a reasonable price, using available software.
Objective 5 Develop an interface that is comprehensive to use, with a calibration capability and user
defined functionality.
Objective 6 Evaluate the performance of the system and refine the output to gain comparable and if
possible improved readings than the present system.
Objective 7 Enable the user to observe the difference between the new systems displacement
readings and Nexygen output.
Test
Piece
Holding
Apparatus
Cross
bar
Twin
Drive
Screws
Servo
Motor
Drive
Belt
Encoder
Disc
Nexygen
Software
Defining the Problem
The project benefitted from having regular access to the D.I.T
Materials Lab. This enabled a continuous assessment of the needs
and wants of the customer. An initial ‘Voice of Customer’
questionnaire helped define the problem and continual input helped
to define the solution.
The internal optical decoder works on the
standard principle of a digital rotary encoder.
It is mounted in its own unit and rotated by a
belt drive attached to the main shaft of the
large servo motor that drives the twin screws
that lower or heighten the cross bar.
The Lloyds LR30K Materials Testing Machine located in DIT
Bolton Street materials laboratory has been proven to give
inaccurate extensometer readings. This generates inaccurate
strain data that has an adverse effect on materials tests results.
The alternative extensometers available from the vendor or on
the market are beyond the materials labs budget.
The principle objective of this project and the report is to
resolve this problem by analysing the problem, investigating
alternative extensometer systems, developing an alternative
and then building, programming and installing it.
This solution would take the form of a vision system.
The resulting ‘MTVS’ system is capable of reading a
displacement as small as 1.8 micrometres. It has an inbuilt
calibration function, a comprehensive UI and a comparison
graph that represents both the Nexygen and the MTVS
displacement readings.
As an extra feature, it can also be used as a mobile microscopic
measuring device.
The system has been validated and the primary user is satisfied
with the end product. In order to achieve this end, a list of
objectives was set:
The imaging device used is a TE70 Microscopic USB
camera. It is the best available way to read displacement to
the required resolution.
It is clamped to the cross bar of the Lloyds LR30k Materials
Testing Machine gantry and translates a change in
displacement of the target image.
This is converted into a numerical value and written to file
and drawn to graph as a stress and strain graph. There is
also a mobile microscope interface function that can be used
as a microscopic measuring device. The software used is NI
IMAQ Vision and the core function of the system for the
displacement tests is the IMAQ Optical Flow VI, set to
track the movement of a single pixel on the Y axis.
The decision to mount the camera on the
crossbar was vital to the entire direction of the
project, and the only viable solution without
purchasing purpose built cameras, housing and
lenses.
Initially the project was directed at observing
the change in position of a mark on the test
subject held in the jaws of the Lloyds LR30K.
If the camera to be used is a USB Microscopic
camera then in order to keep the image
onscreen, the camera would have to move with
it. This is not an option, so directing the
camera at a static background and measuring
the movement of the camera on the Y axis
became the only viable solution. By mounting
the camera on the crossbar of the LR30K and
reading an upward or downward
displacement, the user could determine with
fewer degrees of separation between the test
piece and the software output (see Firgure.18) a
displacement in micrometres. If the degrees of
separation between the test piece and software
are diminished, and the extra element of no
mechanical contact is introduced to the system,
then it should be possible to reduce an error in
reading.
The research into available solutions and the results from the customer survey and ongoing input indicated that
the best way to attain more accurate readings for D.I.T’s Lloyds LR30K materials testing machine, without
purchasing the expensive vendor specific plug and play unit, or another extensometer system was to design and
build a PC based optical vision system extensometer to determine displacement.
Transmission of the displacement information with MTVS System
Test Piece
Holding
Apparatus
Crossbar
Camera
Clamp
Camera
MTVS
Software
The Physical Build
The physical placement of the camera required a
clamp to hold it in place. This clamp had to absorb
the maximum amount of vibration the LR30K would
commonly produce. As the field of vision would only
cover 1mm², and the distance from the subject image
would be 3mm maximum, a slight jolt could knock the
image off target and out of focus very easily. The
moment of fracture of a typical dog bone steel sample
is the most commonly occurring event where vibration
would be a real concern.
Tests where carried out to determine the extent of this
jolt, but the image retained its position, so the
materials chosen for the build are inexpensive
overcompensation.
With over 24 purpose built SUB VI’s
the programming is extensive and
detailed. The heart of the tensile and
compression testing function is the
IMAQ Optical Flow LKP VI. This
calculates the optical movement
(velocity flow) in the image using the
Lucas and Kanede algorithm. The
method is a widely used differential
calculation to estimate that the
movement is equal in the pixels close to
the particle selected to track, and it
assumes that the movement between
frames is consistent and steady. It
statistically estimates the location of the
particle.
The Calibration Gauge VI function is
one of many sub structures in the
program .
This is the function that overlays the 5
reference lines that are overlaid in
proportion to the 100 micrometre
graticule slide markings by the user to
calibrate the system.
Building the UI
The design of the UI is both functional
and intuitive. The extra feature of the
mobile microscope function was added
and fulfils the adaptability brief of the
project.
To operate for a simple tensile test the
user will run through a designated
sequence in tandem with the Nexygen test
set-up procedure.
The results will be defined in the output
graphs on the next tab and user designated
text files.
The image can be calibrated remotely
provided the same model of the camera is
used as the one mounted on the LR30K
The user can run the MTVS from any of
the PC’s within the materials lab and
potentially transfer the program to any PC
with the required LabVIEW software.
The particle
starts here
Change in displacement
The image
moves in an
upward
direction
Nexygen Load vs Displacement
Nexygen Load vs Displacement
System Validation
In order to prove the success of the project a series of tests
where undertaken to match the output of the MTVS system
with the output of the Nexygen system by doing 6 simple
compression test using exactly the same settings. The test
selected was a ‘Compress to Limit General Purpose Test’,
set to move 0.5mm at a speed of 3mm per second. This very
slow and slight movement helped to prove the resolution of
the MTVS system and offered a comparative reference
between systems.
The graph image, taken from the ‘Document and Graph’ tab
shows the variability in signal of the MTVS as opposed to
the steady state reading of the Nexygen suggests two
possibilities:
1. The MTVS system is giving far greater accuracy and precision in its reading, indicating that the Nexygen software
is acting solely on the basis that the motor is turning.
2. The nature of the statistical approximations of the IMAQ LKP Optical Flow are fluctuating the position of the
target particle.
But if the linear Nexygen output is correct, then at this resolution, why vibration is not accounted for or even
represented. The similarity in the signals is a clear indication that they are reading the same result, but in two areas
specifically (the first rise of load and the final signal at the end of the displacement) there is a clear discrepancy. This
was repeated in 5 of the 6 tests. This clearly warrants further investigation.