Normalized difference vegetation index, also known as the normalized difference vegetation index, is widely used in the study of vegetation and the research of plant phenology by means of remote sensing image. It is the best indicator of plant growth condition and the spatial distribution of vegetation density, bearing a linear relation with density of the vegetation distribution. NDVI can reflect the background image of plant canopy, such as soil, damp ground, withered leaves, roughness, etc. and it is also related to the vegetation. It has a variety of advantages, such as a higher detection sensitivity of vegetation, a higher detection range of vegetation coverage, the ability of eliminating the terrain and the community structure of shadows and radiated interference, the weakening of the noise brought by the angle of the sun and the atmosphere, etc. However, NDVI is also susceptible to canopy background variations, which lead to NDVI values of the soil pixels in plants shadows and vegetation pixels close in high spatial resolution data, thus, the separability of the foregoing two kinds of pixels of NDVI data is not satisfactory enough. In order to improve the separability of NDVI extracted from soil pixels and vegetation pixels, this paper, on the basis of NDVI, Red-band Enhanced Normalized Difference Vegetation Index (RNDVI) is constructed by introducing a red band strengthening coefficient , realize the nonlinear tensile of the NDVI value, as to increase the separability of vegetation pixels and the shadow of the soil pixels .On this basis, RNDVI threshold method and RNDVI-SVM method are employed to extract vegetation pixels from the high spatial resolution data obtained by Field Imaging Spectrometer System (FISS). The experimental results show that the accuracy of vegetation pixels extraction using RNDVI can be higher than using NDVI.
Present a novel method of 3D shape measurement of optical free-from surface based on fringe
projection. A virtual reference surface is proposed which can be used to improve the detection
efficiency and realize the automation of measuring process. Sinusoidal fringe patterns are
projected to the high reflected surface of the measured object. The deflection fringe patterns that
modulated by the object surface are captured by the CCD camera. The slope information can be
obtained by analyzing the relationship between the phase deflectometry and the slope of the object
surface. The wave-front reconstruction method is used to reconstruct the surface. With the
application of fringe projection technology the accuracy of optical free-form surfaces
measurement could reach the level of tens of micrometer or even micrometer.
An optical method is proposed for in-situ measurement of angles of space elements separated at a distance of several or
several tens of meters. When it is necessary to measure large objects or geometrical elements within a large scale space,
it is not always possible to bring these workpieces to conventional coordinate measuring machines (CMMs) which are
widely used in industries. Mobile measuring systems provide ideal solutions for these applications. The basic idea of the
presented research work is to set up the multiple common optical references through which the dimensional inspections
of separation angles of bifacial lines in a large scale space can be fulfilled. The angles between the projection light and
each element can be captured through a machine vision system, and thereafter the angles between those corresponding
elements can be determined using the geometrical principles. The method and the calibration approach have been
validated on our designed work station.
This paper presents a methodology for the non-contact inspection of geometric features of internal threads in machined
automotive parts. The method enables in-process internal thread quality verification using a high-precision laser sensor.
It allows extracting thread pitch, major and minor diameters, thread height and even allows finding the angular location
of the starting point of a thread with respect to a reference point on the perimeter. An in-process thread inspection
prototype possessing five axes of motion is presented to demonstrate the capabilities of this method. The validation of
this method and the self-calibration approach for system alignment were tested on several internal threads showing a
high degree of repeatability.
The high accuracy of the vehicle digital dashboard makes it difficult to check its error in real time. On taking the
advantage of is production condition, the digital image processing method can be used to check the dashboard's
precision automatically. The image edge detection method is the key of our dashboard check method. The snake model
has been extensively used today. The GVF snake model overcomes the traditional snake model's shortcoming, it has a
large capture range and is able to move into boundary concavities. But it still needs large amount of computation and is
easily to be disturbed by noise. The wavelet-based multi-scale GVF snake took the advantage of the wavelet transform
and GVF model. In the lower resolution, there were less wavelet coefficients and the GVF snake was easy to deform to
the contour without much computation and was less interfered by noise. In higher resolution, with taking advantage of
the initial position of the foregoing resolution, much more computation would be saved. Experiments show this method
can detect the position of the pointer automatically and exactly.
