This paper proposes the use of information derived from the graph of a texture image function for texture description. The graph of an image function is a rumpled surface in the three-dimensional space that appears li...
详细信息
ISBN:
(纸本)0769521282
This paper proposes the use of information derived from the graph of a texture image function for texture description. The graph of an image function is a rumpled surface in the three-dimensional space that appears like a landscape. Four novel texture feature curves are used to characterize the texture. This method is named as statistical landscape features (SLF). SLF achieves a very high correct classification rate of 94.53% on the entire Brodatz set. Besides the very good performance, another remarkable advantage of the proposed method is that it has no parameter to tune.
Multisensor image registration is a difficult problem. In this paper, we give a new registration method using direct histogram specification technique. We find that after using histogram specification, the resulting i...
详细信息
Multisensor image registration is a difficult problem. In this paper, we give a new registration method using direct histogram specification technique. We find that after using histogram specification, the resulting images with the same view look more similar, though the original images gained by different sensors differ much in intensity. Based on this property, a novel approach to find matching block pairs is proposed. The centers of the block pairs are used as control points (cps). We also use the cluster method of the nearest function criterion to test the correctness of the cps and discard wrong ones. The algorithm has been tested by many aerial images of different sensors. The effectiveness is illustrated by the experimental results.
Hyperbolae are common features in typical GPR scans that may result from localised reflectors (such as rocks), or from a buried cylindrical-shaped objects (such as pipes or drums). The shapes of these hyperbolae are i...
详细信息
ISBN:
(纸本)9090179593
Hyperbolae are common features in typical GPR scans that may result from localised reflectors (such as rocks), or from a buried cylindrical-shaped objects (such as pipes or drums). The shapes of these hyperbolae are influenced by both the nature of the subsurface reflector as well as the relative permittivity of the medium in which the objects are located. It is this uncertainty about what a hyperbola in a GPR scan actually represents, that has made it very difficult to make accurate estimations from GPR data, with regard to the buried object itself on one hand, and to the medium surrounding it on the other. In this paper, a novel general equation for hyperbolae which result from buried cylinders is presented which allows for cylinders of arbitrary radius, resulting in a more accurate estimation of the relative permittivity of the surrounding medium and of the depth, in addition to the radius information. This is achieved by subjecting the radargrams to a series of imageprocessing stages followed by a curve-fitting procedure specifically developed for hyperbolae. The fitting technique is applied on a variety of synthetic hyperbolae that are generated to emulate reflections from targets of varying depth and radius and buried in a range of dielectrics. The results indicate this technique is fully capable of successfully estimating the depth and radius to within 1%. Further application to control site data has also given similar results, validating the method and justifying the assumptions used.
In this paper, we propose an unsupervised land use classification method for multispectral image. Especially, we present a novel spatial mean shift procedure and an automatic band selection method. We make full use of...
详细信息
In this paper, we propose an unsupervised land use classification method for multispectral image. Especially, we present a novel spatial mean shift procedure and an automatic band selection method. We make full use of the edge information from the mean shift procedure to improve the over-segmentation. Experimental results on Landsat TM images validate the efficiency of the proposed method.
We introduce a set-based approach for estimating image motion based on an optical flow constraint and a finite number of arbitrary differential constraints describing physically plausible vector fields. Compared to re...
详细信息
We introduce a set-based approach for estimating image motion based on an optical flow constraint and a finite number of arbitrary differential constraints describing physically plausible vector fields. Compared to related variational estimation approaches, our approach strictly satisfies each separate constraint and becomes not more involved in the presence of higher-order differential operators. The approach is implemented using established subgradient projection schemes onto the set of feasible solutions. Our approach is particularly suited if quantitative prior knowledge about structural flow properties is available, and for the regularized estimation of highly non-rigid image motion.
In this paper, we propose a registration method between GIS data and high-resolution satellite images of urban scenes. Our approach consists of two steps: firstly, the urban straight main road features in images are e...
详细信息
In this paper, we propose a registration method between GIS data and high-resolution satellite images of urban scenes. Our approach consists of two steps: firstly, the urban straight main road features in images are extracted by combining their spectral information with a geometric constraint. Then, by exploiting the frequency spectrum property of linear stripe regions, we perform matching of the road layer of geographic information data and feature images using a new FFT-based algorithm. The significant advantage of the approach is its capability to match the rotated and scaled images robustly even when they have a large scale change or obvious geometric differences. Experimental results demonstrate the robustness and efficiency of the method.
According to characteristic of image wavelet transform and interpolation, this paper proposes an remotesensingimage interpolation method combining wavelet transform and interpolation algorithm, which can improve the...
详细信息
ISBN:
(纸本)081944684X
According to characteristic of image wavelet transform and interpolation, this paper proposes an remotesensingimage interpolation method combining wavelet transform and interpolation algorithm, which can improve the remotesensingimage resolution. Experiments show that the algorithm can properly retain abundant high frequency information in original remotesensingimage. After interpolation processing and wavelet reconstruction, we can obtain an remotesensingimage with higher resolution, better visual effect, higher Signal Noise Ratio (SNR), more detail information and no apparent warp. Therefore, this algorithm is an effective method of super-resolution remotesensingimageprocessing.
One unique feature in the remotesensing problems is that a significant amount of data are available, from which desired information must be extracted. Transform methods offer effective procedures to derive the most s...
详细信息
ISBN:
(纸本)081944667X
One unique feature in the remotesensing problems is that a significant amount of data are available, from which desired information must be extracted. Transform methods offer effective procedures to derive the most significant information for further processing or human interpretation and to extract important features for pattern classificaiton. In this paper a survey of the use of major transforms in remotesensing is presented. These transforms have significant effects on patternrecognition as features derived from orthogonal or related transforms tend to be very effective for classification, and on data reduction and compression. After the introduction, we will examine the empirical orthogonal function, the discrete Karhunen-Loeve transform and related transforms, the wavelet transform, and the component analysis.
The proceedings contains 40 papers from the conference on Proceedings of SPIE: imageprocessing and patternrecognition in remotesensing. The topics discussed include: image fusion of Hyperion and Ikonos imagery;mana...
详细信息
The proceedings contains 40 papers from the conference on Proceedings of SPIE: imageprocessing and patternrecognition in remotesensing. The topics discussed include: image fusion of Hyperion and Ikonos imagery;managing and distributing remotesensingimages based on metadata;new intensity interpolation for resampling of remotesensingimagery;and line extraction in multispectral images.
暂无评论