scholarly journals Image Mosaic Research and Realization Based on LoFTR Algorithm

2021 ◽  
Author(s):  
Aikui Tian ◽  
Kangtao Wang ◽  
liye zhang ◽  
Bingcai Wei
Keyword(s):  
Feature Detection ◽  
Feature Matching ◽  
The Self ◽  
Image Feature ◽  
Feature Descriptor ◽  
Image Mosaic ◽  
Feature Points ◽  
Matching Method ◽  
Fusion Algorithm ◽  
The Matrix

Abstract Aiming at the problem of inaccurate extraction of feature points by the traditional image matching method, low robustness, and problems such as diffculty in inentifying feature points in area with poor texture. This paper proposes a new local image feature matching method, which replaces the traditional sequential image feature detection, description and matching steps. First, extract the coarse features with a resolution of 1/8 from the original image, then tile to a one-dimensional vector plus the positional encoding, feed them to the self-attention layer and cross-attention layer in the Transformer module, and finally get through the Differentiable Matching Layer and confidence matrix, after setting the threshold and the mutual closest standard, a Coarse-Level matching prediction is obtained. Secondly the fine matching is refined at the Fine-level match, after the Fine-level match is established, the image overlapped area is aligned by transforming the matrix to a unified coordinate, and finally the image is fused by the weighted fusion algorithm to realize the unification of seamless mosaic of images. This paper uses the self-attention layer and cross-attention layer in Transformers to obtain the feature descriptor of the image. Finally, experiments show that in terms of feature point extraction, LoFTR algorithm is more accurate than the traditional SIFT algorithm in both low-texture regions and regions with rich textures. At the same time, the image mosaic effect obtained by this method is more accurate than that of the traditional classic algorithms, the experimental effect is more ideal.

scholarly journals Optimization and Implementation of Synthetic Basis Feature Descriptor on FPGA

Electronics ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 391
Author(s):  
Dah-Jye Lee ◽  
Samuel G. Fuller ◽  
Alexander S. McCown
Keyword(s):  
High Speed ◽  
Feature Detection ◽  
Hardware Implementation ◽  
Feature Matching ◽  
Image Features ◽  
Image Feature ◽  
Superior Performance ◽  
Feature Descriptor ◽  
Binary Descriptors ◽  
Field Programmable

Feature detection, description, and matching are crucial steps for many computer vision algorithms. These steps rely on feature descriptors to match image features across sets of images. Previous work has shown that our SYnthetic BAsis (SYBA) feature descriptor can offer superior performance to other binary descriptors. This paper focused on various optimizations and hardware implementation of the newer and optimized version. The hardware implementation on a field-programmable gate array (FPGA) is a high-throughput low-latency solution which is critical for applications such as high-speed object detection and tracking, stereo vision, visual odometry, structure from motion, and optical flow. We compared our solution to other hardware designs of binary descriptors. We demonstrated that our implementation of SYBA as a feature descriptor in hardware offered superior image feature matching performance and used fewer resources than most binary feature descriptor implementations.

scholarly journals Panoramic image mosaic method based on image segmentation and Improved SIFT algorithm

2021 ◽  
Vol 2113 (1) ◽  
pp. 012066
Author(s):  
Lei Zhuang ◽  
Jiyan Yu ◽  
Yang Song
Keyword(s):  
Image Segmentation ◽  
Feature Point ◽  
Image Feature ◽  
Feature Descriptor ◽  
Image Mosaic ◽  
Panoramic Image ◽  
Feature Points ◽  
Sift Algorithm ◽  
Original Algorithm ◽  
Image Pairs

Abstract Aiming at the problem of large amount of calculation in extracting image feature points in panoramic image mosaic by SIFT algorithm, a panoramic image mosaic algorithm based on image segmentation and Improved SIFT is proposed in this paper. The algorithm fully considers the characteristics of panoramic image stitching. Firstly, the stitched image is divided into blocks, and the maximum overlapping block of image pairs is extracted by using mutual information. The SIFT key points are extracted by SIFT algorithm, and the dog is filtered before the spatial extreme value detection of SIFT algorithm to eliminate the feature points with small intensity value; When establishing the feature descriptor, the 128 dimension of the original algorithm is reduced to 64 dimensions to reduce the amount of calculation. In the feature point registration process, the feature descriptor is reduced to 32 dimensions, the feature point pairs are roughly extracted by the optimal node first BBF algorithm, and the feature point pairs are registered and screened by RANSAC; Finally, the image transformation matrix is obtained to realize panoramic image mosaic. The experimental results show that the proposed algorithm not only ensures the panoramic mosaic effect, but also extracts the feature points in 11% of the time of the traditional SIFT algorithm, and the feature point registration speed is 27.17% of the traditional SIFT algorithm.

