1 Prepared by: Precise Object Tracking under Deformation Eng. Mohamed Hassan, EAEA Supervised by: Prof. Dr. Hussien Konber, Al Azhar University Prof. Dr. Mohamoud Ashour, EAEA Dr. Ashraf Aboshosha, EAEA Submitted to: Communication & Electronics Dept., Al Azhar University
55
Embed
1 Prepared by: Precise Object Tracking under Deformation Eng. Mohamed Hassan, EAEA Supervised by: Prof. Dr. Hussien Konber, Al Azhar University Prof. Dr.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
1
Prepared by:
Precise Object Tracking under Deformation
Eng. Mohamed Hassan, EAEA
Supervised by: Prof. Dr. Hussien Konber, Al Azhar University
Prof. Dr. Mohamoud Ashour, EAEA
Dr. Ashraf Aboshosha, EAEA
Submitted to:Communication & Electronics Dept.,
Al Azhar University
2
Key subjects of this framework include: Motivation Visual tracking applications Block diagram of object tracking system Image deformation types Object extraction Morphological operations Geometrical Modeling and pose estimation Conclusion and Future Work
Outlines
3
Motivation
The main objectives of this research work are to:
Overcome the imprecision in object tracking caused by different deformation sources such as noise, change of illumination, blurring, scaling and rotation.
Developing a three dimensional (3D) geometrical model to determine the current pose of an object and predict its future location based on FIR model
Presenting a robust ranging technique to track a visual target instead of the traditional expensive ranging sensors.
4
The precise object tracking is an essential issue in several applications such as:
Robot vision Automated surveillance (civil and military) Medical applications Satellite and space systems Traffic systems Security etc.
Visual Tracking Applications
5
Block Diagram of Object Tracking System
Video Camera
USB Camera
USBBus
Frame grabber
PCImage
Acquisition
ImageProcessing
OutputTarget
6
Image Deformation Types
Noise. Scaling &Rotation. Blurring Change of illumination.
7
Definition: is considered to be any measurement that is not part of the phenomena of interest. Images are affected by different types of noise:
Gaussian noise
Salt and Pepper noise
Poisson Noise
Speckle Noise
Image Deformation: Noise
8
Image De-noising Techniques
The following digital filters have been employed for denoising
Linear filter (Average filter, Gaussian filter and unsharp filter)
Non linear filter (Median filter and Adaptive filter)
Coiflet Wavelets
Proposed filter
9
Spatial filtering term is the filtering operations that are performed directly on the pixels of an image.
The process consists simply of moving the filter mask from point to point in an image.
At each point (x,y) the response of the filter at that point is calculated using a predefined relationship.
The result is the sum of products of the mask coefficients with the corresponding pixels directly under the mask
Pixels of image
Mask coefficients
w(-1,-1) w(-1,0) w(-1,1)
w(0,-1) w(0,0) w(0,1)
w(1,-1) w(1,0) w(1,1)
Linear Spatial Filters
11
Nonlinear spatial filters also operate on neighborhoods, and the mechanics of sliding a mask past an image are the same as was just outlined.
The filtering operation is based conditionally on the values of the pixels in the neighborhood under consideration.
Order-statistics filters are nonlinear spatial filters whose response is based on ordering (ranking)
Nonlinear Spatial Filters
12
The Wavelet transform is a multiresolution analysis tool which decomposes a signal into different frequency sub bands.
Wavelet transform, due to its excellent localization, has rapidly become an indispensable signal and image processing tool for a variety of applications.
Wavelet denoising attempts to remove the noise present in the signal while preserving the signal characteristics, regardless of its frequency content.