Snakes, or active contours, are used extensively in computer vision and image processing application, particularly to
locate object boundaries. GVF (Gradient Vector Flow) model has resolved two key problems of the traditional
deformable model. However, it still requires both the initial contour being close to the target and a large amount of
computation. And it is difficult to process the cupped target edge. This paper analysis the characteristics of deformable
model firstly, then proposed a new method based on B-spline lifting wavelet. Experimentations based on GVF model and
MRI segmentation show that the proposed method is a good resolution to the initialization sensitivity and the large
Level set methods provide powerful numerical techniques for analyzing and solving interface evolution problems based on
partial differential equations. Level sets display interesting elastic behaviors and can handle topological changes. Although
level set methods have many advantages, they still often face difficult challenges such as poor image contrast, noise, and
missing or diffuse boundaries. The robust level set method of this paper is based on the anisotropic diffusion method. The
fast marching method provides a fast implementation for level set methods, the anisotropic diffusion is allowed to better
control the amount of smoothing effect and this process can get both noise smoothing and edge enhancement at the same
time. Experimental results indicate that the method can greatly reduce the noise without distorting the image and made the
level set methods more robust and accurate.
Level set method provides powerful numerical techniques for analyzing and solving interface evolution problems based on partial differential equations. It is particularly appropriate for image segmentation and other computer vision tasks. However, there exists noise in every image and the noise is the main obstacle to image segmentation. In level set method, the propagation fronts are apt to leak through the gaps at locations of missing or fuzzy boundaries that are caused by noise. The robust level set method proposed in this paper is based on the adaptive Gaussian filter. The fast marching method provides a fast implementation for level set method and the adaptive Gaussian filter can adapt itself to the local characteristics of an image by adjusting its variance. Thus, the different parts of an image can be smoothed in different way according to the degree of noisiness and the type of edges. Experiments results demonstrate that the adaptive Gaussian filter can greatly reduce the noise without distorting the image and made the level set methods more robust and accurate.
Although the snake model has been widely used nowadays and obtained quite good results, there are still some key difficulties with it: the narrow capture range and the disability to move into boundary concavities. A new snake model, Gradient Vector Flow snake, can overcome this difficulty. GVF snake model creates its own external force field called GVF force field, this make it insensitive to the initialization and able to move into concave boundary regions. However, GVF snake need large amount of computation and is easily interfered by noise. Accordingly, the wavelet-based GVF snake model can lessen the amount of computation because the multi-scale character of wavelet transform. Due to the different singularities of signal and noise, the module local maxima of their wavelet coefficients vary in different way in multi resolution, so noise can also be distinguished from signal with wavelet-based GVF snake model. The wavelet-based GVF snake model is more quickly and robust contrast to traditional snake model.
Reverse engineering of free-form surfaces is one of the most challenging technologies in advanced manufacturing. With the development of industry more and more sculptured surfaces, such as molds and turbine blades, are required to measure quickly and accurately. Optical non-contact probes possess many advantages, such as high speed, no measuring force, in comparison with contact ones. The ability of stereo vision probe with CCD cameras in gathering a large amount of information simultaneously makes it the most popularly used one in sculptured surface measurements. So a non-contact measurement system is built which consists of CMM and a vision probe with many techniques. It distinguishes itself by high efficiency, high accuracy and reliability, as well as applicability for on-line measurement of complicated sculptured surfaces. With a virtual 3D target in form of a grid plate, all the intrinsic and extrinsic parameters of CCD camera including the uncertainty of image scale factor and optical center of camera can be readily calibrated. Through measuring cylindrical section and surface of gauge block, this system is viable to measure free-form surface and high-reflective metallic surface.