scholarly journals Image Feature Matching Based on Semantic Fusion Description and Spatial Consistency

Symmetry ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 725
Author(s):  
Wei Zhang ◽  
Guoying Zhang
Keyword(s):  
Feature Matching ◽  
Spatial Information ◽  
Pso Algorithm ◽  
Image Feature ◽  
Distance Constraint ◽  
Feature Points ◽  
Matching Method ◽  
Feature Description ◽  
Spatial Consistency ◽  
Image Patches

Image feature description and matching is widely used in computer vision, such as camera pose estimation. Traditional feature descriptions lack the semantic and spatial information, and give rise to a large number of feature mismatches. In order to improve the accuracy of image feature matching, a feature description and matching method, based on local semantic information fusion and feature spatial consistency, is proposed in this paper. Once object detection is used on images, feature points are then extracted, and image patches with various sizes surrounding these points are clipped. These patches are sent into the Siamese convolution network to get their semantic vectors. Then, semantic fusion description of feature points is obtained by weighted sum of the semantic vectors, and their weights optimized by particle swarm optimization (PSO) algorithm. When matching these feature points using their descriptions, feature spatial consistency is calculated based on the spatial consistency of matched objects, and the orientation and distance constraint of adjacent points within matched objects. With the description and matching method, the feature points are matched accurately and effectively. Our experiment results showed the efficiency of our methods.

scholarly journals FSD-BRIEF: A Distorted BRIEF Descriptor for Fisheye Image Based on Spherical Perspective Model

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1839
Author(s):  
Yutong Zhang ◽  
Jianmei Song ◽  
Yan Ding ◽  
Yating Yuan ◽  
Hua-Liang Wei
Keyword(s):  
Feature Matching ◽  
Field Of View ◽  
Image Feature ◽  
Feature Points ◽  
Matching Process ◽  
Feature Descriptors ◽  
Coordinate Mapping ◽  
Matching Performance ◽  
Perspective Model ◽  
Attitude Matrix

Fisheye images with a far larger Field of View (FOV) have severe radial distortion, with the result that the associated image feature matching process cannot achieve the best performance if the traditional feature descriptors are used. To address this challenge, this paper reports a novel distorted Binary Robust Independent Elementary Feature (BRIEF) descriptor for fisheye images based on a spherical perspective model. Firstly, the 3D gray centroid of feature points is designed, and the position and direction of the feature points on the spherical image are described by a constructed feature point attitude matrix. Then, based on the attitude matrix of feature points, the coordinate mapping relationship between the BRIEF descriptor template and the fisheye image is established to realize the computation associated with the distorted BRIEF descriptor. Four experiments are provided to test and verify the invariance and matching performance of the proposed descriptor for a fisheye image. The experimental results show that the proposed descriptor works well for distortion invariance and can significantly improve the matching performance in fisheye images.

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

2021 ◽  
Vol 5 (4) ◽  
pp. 783-793
Author(s):  
Muhammad Muttabi Hudaya ◽  
Siti Saadah ◽  
Hendy Irawan
Keyword(s):  
Image Matching ◽  
Nearest Neighbor ◽  
Feature Matching ◽  
Image Feature ◽  
Brute Force ◽  
K Nearest Neighbor ◽  
Matching Method ◽  
Average Precision ◽  
Detection Model ◽  
Matching Process

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

scholarly journals Hybrid Invariant Local Features for Multiple Satellite Image Matching and Registration

2019 ◽  
Vol 9 (2) ◽  
pp. 309-314
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Satellite Image ◽  
Remote Sensing Data ◽  
Local Features ◽  
Feature Descriptor ◽  
Matching Method ◽  
Multiple Images ◽  
Feature Sets ◽  
Precise Relationship

Automatic image registration (IR) is very challenging and very important in the field of hyperspectral remote sensing data. Efficient autonomous IR method is needed with high precision, fast, and robust. A key operation of IR is to align the multiple images in single co-ordinate system for extracting and identifying variation between images considered. In this paper, presented a feature descriptor by combining features from both Feature from Accelerated Segment Test (FAST) and Binary Robust Invariant Scalable Key point (BRISK). The proposed hybrid invariant local features (HILF) descriptor extract useful and similar feature sets from reference and source images. The feature matching method allows finding precise relationship or matching among two feature sets. An experimental analysis described the outcome BRISK, FASK and proposed HILF in terms of inliers ratio and repeatability evaluation metrics.

