An Infrared-Visible Image Registration Method Based on the Constrained Point Feature

Li, Qingqing; Han, Guangliang; Liu, Peixun; Yang, Hang; Luo, Huiyuan; Wu, Jiajia

doi:10.3390/s21041188

Cited by 8 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [12] proposed a method for registering infrared and visible images based on constrained point features to address the high complexity of traditional point features. This approach avoids the construction of complex feature descriptors and introduces advanced semantic information to improve the registration accuracy.…”

Section: Related Workmentioning

confidence: 99%

Research on Infrared and Visible Image Registration Algorithm for Complex Road Scenes

2023

View full text Add to dashboard Cite

This study proposes a novel image registration algorithm to solve the problem of low registration accuracy caused by excessive difference in resolution and spectral differences between infrared and visible images. First, we use a VI-CycleGAN network to translate visible images into fake infrared images. Furthermore, we incorporate a normalization-based attention mechanism (NAM) into each residual block to capture the global information of the image and preserve its details. Meanwhile, we consider higherlevel semantic information and introduce a hybrid loss function that better preserves the content features of the original image. We then use guided filtering to process the infrared image and fake infrared image to eliminate complex background noise. Subsequently, coarse registration was performed using the Speeded-Up Robust Features (SURF) algorithm. Finally, we used the random sample consensus (RANSAC) algorithm to remove the mismatch points and achieve accurate registration. This study conducted experiments on two different VIS-IR image datasets and compared Gaussian field estimator with manifold regularization (GFEMR), radiation-variation insensitive feature transform (RIFT), and locally normalized image feature transform (LNIFT) algorithms. The experimental results show that compared with LNIFT algorithms, the registration accuracy of the proposed method was improved by approximately 5%.INDEX TERMS Image registration, feature matching, infrared image, visible image, feature descriptor.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on Infrared and Visible Image Registration Algorithm for Complex Road Scenes

2023

View full text Add to dashboard Cite

show abstract

“…It is therefore necessary to convert the collected images into the same coordinate system and calibrate feature relations between two images through remote sensing image registration, so as to carry out the application of the following steps [12]. Remote sensing image registration technology is the basis of various remote sensing applications and is key to determining the application effect [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Bidirectional Symmetry Network with Dual-Field Cyclic Attention for Multi-Temporal Aerial Remote Sensing Image Registration

Chen

Zhang

et al. 2021

Symmetry

View full text Add to dashboard Cite

Multi-temporal remote sensing image registration is a geometric symmetry process that involves matching a source image with a target image. To improve the accuracy and enhance the robustness of the algorithm, this study proposes an end-to-end registration network—a bidirectional symmetry network based on dual-field cyclic attention for multi-temporal remote sensing image registration, which mainly improves feature extraction and feature matching. (1) We propose a feature extraction framework combining an attention module and a pre-training model, which can accurately locate important areas in images and quickly extract features. Not only is the dual receptive field module designed to enhance attention in the spatial region, a loop structure is also used to improve the network model and improve overall accuracy. (2) Matching has not only directivity but also symmetry. We design a symmetric network of two-way matching to reduce the registration deviation caused by one-way matching and use a Pearson correlation method to improve the cross-correlation matching and enhance the robustness of the matching relation. In contrast with two traditional methods and three deep learning-based algorithms, the proposed approach works well under five indicators in three public multi-temporal datasets. Notably, in the case of the Aerial Image Dataset, the accuracy of the proposed method is improved by 39.8% compared with the Two-stream Ensemble method under a PCK (Percentage of Correct Keypoints) index of 0.05. When the PCK index is 0.03, accuracy increases by 46.8%, and increases by 18.7% under a PCK index of 0.01. Additionally, when adding the innovation points in feature extraction into the basic network CNNGeo (Convolutional Neural Network Architecture for Geometric Matching), accuracy is increased by 36.7% under 0.05 PCK, 18.2% under 0.03 PCK, and 8.4% under 0.01 PCK. Meanwhile, by adding the innovation points in feature matching into CNNGeo, accuracy is improved by 16.4% under 0.05 PCK, 9.1% under 0.03 PCK, and 5.2% under 0.01 PCK. In most cases, this paper reports high registration accuracy and efficiency for multi-temporal remote sensing image registration.

show abstract

“…On the one hand, if all observed star points are directly matched with all predicted star points one by one (the existing matching method that is widely used in traditional area of star trackers), the complexity and the time of the star matching step will be significantly increased, thus resulting in the star matching step becoming the new bottleneck of the MEIA’s attitude update rate. On the other hand, although the mainstream feature points-based image registration methods are quite popular and successful in many applications [ 23 , 24 , 25 ], they are not applicable for the above star matching situation. This is because the above matching methods are mainly used to solve the point matching problem between two real images (i.e., the matching image and the matched image), while the star matching step only contains one real image (i.e., the observed star image) and one dataset of the centroid information of the predicted star points.…”

Section: Introductionmentioning

confidence: 99%

Fast Star Matching Method Based on Double K-Vector Lookup Tables for Multi-Exposure Star Trackers

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

A high update rate is always one of the vital indices of star trackers. By recording star positions at N moments within a single star image, the multi-exposure imaging approach (MEIA) proposed in an earlier study can improve the attitude update rate of star trackers by N times. Unfortunately, when the existing star matching method is adopted to match the observed and predicted stars in MEIA, the matching time is significantly increased with the increase in multi-exposure times, N, or the number of navigation stars, M, which sharply affects the MEIA’s performance. Therefore, a fast star matching method based on double K-vector lookup tables (DKVLUTs) is proposed to address the above issue. In this method, the information of all predicted stars is used to establish the DKVLUT, and thus, the speed of the whole matching process between observed and predicted stars would be increased effectively by means of the DKVLUT. Both simulations and experiments are conducted to verify the performance of the proposed method. The results both show that the matching time of the proposed method is reduced by nearly one order of magnitude compared with that of the existing method, which demonstrates the feasibility and effectiveness of the proposed method.

show abstract

An Infrared-Visible Image Registration Method Based on the Constrained Point Feature

Cited by 8 publications

References 46 publications

Research on Infrared and Visible Image Registration Algorithm for Complex Road Scenes

Research on Infrared and Visible Image Registration Algorithm for Complex Road Scenes

Bidirectional Symmetry Network with Dual-Field Cyclic Attention for Multi-Temporal Aerial Remote Sensing Image Registration

Fast Star Matching Method Based on Double K-Vector Lookup Tables for Multi-Exposure Star Trackers

Contact Info

Product

Resources

About