scholarly journals Multi-scale invariant fields: estimation and prediction

2020 ◽  
Vol 2020 (7) ◽  
pp. 073408
Author(s):  
H Ghasemi ◽  
S Rezakhah ◽  
N Modarresi
Keyword(s):  
Scale Invariant ◽  
Multi Scale ◽  
Estimation And Prediction

A Tracking Window Adaptive Compressive Tracking Algorithm

2019 ◽  
Vol 33 (14) ◽  
pp. 1959045 ◽  
Author(s):  
Wenhao Wang ◽  
Mingxin Jiang ◽  
Xiaobing Chen ◽  
Li Hua ◽  
Shangbing Gao
Keyword(s):  
Texture Features ◽  
Candidate Region ◽  
Tracking Algorithm ◽  
Experimental Results ◽  
Scale Invariant ◽  
Compressive Tracking ◽  
Multi Scale ◽  
Feature Normalization ◽  
Object Region ◽  
Candidate Regions

In the original compression tracking algorithm, the size of the tracking box is fixed. There should be better tracking results for scale-invariant objects, but worse tracking results for scale-variant objects. To overcome this defect, a scale-adaptive compressive tracking (CT) algorithm is proposed. First of all, the imbalance of the gray and texture features in the original CT algorithm is balanced by the multi-feature method, which makes the algorithm more robust. Then, searching different candidate regions by using the method of multi-scale search along with feature normalization makes the features extracted from different scales comparable. Finally, the candidate region with the maximum discriminate degree is selected as the object region. Thus, the tracking-box size is adaptive. The experimental results show that when the object scale changes, the improving CT algorithm has higher accuracy and robustness than the original CT algorithm.

scholarly journals TOWARDS ADAPTIVE HIGH-RESOLUTION IMAGES RETRIEVAL SCHEMES

2016 ◽  
Vol III-2 ◽  
pp. 181-189
Author(s):  
A. Kourgli ◽  
H. Sebai ◽  
S. Bouteldja ◽  
Y. Oukil
Keyword(s):  
High Spatial Resolution ◽  
Scale Invariant ◽  
Query Image ◽  
Multi Scale ◽  
Adaptive Schemes ◽  
Retrieval Scheme ◽  
First Results ◽  
High Resolution Images ◽  
Scale Invariant Feature ◽  
Complex Methods

Nowadays, content-based image-retrieval techniques constitute powerful tools for archiving and mining of large remote sensing image databases. High spatial resolution images are complex and differ widely in their content, even in the same category. All images are more or less textured and structured. During the last decade, different approaches for the retrieval of this type of images have been proposed. They differ mainly in the type of features extracted. As these features are supposed to efficiently represent the query image, they should be adapted to all kind of images contained in the database. However, if the image to recognize is somewhat or very structured, a shape feature will be somewhat or very effective. While if the image is composed of a single texture, a parameter reflecting the texture of the image will reveal more efficient. This yields to use adaptive schemes. For this purpose, we propose to investigate this idea to adapt the retrieval scheme to image nature. This is achieved by making some preliminary analysis so that indexing stage becomes supervised. First results obtained show that by this way, simple methods can give equal performances to those obtained using complex methods such as the ones based on the creation of bag of visual word using SIFT (Scale Invariant Feature Transform) descriptors and those based on multi scale features extraction using wavelets and steerable pyramids.

scholarly journals Sparse coded spatial pyramid matching and multi-kernel integrated SVM for non-linear scene classification

2021 ◽  
Vol 72 (6) ◽  
pp. 374-380
Author(s):  
Bhavinkumar Gajjar ◽  
Hiren Mewada ◽  
Ashwin Patani
Keyword(s):  
Deep Learning ◽  
Support Vector ◽  
Scene Classification ◽  
Scale Invariant ◽  
Training Time ◽  
Multi Scale ◽  
Non Linear ◽  
Pyramid Matching ◽  
Scale Invariant Feature ◽  
Distinct Features

Abstract Support vector machine (SVM) techniques and deep learning have been prevalent in object classification for many years. However, deep learning is computation-intensive and can require a long training time. SVM is significantly faster than Convolution Neural Network (CNN). However, the SVM has limited its applications in the mid-size dataset as it requires proper tuning. Recently the parameterization of multiple kernels has shown greater flexibility in the characterization of the dataset. Therefore, this paper proposes a sparse coded multi-scale approach to reduce training complexity and tuning of SVM using a non-linear fusion of kernels for large class natural scene classification. The optimum features are obtained by parameterizing the dictionary, Scale Invariant Feature Transform (SIFT) parameters, and fusion of multiple kernels. Experiments were conducted on a large dataset to examine the multi-kernel space capability to find distinct features for better classification. The proposed approach founds to be promising than the linear multi-kernel SVM approaches achieving 91.12 % maximum accuracy.

Rock Core Thin Section Image Stitching Based on SIFT Features

2014 ◽  
Vol 1049-1050 ◽  
pp. 398-401
Author(s):  
Juan Juan Yin ◽  
Guo Jian Cheng ◽  
Na Liu ◽  
Xin Jian Qiang ◽  
Ye Liu
Keyword(s):  
Thin Section ◽  
Detection Algorithm ◽  
Visual Area ◽  
Image Stitching ◽  
Microscopic Image ◽  
Tight Sandstone ◽  
Scale Invariant ◽  
Multi Scale ◽  
Rock Analysis ◽  
Scale Invariant Feature

Because of the inherent conflict between visual area and resolution in rock microscope structure, during the study of the RCTS (Rock Core Thin Section) microstructure, we cannot focus on the multi-scale structure characteristics of the particles, pores and throats, and it is fail to satisfy the demands of a more comprehensive study. In order to solve this problem, a microscopic image stitching method in RCTS is proposed by applying SIFT (Scale Invariant Feature Transform) detection algorithm. This method can successfully solve the conflict between the visual area and resolution, overcoming the problem of inclining and deformation in images acquisition under the microscope and finally, achieving the seamless stitching of RCTS microscopic image for big visual area. The experimental results show that this method can improve the accuracy of rock analysis in microstructure and has important practical and theoretical significance for the development of tight sandstone reservoir.

