Topological Similarity-Based Multi-Target Correlation Localization for Aerial-Ground Systems

2021 ◽  
Vol 01 (03) ◽  
Author(s):  
Xudong Li ◽  
Lizhen Wu ◽  
Yifeng Niu ◽  
Shengde Jia ◽  
Bosen Lin
Keyword(s):  
Correlation Method ◽  
Threshold Method ◽  
Fusion Algorithm ◽  
Visual Axis ◽  
Topological Similarity ◽  
Correlation Algorithm ◽  
Correlation Problem ◽  
Similarity Method ◽  
Better Than ◽  
Ground Systems

In this paper, an algorithm for solving the multi-target correlation and co-location problem of aerial-ground heterogeneous system is investigated. Aiming at the multi-target correlation problem, the fusion algorithm of visual axis correlation method and improved topological similarity correlation method are adopted in view of large parallax and inconsistent scale between the aerial and ground perspectives. First, the visual axis was preprocessed by the threshold method, so that the sparse targets were initially associated. Then, the improved topological similarity method was used to further associate dense targets with the relative position characteristics between targets. The shortcoming of dense target similarity with small difference was optimized by the improved topological similarity method. For the problem of co-location, combined with the multi-target correlation algorithm in this paper, the triangulation positioning model was used to complete the co-location of multiple targets. In the experimental part, simulation experiments and flight experiments were designed to verify the effectiveness of the algorithm. Experimental results show that the proposed algorithm can effectively achieve multi-target correlation positioning, and that the positioning accuracy is obviously better than other positioning methods.

Auto White Balance Algorithm in Digital Camera

2012 ◽  
Vol 182-183 ◽  
pp. 2080-2084
Author(s):  
Jie Li ◽  
Xue Xiang Wang ◽  
Hao Liu
Keyword(s):  
Hardware Implementation ◽  
Digital Camera ◽  
Low Complexity ◽  
Light Sources ◽  
Light Conditions ◽  
Threshold Method ◽  
White Balance ◽  
White Point ◽  
A New Technique ◽  
Better Than

Auto white balance (AWB) is an important function of digital camera. The purpose of white balance is to adjust the image to make it look like taken under standard light conditions. We present a new technique to detect the reference white point of image in this paper. This technique detects the white point of image by using dynamic threshold method, thus making it more flexible and more applicable compared to other algorithms. We test 50 images which were taken under different light sources, and find that this algorithm is better than or comparable to other algorithms both in subjective and objective aspects. At the same time, this algorithm has low complexity, and it can be easily applied to hardware implementation.

Application of Cascade-Correlation Algorithm in Vibration Characteristics of Hydro Turbine

2010 ◽  
Vol 108-111 ◽  
pp. 1070-1074
Author(s):  
Li Ying Wang ◽  
Wei Guo Zhao ◽  
Jian Min Hou
Keyword(s):  
Bp Neural Network ◽  
Learning Algorithm ◽  
Optimal Operation ◽  
Vibration Characteristics ◽  
Bp Algorithm ◽  
Practical Significance ◽  
Hydro Turbine ◽  
Correlation Algorithm ◽  
Cascade Correlation ◽  
Better Than

The cascade correlation algorithm that is CC algorithms, CC network structure and CC network weights learning algorithm are introduced, based on the operation data of Wanjiazhai hydropower station, considering the pressure fluctuation, the network model of vibration characteristics is established based on CC algorithm, and the applications of CC and BP algorithm in vibration characteristics of turbine are compared. The results show that the CC algorithm is better than BP neural network, the results can be used in the optimal operation of hydropower, and it has a practical significance.

scholarly journals Valid Probabilistic Anomaly Detection Models for System Logs

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Chunbo Liu ◽  
Lanlan Pan ◽  
Zhaojun Gu ◽  
Jialiang Wang ◽  
Yitong Ren ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Large Scale ◽  
Learning Algorithm ◽  
Recall Rate ◽  
Support Vector ◽  
Fusion Algorithm ◽  
Flexible Tool ◽  
System Logs ◽  
Output Only ◽  
Better Than

