Vector Planar Elements: Geometrical Similarity Measurement Based on Fourier Descriptors

GEOMATICA ◽  
2015 ◽  
Vol 69 (4) ◽  
pp. 385-394
Author(s):  
Zhanlong Chen ◽  
Yongyang Xu ◽  
Liang Wu
Keyword(s):  
Extraction Method ◽  
Shortest Paths ◽  
Impact Factors ◽  
Similarity Measurement ◽  
Fourier Descriptors ◽  
Feature Points ◽  
Scaling Invariance ◽  
Geometrical Similarity ◽  
Contour Feature

With the rotation, translation and scaling invariance, etc. it is difficult to measure the similarity between GIS planar elements. To describe the graphics precisely, according to the number of shortest paths where vertices occur, we define the “vertex betweenness;” this measures the importance of each vertex in a graph. The higher the vertex betweenness, the more important vertex becomes. We propose a contour fea ture points extraction method, where Fourier descriptors are used. We normalize the first n order factors of Fourier descriptors, on the basis of similarity between polygons, which is obtained by comparing the cosine values for every two vectors. The experiment is operated on two different data scales, 1:50 000 and 1:250 000. Combined with analysis of impact factors during similarity measurement, the experiment results show that the contour feature points extraction method can effectively measure the geometrical similarity between GIS planar elements.

A New Algorithm of Image Registration Based on Contour Feature

2014 ◽  
Vol 912-914 ◽  
pp. 1092-1097
Author(s):  
Fu Hua Song ◽  
Peng Hui Li ◽  
Jian Ran Deng
Keyword(s):  
Image Registration ◽  
Rotation Angle ◽  
Closed Contour ◽  
Feature Points ◽  
Registration Algorithm ◽  
Image Registration Algorithm ◽  
Contour Feature ◽  
Circular Correlation ◽  
Open Contour ◽  
Calculated Amount

Image registration is an important task in image processing. In this paper, a new and fast contour-based image registration algorithm is proposed. In this algorithm, we fetch contour points and calculate the normal angles firstly, then figure out the histogram of the contour-feature points. By computing circular correlation of the histogram, the rotation angle can be gained. As the rotation angle is obtained, it vastly simplifies the complexity of estimating other registration parameters and reduces the calculated amount, thus achieving a fast image registration algorithm. This algorithm has the invariance of rotation, translation and scale, and it has high robustness for either open contour or closed contour.

scholarly journals Multi-Player Tracking for Multi-View Sports Videos with Improved K-Shortest Path Algorithm

2020 ◽  
Vol 10 (3) ◽  
pp. 864
Author(s):  
Qiaokang Liang ◽  
Wanneng Wu ◽  
Yukun Yang ◽  
Ruiheng Zhang ◽  
Yu Peng ◽  
...  
Keyword(s):  
Measurement Method ◽  
Detection Method ◽  
Shortest Paths ◽  
Similarity Measurement ◽  
Appearance Model ◽  
Shortest Path Algorithm ◽  
Tracking Method ◽  
Player Tracking ◽  
Sports Videos ◽  
Better Than

Sports analysis has recently attracted increasing research efforts in computer vision. Among them, basketball video analysis is very challenging due to severe occlusions and fast motions. As a typical tracking-by-detection method, k-shortest paths (KSP) tracking framework has been well used for multiple-person tracking. While effective and fast, the neglect of the appearance model would easily lead to identity switches, especially when two or more players are intertwined with each other. This paper addresses this problem by taking the appearance features into account based on the KSP framework. Furthermore, we also introduce a similarity measurement method that can fuse multiple appearance features together. In this paper, we select jersey color and jersey number as two example features. Experiments indicate that about 70% of jersey color and 50% of jersey number over a whole sequence would ensure our proposed method preserve the player identity better than the existing KSP tracking method.

scholarly journals A New Skeleton Feature Extraction Method for Terrain Model Using Profile Recognition and Morphological Simplification

2013 ◽  
Vol 2013 ◽  
pp. 1-16
Author(s):  
Huijie Zhang ◽  
Zhiqiang Ma ◽  
Yaxin Liu ◽  
Xinting He ◽  
Yun Ma
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Feature Points ◽  
Feature Extraction Method ◽  
Terrain Model ◽  
Noise Point ◽  
Key Factor ◽  
Morphological Theory ◽  
Negative Effect ◽  
Real Experimental Data

