scholarly journals Robust Feature Matching with Spatial Smoothness Constraints

2020 ◽  
Vol 12 (19) ◽  
pp. 3158
Author(s):  
Xu Huang ◽  
Xue Wan ◽  
Daifeng Peng
Keyword(s):  
Energy Function ◽  
Feature Matching ◽  
Feature Point ◽  
Limiting Factors ◽  
Feature Points ◽  
Point Sets ◽  
Matching Accuracy ◽  
Matching Problem ◽  
Underlying Assumption ◽  
Speeded Up Robust Features

Feature matching is to detect and match corresponding feature points in stereo pairs, which is one of the key techniques in accurate camera orientations. However, several factors limit the feature matching accuracy, e.g., image textures, viewing angles of stereo cameras, and resolutions of stereo pairs. To improve the feature matching accuracy against these limiting factors, this paper imposes spatial smoothness constraints over the whole feature point sets with the underlying assumption that feature points should have similar matching results with their surrounding high-confidence points and proposes a robust feature matching method with the spatial smoothness constraints (RMSS). The core algorithm constructs a graph structure from the feature point sets and then formulates the feature matching problem as the optimization of a global energy function with first-order, spatial smoothness constraints based on the graph. For computational purposes, the global optimization of the energy function is then broken into sub-optimizations of each feature point, and an approximate solution of the energy function is iteratively derived as the matching results of the whole feature point sets. Experiments on close-range datasets with some above limiting factors show that the proposed method was capable of greatly improving the matching robustness and matching accuracy of some feature descriptors (e.g., scale-invariant feature transform (SIFT) and Speeded Up Robust Features (SURF)). After the optimization of the proposed method, the inlier number of SIFT and SURF was increased by average 131.9% and 113.5%, the inlier percentages between the inlier number and the total matches number of SIFT and SURF were increased by average 259.0% and 307.2%, and the absolute matching accuracy of SIFT and SURF was improved by average 80.6% and 70.2%.

Improvement of Image Mosaic Algorithm Based on SURF

2013 ◽  
Vol 427-429 ◽  
pp. 1625-1630
Author(s):  
Xu Lin Long ◽  
Qiang Chen ◽  
Jun Wei Bao
Keyword(s):  
Coordinate System ◽  
Random Sample ◽  
Clustering Algorithm ◽  
Feature Matching ◽  
Consensus Method ◽  
Image Mosaic ◽  
Matching Accuracy ◽  
Speeded Up Robust Features ◽  
Random Sample Consensus ◽  
Improved Algorithm

The present study concerns about feature matching in image mosaic. In order to solve the problems of low accuracy and poor applicability in the traditional speeded up robust features algorithm, this paper presents an improved algorithm. Clustering algorithm based on density instead of random sample consensus method is used to eliminate mismatching pairs. The initial matching pairs are mapped onto a plane coordinate system, which can be regarded as points, by calculating the density of each point to extract the final matching pairs. The results show that this algorithm overcomes the limitations of the traditional speeded up robust features mosaic method, improving the matching accuracy and speed, and the mosaic effect. It has certain theoretical and practical value.

Feature Matching Based on Triangle Guidance and Constraints

2018 ◽  
Vol 32 (08) ◽  
pp. 1855014 ◽  
Author(s):  
Hongmin Liu ◽  
Hongya Zhang ◽  
Zhiheng Wang ◽  
Yiming Zheng
Keyword(s):  
Feature Matching ◽  
High Accuracy ◽  
Geometric Constraints ◽  
Feature Point ◽  
Feature Points ◽  
Matching Method ◽  
Shared Feature ◽  
Triangular Structure ◽  
Circle Center ◽  
Image Transformations

For images with distortions or repetitive patterns, the existing matching methods usually work well just on one of the two kinds of images. In this paper, we present novel triangle guidance and constraints (TGC)-based feature matching method, which can achieve good results on both kinds of images. We first extract stable matched feature points and combine these points into triangles as the initial matched triangles, and triangles combined by feature points are as the candidates to be matched. Then, triangle guidance based on the connection relationship via the shared feature point between the matched triangles and the candidates is defined to find the potential matching triangles. Triangle constraints, specially the location of a vertex relative to the inscribed circle center of the triangle, the scale represented by the ratio of corresponding side lengths of two matching triangles and the included angles between the sides of two triangles with connection relationship, are subsequently used to verify the potential matches and obtain the correct ones. Comparative experiments show that the proposed TGC can increase the number of the matched points with high accuracy under various image transformations, especially more effective on images with distortions or repetitive patterns due to the fact that the triangular structure are not only stable to image transformations but also provides more geometric constraints.