A Fast Feature Matching Algorithm Based on Multi Scale Spatial Segmentation Technology

2014 ◽  
Vol 490-491 ◽  
pp. 1217-1220
Author(s):  
Shu Rong Li ◽  
Yuan Yuan Huang ◽  
Zuo Jin Hu
Keyword(s):  
Feature Matching ◽  
Multiple Scales ◽  
Feature Space ◽  
Feature Points ◽  
Huge Amount ◽  
Scale Invariant ◽  
Matching Algorithm ◽  
Multi Scale ◽  
Spatial Segmentation ◽  
Scale Invariant Feature

SIFT (Scale invariant feature transform) and correlative algorithms are now widely used in content based image retrieval technology. They compute distance and use neighbor algorithm to look for the optimal matching couples. The disadvantage of such way is high complexity, especially when huge amount of images need to be retrieved or recognized. To solve this problem, a new matching way based on feature space division under multi-scale is proposed. The algorithm will divide the feature space under multiple scales, so that those feature points which are located in somewhere can use a code to represent, and finally realize the matching through the code. Without calculating distance, the algorithm complexity is greatly reduced. Experiments show that, the algorithm keeps the matching accuracy and greatly enhance the efficiency of the matching at the same time.

scholarly journals TOWARDS ADAPTIVE HIGH-RESOLUTION IMAGES RETRIEVAL SCHEMES

2016 ◽  
Vol XLI-B2 ◽  
pp. 201-209
Author(s):  
A. Kourgli ◽  
H. Sebai ◽  
S. Bouteldja ◽  
Y. Oukil
Keyword(s):  
High Spatial Resolution ◽  
Scale Invariant ◽  
Query Image ◽  
Multi Scale ◽  
Adaptive Schemes ◽  
Retrieval Scheme ◽  
First Results ◽  
High Resolution Images ◽  
Scale Invariant Feature ◽  
Complex Methods

Nowadays, content-based image-retrieval techniques constitute powerful tools for archiving and mining of large remote sensing image databases. High spatial resolution images are complex and differ widely in their content, even in the same category. All images are more or less textured and structured. During the last decade, different approaches for the retrieval of this type of images have been proposed. They differ mainly in the type of features extracted. As these features are supposed to efficiently represent the query image, they should be adapted to all kind of images contained in the database. However, if the image to recognize is somewhat or very structured, a shape feature will be somewhat or very effective. While if the image is composed of a single texture, a parameter reflecting the texture of the image will reveal more efficient. This yields to use adaptive schemes. For this purpose, we propose to investigate this idea to adapt the retrieval scheme to image nature. This is achieved by making some preliminary analysis so that indexing stage becomes supervised. First results obtained show that by this way, simple methods can give equal performances to those obtained using complex methods such as the ones based on the creation of bag of visual word using SIFT (Scale Invariant Feature Transform) descriptors and those based on multi scale features extraction using wavelets and steerable pyramids.

scholarly journals Hypoxia shapes coral reefs

2018 ◽  
Author(s):  
David Blakeway
Keyword(s):  
Three Dimensional ◽  
Distribution Data ◽  
Scale Invariant ◽  
Ecological Processes ◽  
Network Cell ◽  
Invariant Structure ◽  
Multi Scale ◽  
Geometric Patterns ◽  
Calm Weather ◽  
The Many

The three-dimensional form of a coral reef emerges from thousands of years of ecological interactions between reef-building organisms and their environment. Time integrates those interactions, such that the predominant ecological processes are distilled into reef form, often as striking geometric patterns. Several of these patterns have a fractal appearance, exhibiting nested, scale-invariant structure. Cellular reefs are one fractal reef morphotype, characterised by the presence of subcircular, bowl-shaped, depressions (‘cells’) within the reef network. Cell diameters range from approximately 10 metres to 1 kilometre, the larger cells being compound structures containing multiple smaller cells. The common attribute shared by cellular reefs of all scales is an abundance of staghorn Acropora. Staghorn’s fast growth, fuelled by a correspondingly fast metabolism, allows them to rapidly fill lagoons, but leaves them vulnerable to reduced water flow as their own growth begins to impede lagoonal circulation. This article outlines a conceptual model of multi-scale cellular reef development, based on water quality and coral distribution data from the cellular reefs of Western Australia’s Houtman Abrolhos Islands. The key process in the model is density-stratification of the water column during extended periods of warm, calm, weather. Warm water in the shallows traps stable pools of cooler and denser water at depth. The trapped water is rapidly depleted of oxygen, which causes extensive mortality among staghorn colonies. This initiates a negative feedback process in which ongoing growth of colonies above the stratification boundary further reduces water circulation at depth, such that subsequent stratification events kill increasingly larger areas of the reef, eventually producing massive, stagnant cells in which few corals can survive. Investigating the many other reef patterns may provide similar insights into the predominant natural ecological processes occurring on those reefs.

Sign in / Sign up

Export Citation Format

Share Document