Industries are moving towards automation in order to increase productivity and ensure quality. Variety of electronic and electromagnetic systems are being employed to assist human operator in fast and accurate quality inspection of products. Majority of these systems are equipped with cameras and rely on diverse image processing algorithms. Information is lost in 2D image, therefore acquiring accurate 3D data from 2D images is an open issue. FAST, SURF and SIFT are well-known spatial domain techniques for features extraction and henceforth image registration to find correspondence between images. The efficiency of these methods is measured in terms of the number of perfect matches found. A novel fast and robust technique for stereo-image processing is proposed. It is based on non-rigid registration using modified normalized phase correlation. The proposed method registers two images in hierarchical fashion using quad-tree structure. The registration process works through global to local level resulting in robust matches even in presence of blur and noise. The computed matches can further be utilized to determine disparity and depth for industrial product inspection. The same can be used in driver assistance systems. The preliminary tests on Middlebury dataset produced satisfactory results. The execution time for a 413 x 370 stereo-pair is 500ms approximately on a low cost DSP.
Proc. SPIE. 10338, Thirteenth International Conference on Quality Control by Artificial Vision 2017
KEYWORDS: Radar, Unmanned aerial vehicles, Digital signal processing, Cameras, Receivers, Image registration, Signal processing, Electrical engineering, Filtering (signal processing), Global Positioning System
The paper presents a passive technique for real-time altitude above ground level estimation for aerial vehicles using a monocular camera, a GPS receiver and an inertial measurement unit. The paper discusses a robust method for featureless registration of successive images through phase correlation using Gram polynomial decimation. Altitude is estimated by formulating the shift in pixels between the images in terms of distance travelled, calculated using corresponding GPS latitudes and longitudes. Resultant value is compensated for changes in pitch before being passed through Savitzky-Golay filter. The system can generate results every 300ms on a lowcost commercial digital signal processor with mean error of 2m and standard deviation of 13m. The proposed system is suitable for speeds up to 300m/s and altitudes up to 3000m.
Growing numbers of long tunnels across the globe has increased the need for safety measurements and inspections of tunnels in these days. To avoid serious damages, tunnel inspection is highly recommended at regular intervals of time to find any deformations or cracks at the right time. While following the stringent safety and tunnel accessibility standards, conventional geodetic surveying using techniques of civil engineering and other manual and mechanical methods are time consuming and results in troublesome of routine life. An automatic tunnel inspection by image processing techniques using non rigid registration has been proposed. There are many other image processing methods used for image registration purposes. Most of the processes are operation of images in its spatial domain like finding edges and corners by Harris edge detection method. These methods are quite time consuming and fail for some or other reasons like for blurred or images with noise. Due to use of image features directly by these methods in the process, are known by the group, correlation by image features. The other method is featureless correlation, in which the images are converted into its frequency domain and then correlated with each other. The shift in spatial domain is the same as in frequency domain, but the processing is order faster than in spatial domain. In the proposed method modified normalized phase correlation has been used to find any shift between two images. As pre pre-processing the tunnel images i.e. reference and template are divided into small patches. All these relative patches are registered by the proposed modified normalized phase correlation. By the application of the proposed algorithm we get the pixel movement of the images. And then these pixels shifts are converted to measuring units like mm, cm etc. After the complete process if there is any shift in the tunnel at described points are located.
This paper presents a new approach to optical material stress analysis, which eliminates the need to apply
a random dot pattern to the surface of the sample being tested. A multi-resolution hierarchical sub-division
is implemented, with a consistent polynomial decimation applied at each layer of the tree. The degree of
decimation must be selected depending on the nature of the structure of the surface of the sample being At each
layer the individual patches are registered using a modified normalized phase correlation, whereby the Fourier
basis functions are projected onto the orthogonal complement of a low degree Gram polynomial basis. This
reduces the effect of the Gibbs error on the local registration. The registration positions are then subjected to
a regularization via an entropy weighted tensor-polynomial approximation. The Gibbs polynomial basis is used
for the tensor product, since they are orthonormal and model the continuous deformation associated with an
elastic deformation. The stability of the proposed method is demonstrated in real measurements and the results
with and without the application of the random pattern are compared.
This paper presents a new approach to non-rigid elastic registration. The method is applied to hyper spectral imaging
data for the automatic quality control of decorative foils which are subject to deformation during lamination. A new image
decimation procedure based on Savitzky-Golay smoothing is presented and applied in a multiresolution pyramid. Modified
Fourier basis functions implemented by projection onto the orthogonal complement of a truncated Gram polynomial basis
are presented. The modified functions are used to compute spectra whereby the Gibbs error associated with local gradients
in the image are reduced. The paper also presents the first direct linear solution to weighted tensor product polynomial
approximation. This method is used to regularize the patch coordinates, the solution is equivalent to a Galerkin type
solution to a partial differential equations. The new solution is applied to published standard data set and to data acquired
in a production environment. The speed of the new solution justifies explicit reference: the present solution implemented
in MATLAB requires approximatly 1.3s to register an image of size 800 ×× 500 pixels. This is approximately a factor 10
to 100 faster than previously published results for the same data set.
This paper presents a new approach to non-rigid registration. A hierarchical subdivision approach is applied, with
local normalized phase correlation for patch registration. The major improvement is achieved by implementing a
suitable decimation at each level. The decimation is implemented via a Gram polynomial basis. Both global and
local polynomial approximation are considered and compared with the use of a Fourier basis. The issue of Gibbs
error in polynomial decimation is examined. It is shown that the Gram basis is superior when applied to signals
with strong gradient, i.e., a gradient which generates a significant Gibbs error with a Fourier basis. A bivariate
Gram polynomial tensor product approximation is used to implement regularization. It is demonstrated that
the new method performs well on both synthetic and real image data. The procedure requires approximately
1.3 sec. to register an image with 800 × 500 pixels.