Wavelet Transform
13
Figure 1 The two-dimensional FWT - the analysis filter
Wavelet Transform
Figure 2 Two-scale of two-dimensional decomposition
14
The proposed filter is a cascaded spatial filter based on median fitter and Coiflet wavelets. Its edge-preserving nature makes it useful in cases where edge blurring is undesirable. It is very useful in real object tracking. This filter is the best one for removing all types of noise
Denoising Proposed Filter
I/p image Median filter Coiflet Wavelets O/p image
Figure 3 Cascaded spatial filter based on median fitter and Coiflet wavelets
15
Image Similarity Measure
To validate the efficiency of the previous digital filters the following similarity measures have been applied
2D Cross Correlation
Peak Signal-to-Noise Ratio (PSNR)dB
22
1 1 1
[ * ]i n i n i n
i x i y i x i yi i i
x m y m x m y m
1020 log IMaxPSNR
MSE
1 12
0 0
1, ( , )
m n
i j
MSE I i j k i jmn
P P
16
2D Cross Correlation
Unsharp filter
Average filter
Gaussian filter
Median filter
Adaptive filter
Proposed
filter
Salt and paper noise
0.9234 0.9890 0.6983 0.9809 0.7804 0.9984
Gaussian noise
0.5651 0.9861 0.9446 0.9701 0.9701 0.9876
Poisson noise
0.8270 0.9920 0.9900 0.9910 0.9913 0.9961
Speckle noise
0.6349 0.9879 0.7737 0.8341 0.8547 0.9871
Table 1. 2D cross correlation similarity measure
17
Peak Signal-to-Noise Ratio (PSNR)dB
Unsharp filter
Average filter
Gaussian filter
Median filter
Adaptive filter
Proposed
filter
Salt and paper noise
18.59 27.37 25.49 36.00 22.97 49.48
Gaussian noise
9.94 26.16 23.80 26.42 26.79 32.80
Poisson noise
14.74 28.71 30.21 31.92 32.80 43.16
Speckle noise
10.86 26.73 25.38 26.71 27.59 37.67
Table 2. PSNR similarity measure
18
Scaling & Rotation
Definition: Scaling & rotation is affine Transformation where Straight lines remain straight, and parallel lines remain parallel.
Scaling and Rotation: The linear transformation and radon transformation have been used to recover an image from a rotated and scaled origin.
19
Scaled image
Original image
Scaled &rotated image
Figure 4 Rotated and scaled image
Scaling & Rotation
20
Figure 5 Control point selection
Linear Transformation
21
Original image
Scaled & rotated image recovered image
Figure 6 Recovered by using linear transformation
Linear Transformation
22
Radon transform: This transform is able to transform two dimensional images with lines into a domain of possible line parameters, where each line in the image will give a peak positioned at the corresponding line parameters.Projections can be computed along any angle θ, by use general equation of the Radon transformation:
Radon Transformation
, cos sin
, . is the delta function
R x f x y x y x dydy
where
x' is the perpendicular distance of the beam from the origin and θ is the angle of incidence of the beams.
23
Original image
Figure7 Canny edge detection and edge linking
Edge detection Edge linking
Radon Transformation
24Figure 8 Radon transform projections along 180 degrees, from -90 to +89
Radon Transformation
25
Original image
Rotated image recovered image
Figure 9 Recovered by using radon transform
Radon Transformation
26
Blurring: degradation of an image can be caused by motion
There are two types of blurring
Known blurring: the length and the angle of blurring are known
Unknown blurring: the length and the angle of blurring are unknown
Blurring
27
Deblurring Techniques
Deblurring using Wiener filter Deblurring using a regularized filter Deblurring using Lucy-Richardson algorithm Deblurring using blind deconvolution algorithm
g = H f + n
A blurred or degraded image can be approximately described by this equation
28
Deblurring using the Blind Deconvolution Algorithm
Figure 10 Deblurring using the blind deconvolution algorithm
29Figure 11, Capability of object tracking under blurring (a, b) with known blur function and after deblurring (c, d
(a) Blurred image (b) Person detection under motion deformation
(c)Deblurred image (d) Person detection indeblurred image
Deblurring Techniques
30
Blurred image correlation with original one
Deblurred image using correct parameters correlation
Deblurring Techniques
31
Deblurred image using longer PSF correlation
Deblurred image using different angle correlation
Figure 12, 2D cross correlation with the deblurring form
Deblurring Techniques
32
Correlation Condition
blurred image with the original one 0.0614
deblurred image with the original one using correct parameters
0.3523
deblurred image with the original one using longer PSF
0.0558
deblurred image with the original one using different angle
0.1231
Table 3, 2D cross correlation with the deblurring form
Deblurring Techniques
33
Change of Illumination
Change of illumination
Color model deformation may happen due to the change in illumination
Proposed solution
Selecting an appropriate color model (RGB, HSV or ycbcr) to overcome the deformation problem
34
RGB Representation
The RGB color model
mapped to a cubeA Representation of additive color mixing
Weak points of the RGB color model
RGB color model is affected by the change of illumination
RGB is non uniform color model
35
HSV Representations
Hue, saturation and intensity are often plotted in cylindrical coordinates with hue the angle, saturation the radius, and intensity the axis.