scholarly journals A Registration Scheme for Multispectral Systems Using Phase Correlation and Scale Invariant Feature Matching

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Hanlun Li ◽  
Aiwu Zhang ◽  
Shaoxing Hu
Keyword(s):  
Phase Correlation ◽  
Feature Point ◽  
Reference Image ◽  
Feature Points ◽  
Scale Invariant ◽  
Matching Problem ◽  
Invariant Feature ◽  
Significant Difference ◽  
Scale Invariant Feature ◽  
Band Image

In the past few years, many multispectral systems which consist of several identical monochrome cameras equipped with different bandpass filters have been developed. However, due to the significant difference in the intensity between different band images, image registration becomes very difficult. Considering the common structural characteristic of the multispectral systems, this paper proposes an effective method for registering different band images. First we use the phase correlation method to calculate the parameters of a coarse-offset relationship between different band images. Then we use the scale invariant feature transform (SIFT) to detect the feature points. For every feature point in a reference image, we can use the coarse-offset parameters to predict the location of its matching point. We only need to compare the feature point in the reference image with the several near feature points from the predicted location instead of the feature points all over the input image. Our experiments show that this method does not only avoid false matches and increase correct matches, but also solve the matching problem between an infrared band image and a visible band image in cases lacking man-made objects.

scholarly journals ICA-ASIFT-Based Multi-Temporal Matching of High-Resolution Remote Sensing Urban Images

2016 ◽  
Vol 16 (5) ◽  
pp. 34-49 ◽  
Author(s):  
Fenghua Huang ◽  
Zhengyuan Mao ◽  
Wenzao Shi
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Large Scale ◽  
Feature Point ◽  
Feature Points ◽  
Affine Invariant ◽  
Remote Sensing Images ◽  
Matching Accuracy ◽  
Affine Transform ◽  
Urban Images

Abstract While SIFT (Scale Invariant Feature Transform) features are used to match High-Resolution (HR) remote sensing urban images captured at different phases with large scale and view variations, feature points are few and the matching accuracy is low. Although replacing SIFT with fully affine invariant features ASIFT (Affine-SIFT) can increase the number of feature points, it results in matching inefficiency and a non-uniform distribution of matched feature point pairs. To address these problems, this paper proposes the novel matching method ICA-ASIFT, which matches HR remote sensing urban images captured at different phases by using an Independent Component Analysis algorithm (ICA) and ASIFT features jointly. First, all possible affine deformations are modeled for the image transform, extracting ASIFT features of remote sensing images captured at different times. The ICA algorithm reduces the dimensionality of ASIFT features and improves matching efficiency of subsequent ASIFT feature point pairs. Next, coarse matching is performed on ASIFT feature point pairs through the algorithms of Nearest Vector Angle Ratio (NVAR), Direction Difference Analysis (DDA) and RANdom SAmple Consensus (RANSAC), eliminating apparent mismatches. Then, fine matching is performed on rough matched point pairs using a Neighborhoodbased Feature Graph Matching algorithm (NFGM) to obtain final ASIFT matching point pairs of remote sensing images. Finally, final matching point pairs are used to compute the affine transform matrix. Matching HR remote sensing images captured at different phases is achieved through affine transform. Experiments are used to compare the performance of ICA-ASFIT and three other algorithms (i.e., Harris- SIFT, PCA-SIFT, TD-ASIFT) on HR remote sensing images captured at different times in different regions. Experimental results show that the proposed ICA-ASFIT algorithm effectively matches HR remote sensing urban images and outperforms other algorithms in terms of matching accuracy and efficiency.

