The Zipingpu tunnel located at the Sichuan province Dujiangyan to the Wenchuan section of 317 state highway, it is the key difficult project in this section. This tunnel is designed for dual-hole, the length of left h...
详细信息
The Zipingpu tunnel located at the Sichuan province Dujiangyan to the Wenchuan section of 317 state highway, it is the key difficult project in this section. This tunnel is designed for dual-hole, the length of left hole is 4090 m, the right hole is 4060 m, the maximum burying depth surpasses 550 m, it is a high concentration gas tunnel and has appeared several gas abnormal emission phenomenon in the construction. Combination with existing features of gas tunnel monitoring data, this paper carried on the classification to the Zipingpu tunnel massive monitor data to analyze and predicted gas emission tendency, then fined the influencing factor of monitor data, proposed the gas monitor data division type and the prediction model, and practical application in Zipingpu tunnel construction process, prediction result is conform with sample measured data.
Automatic inshore ship detection from remotesensingimagery has many important applications, such as ship change detection and harbor dynamic surveillance. Stable performance of inshore ship detection is vital to the...
详细信息
Automatic inshore ship detection from remotesensingimagery has many important applications, such as ship change detection and harbor dynamic surveillance. Stable performance of inshore ship detection is vital to the analysis of ship change and then determines the harbor surveillance effect. However, it is hard to detect inshore ships utilizing the traditional area-based method because the grayscale and texture character of inshore ships are similar to that of the shore. In this paper, a new method based on invariant generalized Hough transform is introduced to extract ship shape using the evidence-gathering procedure. In contrast with other shape extraction methods used in inshore ships detection, our method is specially tolerant to noise and occlusion, and also invariant to translation, scale and rotation transformation. Moreover, our method can be used to separate ships moored together that can benefit to ship recognition. Experiment results are demonstrated on the optical remotesensingimagery from Google Earth.
Edge of image is one of the most fundamental and significant features. Edge detection is always one of the classical studying projects of computer vision and imageprocessing field. It is the first step of image analy...
详细信息
Edge of image is one of the most fundamental and significant features. Edge detection is always one of the classical studying projects of computer vision and imageprocessing field. It is the first step of image analysis and understanding. With the continuous improvement of remotesensingimage, especially the appearance of Digital Aerial image, edge detection is necessary step to extract information from the Digital Aerial images..The purpose of edge detection is to discover the information about the shapes and the reflectance or transmittance in an image. The correctness and reliability of its results affect directly the comprehension machine system made for objective world. In this paper FPGA-based architecture for edge detection algorithms has been proposed. The implementation of edge detection algorithms on a field programmable gate array (FPGA) is having advantage of using large memory and embedded multipliers. FPGAs are providing a platform for processing real time algorithms on application-specific hardware with substantially higher performance than programmable digital signal processors (DSPs). The proposed architecture can be used as a building block of a aerial imaging systems for navigation and for the patternrecognition. The hardware implementation results are presented for the Sobel and Prewitt operator.
Hough transform has been applied abroad in object shape detection. However, the traditional generalized Hough transform may not make the vote focus to one point when the image has a high-level noise. As a result, the ...
详细信息
Hough transform has been applied abroad in object shape detection. However, the traditional generalized Hough transform may not make the vote focus to one point when the image has a high-level noise. As a result, the object positioning is not very precise, or even wrong. It makes the Hough Transform can't be used in strong noisy image or complex object background on this condition. In this paper, we apply fuzzy set theory to generalized Hough transform and use a new method to process strong noisy image. The method regards the unfocused area not just as some simple point but a "fuzzy voting point" - a fuzzy area. Consequently, the fuzzy set theory can be used to describe the "fuzzy voting point". By constructing a new subjection function, we can calculate a cut set and use it as weight to optimize the position of the reference points. The experiments show that this method can get more accurate and robust object position than traditional method in shape detection from high-level noise image.
Characterization of two-dimensional textures has many potential applications such as remotesensing, content base image retrieval, image segmentation, etc. In real world, noise has a disturbing effect in the analysis ...
详细信息
Characterization of two-dimensional textures has many potential applications such as remotesensing, content base image retrieval, image segmentation, etc. In real world, noise has a disturbing effect in the analysis of images and textures. In this paper, a new rotation invariant texture descriptor, LSP (Local Similarity pattern) is proposed to characterize the local contrast information based on the similarity or dissimilarity of adjacent pixels into a one- dimensional LSP histogram. The aligned histogram could be used as a feature vector to describe the related texture. Experimental results show that the proposed LSP operator can achieve significant improvement in the classification of textures in spite of their embedded noise. Especially, increasing the noise has a few effects on the performance of this method.
Changes in illumination conditions have a significant effect on the performance of robot vision tasks such as object recognition. One way to handle varying illumination is to apply illumination normalization as a pre-...
详细信息
Changes in illumination conditions have a significant effect on the performance of robot vision tasks such as object recognition. One way to handle varying illumination is to apply illumination normalization as a pre-processing step. We compare several illumination normalization methods for the task of robot soccer. Our results show improved recognition performance under changes in intensity and brightness.
A new approach for object extraction from high-resolution satellite images is presented in this paper. The new approach integrates image fusion, multi-spectral classification, feature extraction and feature segmentati...
详细信息
image classification plays an important part in the fields of remotesensing, image analysis and patternrecognition. image classification can be done using conventional methods. But conventional methods lead to miscl...
ISBN:
(纸本)9781450304498
image classification plays an important part in the fields of remotesensing, image analysis and patternrecognition. image classification can be done using conventional methods. But conventional methods lead to misclassification due to strictly convex boundaries. Textural features are included for better classification but are inconvenient for conventional methods. The proposed system uses textural feature based image classification using neural network. Textural features are extracted using Gray level co-occurrence matrix and artificial neural network is developed for the classification of images into different classes. Neural network is trained by supervised learning using standard back propagation algorithm for the classification of images.
Combining spectral and spatial information can improve land use classification of high-resolution data. However,the use of spatial information always focus on objects' spatial pattern,whereas not pay enough attent...
详细信息
Combining spectral and spatial information can improve land use classification of high-resolution data. However,the use of spatial information always focus on objects' spatial pattern,whereas not pay enough attention to spatial relationship,which is more convenient and effective in remotesensing *** letter proposes a spectral-spatial information method,which aims to exploit objects' spatial relationships in high resolution imagery,and then integrate it with spectral information in remotesensing *** experiment on urban mapping based on spectral-spatial information using Quickbird imagery,and compare its result with supervised classification methods like maximum likelihood classification,and support vector machine (SVM) *** results show that the proposed method yield better performance than the others in both precision and rationality.
暂无评论