An Optical Remote Sensing Image Matching Method Based on the Simple and Stable Feature Database

Abstract

Satellite remote sensing has entered the era of big data due to the increase in the number of remote sensing satellites and imaging modes. This presents significant challenges for the processing of remote sensing systems and will result in extremely high real-time data processing requirements. The effective and reliable geometric positioning of remote sensing images is the foundation of remote sensing applications. In this paper, we propose an optical remote sensing image matching method based on a simple stable feature database. This method entails building the stable feature database, extracting local invariant features that are comparatively stable from remote sensing images using an iterative matching strategy, and storing useful information about the features. Without reference images, the feature database-based matching approach potentially saves storage space for reference data while increasing image processing speed. To evaluate the performance of the feature database matching method, we train the feature database with various local invariant feature algorithms on different time phases of Gaofen-2 (GF-2) images. Furthermore, we carried out matching comparison experiments with various satellite images to confirm the viability and stability of the feature database-based matching method. In comparison with direct matching using the classical feature algorithm, the feature database-based matching method in this paper can essentially improve the correct rate of feature point matching by more than 30% and reduce the matching time by more than 40%. This method improves the accuracy and timeliness of image matching, potentially solves the problem of large storage space occupied by the reference data, and has great potential for fast matching of optical remote sensing images.

MSRSI-TPMF: A Tie Points Matching Framework of Multisource Remote Sensing Images

“…For example, cross-modal feature description matching network (CM-Net) [30], multiscale framework with unsupervised learning (MU-Net) [31] and so on. [32] 2022 256×256 satellite-aerial image pairs literature [33] 2022 256×256 GF3 FSII literature [34] 2022 1240×1400 AHB dataset literature [35] 2022 600×600 Multimodal Remote Sensing literature [36] 2022 13056×11008 Google Earth literature [37] 2022 800×800 UAV, PAN, SAR, CIAP literature [31] 2022 512×512 Multimodal Remote Sensing literature [38] 2023 750×750 Multimodal Remote Sensing literature [39] 2023 27620×29200 Jilin-1, Gaofen-1, Gaofen-2 literature [40] 2023 855×831 Multimodal Remote Sensing…”

Lightweight and Stable Multi-Feature Databases for Efficient Geometric Localization of Remote Sensing Images

“…This section details the construction of the stable feature database to improve database stability and reduce descriptor redundancy. Initially, the iterative matching filtering strategy is used to determine the accurate geographic locations of stable feature classes [42]. Later, stable feature descriptors are re-extracted from each image in the training set, with each feature point storing descriptors for multiple imaging conditions.…”

“…The feature set F k is modified under the condition of valid matches, adjusted based on the matching results with T k and two predefined thresholds thre1 and thre2, and then stored in the feature database. Refer to Algorithm 1 for specific algorithmic details, more detailed training steps and parameter settings can be found in reference [42].…”

“…We made a simple modification to enhance the likelihood of multiple descriptors within feature classes, and we maintain the CU M of unmatched feature points within successfully matched feature classes unchanged, so it no longer increases compared to the original method [42]. Furthermore, to ensure the accuracy of features within feature classes, during the training-matching process, we ensure that one feature class can only match one feature point in the training image.…”

“…There are various methods for extracting local invariant features, and how to store features with strong robustness and strong reproducibility in the feature database is a difficult problem to solve. We previously proposed a fast matching method based on simple and stable feature databases [42]. The method combines a training-feedback mechanism for iterative matching of feature databases to construct stable feature classes.…”