Unusual Event Detection using Mean Feature Point Matching Algorithm

2016 ◽  
Vol 6 (4) ◽  
pp. 1595 ◽  
Author(s):  
Chitra Hegde ◽  
Shakti Singh Chundawat ◽  
Divya S N
Keyword(s):  
Input Image ◽  
Feature Point ◽  
Experimental Result ◽  
Feature Points ◽  
Surveillance Video ◽  
Point Matching ◽  
Public And Private ◽  
Unusual Event ◽  
Speeded Up Robust Features ◽  
Feature Point Matching

Analysis and detection of unusual events in public and private surveillance system is a complex task. Detecting unusual events in surveillance video requires the appropriate definition of similarity between events. The key goal of the proposed system is to detect behaviours or actions that can be considered as anomalies. Since suspicious events differ from domain to domain, it remains a challenge to detect those events in major domains such as airport, super malls, educational institutions etc. The proposed Mean Feature Point Matching (MFPM) algorithm is used for detecting unusual events. The Speeded-Up Robust Features (SURF) method is used for feature extraction. The MFPM algorithm compares the feature points of the input image with the mean feature points of trained dataset. The experimental result shows that the proposed system is efficient and accurate for wide variety of surveillance videos.

scholarly journals Study on Reconstruction and Feature Tracking of Silicone Heart 3D Surface

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7570
Author(s):  
Ziyan Zhang ◽  
Yan Liu ◽  
Jiawei Tian ◽  
Shan Liu ◽  
Bo Yang ◽  
...  
Keyword(s):  
Surface Reconstruction ◽  
Feature Tracking ◽  
Feature Matching ◽  
Negative Impact ◽  
Three Dimensional ◽  
Geometric Constraints ◽  
Feature Point ◽  
Feature Points ◽  
3D Surface Reconstruction ◽  
3D Surface

At present, feature-based 3D reconstruction and tracking technology is widely applied in the medical field. In minimally invasive surgery, the surgeon can achieve three-dimensional reconstruction through the images obtained by the endoscope in the human body, restore the three-dimensional scene of the area to be operated on, and track the motion of the soft tissue surface. This enables doctors to have a clearer understanding of the location depth of the surgical area, greatly reducing the negative impact of 2D image defects and ensuring smooth operation. In this study, firstly, the 3D coordinates of each feature point are calculated by using the parameters of the parallel binocular endoscope and the spatial geometric constraints. At the same time, the discrete feature points are divided into multiple triangles using the Delaunay triangulation method. Then, the 3D coordinates of feature points and the division results of each triangle are combined to complete the 3D surface reconstruction. Combined with the feature matching method based on convolutional neural network, feature tracking is realized by calculating the three-dimensional coordinate changes of the same feature point in different frames. Finally, experiments are carried out on the endoscope image to complete the 3D surface reconstruction and feature tracking.

scholarly journals Precise vehicle ego-localization using feature matching of pavement images

2020 ◽  
Vol 3 (2) ◽  
pp. 37-47
Author(s):  
Zijun Jiang ◽  
Zhigang Xu ◽  
Yunchao Li ◽  
Haigen Min ◽  
Jingmei Zhou
Keyword(s):  
Real Time ◽  
Intelligent Transportation System ◽  
Feature Matching ◽  
Consensus Algorithm ◽  
Feature Points ◽  
Content Type ◽  
Localization Accuracy ◽  
Vehicle Localization ◽  
Speeded Up Robust Features ◽  
Automatic Parking

Purpose Precise vehicle localization is a basic and critical technique for various intelligent transportation system (ITS) applications. It also needs to adapt to the complex road environments in real-time. The global positioning system and the strap-down inertial navigation system are two common techniques in the field of vehicle localization. However, the localization accuracy, reliability and real-time performance of these two techniques can not satisfy the requirement of some critical ITS applications such as collision avoiding, vision enhancement and automatic parking. Aiming at the problems above, this paper aims to propose a precise vehicle ego-localization method based on image matching. Design/methodology/approach This study included three steps, Step 1, extraction of feature points. After getting the image, the local features in the pavement images were extracted using an improved speeded up robust features algorithm. Step 2, eliminate mismatch points. Using a random sample consensus algorithm to eliminate mismatched points of road image and make match point pairs more robust. Step 3, matching of feature points and trajectory generation. Findings Through the matching and validation of the extracted local feature points, the relative translation and rotation offsets between two consecutive pavement images were calculated, eventually, the trajectory of the vehicle was generated. Originality/value The experimental results show that the studied algorithm has an accuracy at decimeter-level and it fully meets the demand of the lane-level positioning in some critical ITS applications.

scholarly journals An Improved Method for Stable Feature Points Selection in Structure-from-Motion Considering Image Semantic and Structural Characteristics