Feature-Based GDLOH Deformable Registration for CT Lung Image

2013 ◽  
Vol 333-335 ◽  
pp. 969-973
Author(s):  
Yu Han Yang ◽  
Yao Qin Xie
Keyword(s):  
Feature Detection ◽  
Deformable Registration ◽  
Measurement Tool ◽  
Feature Descriptor ◽  
Feature Points ◽  
Scale Invariant ◽  
Clinical Images ◽  
Speeded Up Robust Features ◽  
Matching Process ◽  
Novel Approach

To improve the efficiency and accuracy of the conventional SIFT-TPS (Scale-invariant feature transform and Thin-Plate Spline) method in deformable registration for CT lung image, we develop a novel approach by using combining SURF(Speeded up Robust Features) and GDLOH(Gradient distance-location-orientation histogram) to detect matching feature points. First, we employ SURF as feature detection to find the stable feature points of the two CT images rapidly. Then GDLOH is taken as feature descriptor to describe each detected points characteristic, in order to supply measurement tool for matching process. In our experiment, five couples of clinical images are simulated using our algorithm above, result in an obvious improvement in run-time and registration quality, compared with the conventional methods. It is demonstrated that the proposed method may create a new window in performing a good robust and adaptively for deformable registration for CT lung tomography.

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 Local Deep Descriptor for Remote Sensing Image Feature Matching

2019 ◽  
Vol 11 (4) ◽  
pp. 430 ◽  
Author(s):  
Yunyun Dong ◽  
Weili Jiao ◽  
Tengfei Long ◽  
Lanfa Liu ◽  
Guojin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Computer Vision ◽  
Deep Learning ◽  
Feature Matching ◽  
Remote Sensing Image ◽  
Image Feature ◽  
Training Dataset ◽  
Feature Descriptor ◽  
Remote Sensing Images

Feature matching via local descriptors is one of the most fundamental problems in many computer vision tasks, as well as in the remote sensing image processing community. For example, in terms of remote sensing image registration based on the feature, feature matching is a vital process to determine the quality of transform model. While in the process of feature matching, the quality of feature descriptor determines the matching result directly. At present, the most commonly used descriptor is hand-crafted by the designer’s expertise or intuition. However, it is hard to cover all the different cases, especially for remote sensing images with nonlinear grayscale deformation. Recently, deep learning shows explosive growth and improves the performance of tasks in various fields, especially in the computer vision community. Here, we created remote sensing image training patch samples, named Invar-Dataset in a novel and automatic way, then trained a deep learning convolutional neural network, named DescNet to generate a robust feature descriptor for feature matching. A special experiment was carried out to illustrate that our created training dataset was more helpful to train a network to generate a good feature descriptor. A qualitative experiment was then performed to show that feature descriptor vector learned by the DescNet could be used to register remote sensing images with large gray scale difference successfully. A quantitative experiment was then carried out to illustrate that the feature vector generated by the DescNet could acquire more matched points than those generated by hand-crafted feature Scale Invariant Feature Transform (SIFT) descriptor and other networks. On average, the matched points acquired by DescNet was almost twice those acquired by other methods. Finally, we analyzed the advantages of our created training dataset Invar-Dataset and DescNet and gave the possible development of training deep descriptor network.

Automatic Image Mosaic Based on SIFT Using Bidirectional Matching

2012 ◽  
Vol 457-458 ◽  
pp. 841-847 ◽  
Author(s):  
Jian Fang Dou ◽  
Jian Xun Li
Keyword(s):  
Rapid Detection ◽  
Feature Detection ◽  
Moving Objects ◽  
Feature Matching ◽  
Weighted Average ◽  
Image Mosaic ◽  
Strong Robustness ◽  
Matching Strategy ◽  
Ransac Algorithm ◽  
Traditional Image

In the paper, an image mosaic algorithm based on SIFT feature matching is proposed. For an image mosaic method based on feature matching, feature detection is needed to perform in each image. Thus a rapid detection operator is essential to the efficiency of the whole algorithm. In this paper, we use SIFT to extract features. The extracted features are matched by k-d tree and bidirectional matching strategy to enhance the accuracy of matching. Then, a RANSAC algorithm is applied to eliminate outliers to ensure effectiveness of the matching. Finally images are stitched by weighted average blending algorithm. The presented algorithm overcomes the disadvantages of the traditional image mosaic methods which are susceptible to different scale and moving objects, and can achieve sub-pixel accuracy of matching and algorithm is still available to the images at different scale. Experimental results show that the method with strong robustness performs effectively.

Sign in / Sign up

Export Citation Format

Share Document