It is always difficul to reserve rings and main truck lines in the real engineering of feature extraction for terrain model. In this paper, a new skeleton feature extraction method is proposed to solve these problems, which put forward a simplification algorithm based on morphological theory to eliminate the noise points of the target points produced by classical profile recognition. As well all know, noise point is the key factor to influence the accuracy and efficiency of feature extraction. Our method connected the optimized feature points subset after morphological simplification; therefore, the efficiency of ring process and pruning has been improved markedly, and the accuracy has been enhanced without the negative effect of noisy points. An outbranching concept is defined, and the related algorithms are proposed to extract sufficient long trucks, which is capable of being consistent with real terrain skeleton. All of algorithms are conducted on many real experimental data, including GTOPO30 and benchmark data provided by PPA to verify the performance and accuracy of our method. The results showed that our method precedes PPA as a whole.

scholarly journals Automatic Cell Segmentation in Cyto- and Histometry Using Dominant Contour Feature Points

1998 ◽  
Vol 17 (4) ◽  
pp. 243-250 ◽  
Author(s):  
U. Pal ◽  
Karsten Rodenacker ◽  
B. B. Chaudhuri
Keyword(s):  
Cell Segmentation ◽  
Manual Segmentation ◽  
Feature Points ◽  
Shape Features ◽  
Dominant Feature ◽  
Contour Feature ◽  
Segmentation Approach

Automatic cell segmentation has various application potentials in cytometry and histometry. In this paper, an automatic cluster (touching) cell segmentation approach using the dominant contour feature points has been presented. Dominant feature points are the locations of indentation on the contour of the cluster. First, dominant feature points on the contour of the cluster are detected by distance profile. Next, using shape features of the cells, these feature points are selected for segmentation. We compared the results of the proposed method with manual segmentation and observed that the method has an overall accuracy about to 82%.

A Sum-of-Squares Polynomial Approach for Road Anomaly Detection Using Vehicle Sensor Measurements

2017 ◽  
Author(s):  
Dule Shu ◽  
Constantino Lagoa ◽  
Timothy Cleary
Keyword(s):  
Feature Extraction ◽  
Anomaly Detection ◽  
Extraction Method ◽  
Sum Of Squares ◽  
New Method ◽  
Feature Points ◽  
Feature Extraction Method ◽  
Different Types ◽  
Simulation Results ◽  
Vehicle Sensor

This paper presents a new method for road anomaly detection. The existence of road anomalies is determined by the behaviors of vehicles. A special polynomial named Sum-of-Squares (SOS) polynomial is used as a metric to evaluate the normality of vehicle behaviors. The method can process multiple types of sensor measurements. A feature extraction method is used to obtain concise representations of the sensor measurements. These representations, called feature points, are used to calculate the value of the SOS polynomial. Simulation results have been shown to demonstrate that the proposed method can effectively detect different types of road anomalies.

scholarly journals Research on Feature Extraction Method of Indoor Visual Positioning Image Based on Area Division of Foreground and Background

2021 ◽  
Vol 10 (6) ◽  
pp. 402
Author(s):  
Ping Zheng ◽  
Danyang Qin ◽  
Bing Han ◽  
Lin Ma ◽  
Teklu Merhawit Berhane
Keyword(s):  
Feature Extraction ◽  
Open Source Software ◽  
Extraction Method ◽  
Feature Matching ◽  
Physical World ◽  
Feature Points ◽  
Feature Extraction Method ◽  
Visual Positioning ◽  
Extraction Algorithm ◽  
Better Than

In the process of indoor visual positioning and navigation, difficult points often exist in corridors, stairwells, and other scenes that contain large areas of white walls, strong consistent background, and sparse feature points. Aiming at the problem of positioning and navigation in the real physical world where the walls with sparse feature points are difficult to be filled with pictures, this paper designs a feature extraction method, ARAC (Adaptive Region Adjustment based on Consistency) using Free and Open-Source Software and tools. It divides the image into foreground and background and extracts their features respectively, to achieve not only retain positioning information but also focus more energy on the foreground area which is favourable for navigation. In the test phase, under the combined conditions of illumination, scale and affine changes, the feature matching maps by the feature extraction algorithm proposed in this paper are compared with those by SIFT and SURF. Experiments show that the number of correctly matched feature pairs obtained by ARAC is better than SIFT and SURF, and whose time of feature extraction and matching is comparable to SURF, which verifies the accuracy and efficiency of the ARAC feature extraction method.

Sign in / Sign up

Export Citation Format

Share Document