System logs can record the system status and important events during system operation in detail. Detecting anomalies in the system logs is a common method for modern large-scale distributed systems. Yet threshold-based classification models used for anomaly detection output only two values: normal or abnormal, which lacks probability of estimating whether the prediction results are correct. In this paper, a statistical learning algorithm Venn-Abers predictor is adopted to evaluate the confidence of prediction results in the field of system log anomaly detection. It is able to calculate the probability distribution of labels for a set of samples and provide a quality assessment of predictive labels to some extent. Two Venn-Abers predictors LR-VA and SVM-VA have been implemented based on Logistic Regression and Support Vector Machine, respectively. Then, the differences among different algorithms are considered so as to build a multimodel fusion algorithm by Stacking. And then a Venn-Abers predictor based on the Stacking algorithm called Stacking-VA is implemented. The performances of four types of algorithms (unimodel, Venn-Abers predictor based on unimodel, multimodel, and Venn-Abers predictor based on multimodel) are compared in terms of validity and accuracy. Experiments are carried out on a log dataset of the Hadoop Distributed File System (HDFS). For the comparative experiments on unimodels, the results show that the validities of LR-VA and SVM-VA are better than those of the two corresponding underlying models. Compared with the underlying model, the accuracy of the SVM-VA predictor is better than that of LR-VA predictor, and more significantly, the recall rate increases from 81% to 94%. In the case of experiments on multiple models, the algorithm based on Stacking multimodel fusion is significantly superior to the underlying classifier. The average accuracy of Stacking-VA is larger than 0.95, which is more stable than the prediction results of LR-VA and SVM-VA. Experimental results show that the Venn-Abers predictor is a flexible tool that can make accurate and valid probability predictions in the field of system log anomaly detection.

Multi-Focus Image Fusion Using Local Energy Pattern

2011 ◽  
Vol 145 ◽  
pp. 119-123
Author(s):  
Ko Chin Chang
Keyword(s):  
Wavelet Transform ◽  
Image Fusion ◽  
Discrete Wavelet Transform ◽  
Discrete Wavelet ◽  
Local Energy ◽  
View Point ◽  
Fusion Algorithm ◽  
Image Capture ◽  
Focus Image ◽  
Better Than

For general image capture device, it is difficult to obtain an image with every object in focus. To solve the fusion issue of multiple same view point images with different focal settings, a novel image fusion algorithm based on local energy pattern (LGP) is proposed in this paper. Firstly, each focus images is decomposed using discrete wavelet transform (DWT) separately. Secondly, to calculate LGP with the corresponding pixel and its surrounding pixels, then use LGP to compute the new coefficient of the pixel from each transformed images with our proposed weighted fusing rules. The rules use different operations in low-bands coefficients and high-bands coefficients. Finally, the generated image is reconstructed from the new subband coefficients. Moreover, the reconstructed image can represent more detailed for the obtained scene. Experimental results demonstrate that our scheme performs better than the traditional discrete cosine transform (DCT) and discrete wavelet transform (DWT) method in both visual perception and quantitative analysis.

scholarly journals A Novel Frequency Domain Iterative Image Registration Algorithm Based on Local Region Extraction

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Xiujie Qu ◽  
Haili Huo ◽  
Sitong Lian ◽  
Fei Zhao
Keyword(s):  
High Speed ◽  
Large Angle ◽  
Correlation Method ◽  
Target Position ◽  
Local Region ◽  
Phase Correlation ◽  
Geometric Distortion ◽  
Speeded Up Robust Features ◽  
Correlation Algorithm ◽  
Region Extraction

Because of the differences of imaging time, position between sensor and target position, scaling, rotation, translation, and other transformations between the series of images will be generated by the imaging system. The conventional phase correlation algorithm has been widely applied because of its advantages of high speed, precision, and weak influence of the geometric distortion when computing these changing parameters. However, when the scaling factor and the rotation angle are too large, it is difficult to use the conventional phase correlation method for high precision registration. To solve this problem, this paper presents a novel method, which combines the speeded up robust features algorithm and the phase correlation method under the log polar. Through local region extraction and reusing a two-step iterative phase correlation algorithm, this method avoids excessive computation and the demand of characteristics of the image and effectively improves the accuracy of registration. A plurality of visible light image simulation verifies that this is a fast, accurate, and robust algorithm, even when the image has large angle rotation and large multiple scaling.

Bidimensional strain measurement using digital images

1999 ◽  
Vol 213 (8) ◽  
pp. 811-817 ◽  
Author(s):  
P Vacher ◽  
S Dumoulin ◽  
F Morestin ◽  
S Mguil-Touchal
Keyword(s):  
Displacement Field ◽  
Strain Measurement ◽  
Strain Field ◽  
Iterative Process ◽  
Large Range ◽  
Correlation Method ◽  
Image Correlation ◽  
Large Strains ◽  
Elastic Strains ◽  
Better Than

This paper proposes a method that allows a strain field on plane samples to be determined using the digital image correlation method. The displacement field is approximated by an iterative process attempting to optimize the correlation between two pictures, the first one before strain and the second one after strain. The precision obtained on the displacement field can be better than 0.01 pixel. This precision makes it possible to calculate the strains in a large range, from elastic strains (>0.01 per cent) to large strains (>200 per cent), with or without a strain gradient.