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2416
Author(s):  
Fei Wang ◽  
Zhendong Liu ◽  
Hongchun Zhu ◽  
Pengda Wu ◽  
Chengming Li
Keyword(s):  
Structure From Motion ◽  
Feature Matching ◽  
Structural Characteristics ◽  
Feature Point ◽  
Feature Points ◽  
Improved Method ◽  
Point Selection ◽  
Aerial Triangulation ◽  
Oblique Images ◽  
Stable Feature

Feature matching plays a crucial role in the process of 3D reconstruction based on the structure from motion (SfM) technique. For a large collection of oblique images, feature matching is one of the most time-consuming steps, and the matching result directly affects the accuracy of subsequent tasks. Therefore, how to extract the reasonable feature points robustly and efficiently to improve the matching speed and quality has received extensive attention from scholars worldwide. Most studies perform quantitative feature point selection based on image Difference-of-Gaussian (DoG) pyramids in practice. However, the stability and spatial distribution of feature points are not considered enough, resulting in selected feature points that may not adequately reflect the scene structures and cannot guarantee the matching rate and the aerial triangulation accuracy. To address these issues, an improved method for stable feature point selection in SfM considering image semantic and structural characteristics is proposed. First, the visible-band difference vegetation index is used to identify the vegetation areas from oblique images, and the line feature in the image is extracted by the optimized line segment detector algorithm. Second, the feature point two-tuple classification model is established, in which the vegetation area recognition result is used as the semantic constraint, the line feature extraction result is used as the structural constraint, and the feature points are divided into three types. Finally, a progressive selection algorithm for feature points is proposed, in which feature points in the DoG pyramid are selected by classes and levels until the number of feature points is satisfied. Oblique images of a 40-km2 area in Dongying city, China, were used for validation. The experimental results show that compared to the state-of-the-art method, the method proposed in this paper not only effectively reduces the number of feature points but also better reflects the scene structure. At the same time, the average reprojection error of the aerial triangulation decrease by 20%, the feature point matching rate increase by 3%, the selected feature points are more stable and reasonable.

scholarly journals Unusual Event Detection using Mean Feature Point Matching Algorithm

2016 ◽  
Vol 6 (4) ◽  
pp. 1595
Author(s):  
Chitra Hegde ◽  
Shakti Singh Chundawat ◽  
Divya S N
Keyword(s):  
Input Image ◽  
Feature Point ◽  
Experimental Result ◽  
Feature Points ◽  
Surveillance Video ◽  
Point Matching ◽  
Public And Private ◽  
Unusual Event ◽  
Speeded Up Robust Features ◽  
Feature Point Matching

Analysis and detection of unusual events in public and private surveillance system is a complex task. Detecting unusual events in surveillance video requires the appropriate definition of similarity between events. The key goal of the proposed system is to detect behaviours or actions that can be considered as anomalies. Since suspicious events differ from domain to domain, it remains a challenge to detect those events in major domains such as airport, super malls, educational institutions etc. The proposed Mean Feature Point Matching (MFPM) algorithm is used for detecting unusual events. The Speeded-Up Robust Features (SURF) method is used for feature extraction. The MFPM algorithm compares the feature points of the input image with the mean feature points of trained dataset. The experimental result shows that the proposed system is efficient and accurate for wide variety of surveillance videos.

Image Feature Matching Based on SIFT Algorithm

2014 ◽  
Vol 644-650 ◽  
pp. 4157-4161
Author(s):  
Xin Zhang ◽  
Ya Sheng Zhang ◽  
Hong Yao
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Quadratic Function ◽  
Scale Space ◽  
Feature Point ◽  
Image Feature ◽  
Three Dimension ◽  
Feature Points ◽  
Gradient Distribution ◽  
Sift Feature

In the process of image matching, it is involved such as image rotation, scale zooming, brightness change and other problems. In order to improve the precision of image matching, image matching algorithm based on SIFT feature point is proposed. First, the method of generating scale space is introduced. Then, the scale and position of feature points are determined through three dimension quadratic function and feature vectors are determined through gradient distribution characteristic of neighborhood pixels of feature points. Finally, feature matching is completed based on the Euclidean distance. The experiment result indicates that using SIFT feature point can achieve image matching effectively.

Sign in / Sign up

Export Citation Format

Share Document