HSV color wheel conical representation
of the HSV
The cylindrical representation of the HSV
36
Chrominance is defined as the difference between a color and a reference white at the same luminance.
YCbCr Color Model
The conversion from RGB to YCbCr
0.257 0.504 0.098 16
0.148 0.291 0.439 128
0.439 0.368 0.071 128b
r
Y R
C G
BC
The conversion from YCbCr to RGB
1.164 0.000 1.598 16
1.164 0.329 0.813 128
1.164 2.017 0.000 128
R Y
G Cb
B Cr
37
Advantage of YCbCr
The main advantages of this model are: The luminance component (Y) of YCbCr is independent of the
color The skin color cluster is more compact in YCbCr than in other
color space YCbCr has the smallest overlap between skin and non-skin data
in under various illumination conditions. YCbCr is broadly utilized in video compression standards
YCbCr is a family of color spaces used in video systems.
YCbCr is one of two primary color spaces used to represent digital component video (the other is RGB).
38
To track a visual target we have to relay on a segmentation technique such as:ThresholdingClusteringRegion growingEdge-basedPhysical model-basedFrame SubtractionFast block matchingThroughout this framework a color table thresholding segmentation technique has been applied to extract the visual target
Object Extraction
39
Original image
sample
Tracked object
Homogeneous Object Extraction
40
sample
Homogeneous Object Extraction
RGB YCbCrHSV
Figure 13, Comparison of homogeneous object extraction
Original image
41
Original image
Tracked object
sample
Inhomogeneous Object Extraction
42
Original image
RGB
sample
YCbCrHSV
Figure 14, Comparison of inhomogeneous object extraction
Inhomogeneous Object Extraction
43
The most basic morphological operations are dilation and erosion
Morphological operations
Dilation adds pixels to the boundaries of objects in an image. Expand/enlarge objects in the imageFill gaps or bays of insufficient widthFill small holes of sufficiently small sizeConnects objects separated by a distance less than the size of the window
Erosion removes pixels on object boundaries.to erode away the boundaries of regions of foreground pixels (i.e. white pixels, typically). Thus areas of foreground pixels shrink in size, and holes within those areas become larger
44
Opening and Closing are morphological operations which are based on dilation and erosion.
Opening smoothes the contours of objects, breaks narrow isthmuses and eliminates thin protrusions.
Closing also produces the smoothing of sections of contours but fuses narrow breaks, fills gaps in the contour and eliminates small holes.
Opening is basically erosion followed by dilation while closing is dilation followed by erosion.
Morphological operations
45
Binary object Binary after removing extra pixel
Binary object after dilation holes
Binary object after closing
Morphological operations
Figure 15, The effect of the morphological operation
46
Morphological operations
Figure 16, Center of gravity, ellipse fitting and bound box of an image
47
Geometrical Modeling
Figure 17 object tracking at different distance
48
bDN aeWhere, a = 30606.621b=-0.03410108
The relation between distance (D) and no of pixel (N)
Geometrical Modeling
Figure 18. The relation between range (D) and projection size (N)
49
The relation between the range and location of the object in 3D domain
Geometrical Modeling
Figure 19. The relation between the range and location of the object in 3D domain
50
1
nT
i
y t au t i e t a u t e t
Motion Estimation and Prediction based on FIR
Figure 19, FIR model structures
51
Motion Estimation and Prediction based on FIR
Figure 20, Models output w.r.t system output
52
Motion Estimation and Prediction based on FIR
Figure 21 Model output w.r.t system output
53
Motion Estimation and Prediction based on FIR
Figure 22 The capability of the model to predict the output if the system input is known
54
Throughout this framework the following academic tasks have been achieved
Developing a novel Universal filter for image denoising Selecting qualitative radon transformation for correction of the
rotation Intensive comparative study for dealing with kwon/unknown
bulrring Employing a color table thresholding segmentation technique on
YCbCr to extract the visual target 3D Geometrical modeling for estimation and prediction of target
pose As a future work, we are going to implement the applied
algorithm on an embedded system to develop a visual RADAR System