Novel Infrared and Visible Images Fusion Algorithm Based on NSCT

2014 ◽  
Vol 989-994 ◽  
pp. 3763-3767
Author(s):  
Hai Feng Tan ◽  
Tian Wen Luo ◽  
Jing Jun Zhu ◽  
Guan Zhong Li ◽  
Quan Xi Zhang
Keyword(s):  
High Frequency ◽  
Low Frequency ◽  
Nonsubsampled Contourlet Transform ◽  
Target Image ◽  
Fusion Algorithm ◽  
Regional Energy ◽  
Fusion Methods ◽  
Visible Images ◽  
Regional Variance ◽  
Better Than

A novel fusion algorithm based on Nonsubsampled Contourlet Transform (NSCT) is proposed, according to the characteristics of infrared and visible images. Firstly, the registered infrared and visible images from the same scene were transformed by NSCT transforms; then the low frequency coefficient is fused by the combination of local energy and normalised correlation matrix, the high frequency coefficient fusion is fused by regional energy matching with regional variance; finally, the target image is obtained by performing inverse NSCT transforms. experimental results indicate that the proposed algorithm can effectively get more detail information and the fusion performance is dramatically better than traditional fusion methods.

LBSN-Based Personalized Routes Recommendation

2014 ◽  
Vol 644-650 ◽  
pp. 3230-3234
Author(s):  
Li Chao Zhu ◽  
Zhi Jun Li ◽  
Shou Xu Jiang
Keyword(s):  
Social Network ◽  
Activity Pattern ◽  
Activity Patterns ◽  
Semantic Space ◽  
Location Based Social Network ◽  
Geographical Space ◽  
Similarity Method ◽  
Better Than

In this paper, we present personalized routes recommendation on Location Based Social Network. We model user in both geographical space and semantic space, and define Activity Pattern to describe individual’s personalized character, i.e. individual’s activity regularity. We extract routes which match individual’s activity patterns from high similar users’ trajectories, and according to scoring strategy to recommend top-k routes to a user. We evaluated our method with a real GPS dataset collected from GeoLife. The results show that there exist Activity Pattern in individual’s movement, and our method is better than traditional Cosine-based Similarity method on both precision and k-cover.

Liquid Flow Measurement by Cross-Correlation of Temperature Fluctuations

1972 ◽  
Vol 5 (11) ◽  
pp. 435-439 ◽  
Author(s):  
S A Abesekera ◽  
M S Beck
Keyword(s):  
Laminar Flow ◽  
Liquid Flow ◽  
Flow Measurement ◽  
Cross Correlation ◽  
Correlation Method ◽  
Velocity Profiles ◽  
Pulsating Flow ◽  
Flow Conditions ◽  
Viscous Liquids ◽  
Better Than

The applicability of the temperature cross-correlation method to the measurement of liquid flow under steady and pulsating flow conditions is investigated and some further results to those published earlier are presented. The method is proved to be an accurate and reliable method of flow measurement in laminar flow of highly viscous liquids and turbulent flow of liquids under steady and pulsating flow conditions. In laminar flow, the measurement is dependent on the velocity profiles and hence sensitive to any disturbances which may distort the velocity profiles. In pulsating flow, the measurement is dependent on a parameter called the ‘Frequency parameter’ (KR). Only if KR <1 can the flow meter, calibrated for steady flow measurement, meter pulsating flow accurately. This condition is easily satisfied by highly viscous liquids. The measurement technique provides a linear output and an accuracy better than 3% can be achieved.

Research on the Unusual Graphic Display in Creative Design for Graphic Ads

2014 ◽  
Vol 933 ◽  
pp. 662-666
Author(s):  
Jun Peng
Keyword(s):  
Correlation Method ◽  
Creative Design ◽  
Graphic Display ◽  
Creative Methods ◽  
Graphic Language ◽  
Similarity Method

The graphic ad is to convey the theme accurately and clearly with its own unique graphic language. The unusual graphic display is an effective way for graphic creativity and expression. This paper analyzes and discusses the influence and significance of the unusual graphic display on the graphic ad design with some creative methods, such as correlation method, similarity method, contradicting method, multi-angle graphic expression method. etc.

Sign in / Sign up

Export Citation Format

Share Document