The fusion of image data from multiple sensors is crucial for many applications. However, there are significant nonlinear intensity deformations between images from different kinds of sensors, leading to matching failure. To address this need, this paper proposes an effective coarse-to-fine matching method for multimodal remote sensing images (3MRS). In the coarse matching stage, feature points are first detected on a maximum moment map calculated with a phase congruency model. Then, feature description is conducted using an index map constructed by finding the index of the maximum value in all orientations of convolved images obtained using a set of log-Gabor filters. At last, several matches are built through image matching and outlier removal, which can be used to estimate a reliable affine transformation model between the images. In the stage of fine matching, we develop a novel template matching method based on the log-Gabor convolution image sequence and match the template features with a 3D phase correlation matching strategy, given that the initial correspondences are achieved with the estimated transformation. Results show that compared with SIFT, and three state-of-the-art methods designed for multimodal image matching, PSO-SIFT, HAPCG, and RIFT, only 3MRS successfully matched all six types of multimodal remote sensing image pairs: optical–optical, optical–infrared, optical–depth, optical–map, optical–SAR, and day–night, with each including ten different image pairs. On average, the number of correct matches (NCM) of 3MRS was 164.47, 123.91, 4.88, and 4.33 times that of SIFT, PSO-SIFT, HAPCG, and RIFT for the successfully matched image pairs of each method. In terms of accuracy, the root-mean-square error of correct matches for 3MRS, SIFT, PSO-SIFT, HAPCG, and RIFT are 1.47, 1.98, 1.79, 2.83, and 2.45 pixels, respectively, revealing that 3MRS got the highest accuracy. Even though the total running time of 3MRS was the longest, the efficiency for obtaining one correct match is the highest considering the most significant number of matches. The source code of 3MRS and the experimental datasets and detailed results are publicly available.

Accurate geopositioning of optical satellite imagery is a fundamental step for many photogrammetric applications. Considering the imaging principle and data processing manner, SAR satellites can achieve high geopositioning accuracy. Therefore, SAR data can be a reliable source for providing control information in the orientation of optical satellite images. This paper proposes a practical solution for an accurate orientation of optical satellite images using SAR reference images to take advantage of the merits of SAR data. Firstly, we propose an accurate and robust multimodal image matching method to match the SAR and optical satellite images. This approach includes the development of a new structural-based multimodal applicable feature descriptor that employs angle-weighted oriented gradients (AWOGs) and the utilization of a three-dimensional phase correlation similarity measure. Secondly, we put forward a general optical satellite imagery orientation framework based on multiple SAR reference images, which uses the matches of the SAR and optical satellite images as virtual control points. A large number of experiments not only demonstrate the superiority of the proposed matching method compared to the state-of-the-art methods but also prove the effectiveness of the proposed orientation framework. In particular, the matching performance is improved by about 17% compared with the latest multimodal image matching method, namely, CFOG, and the geopositioning accuracy of optical satellite images is improved, from more than 200 to around 8 m.

Strong geometric and radiometric distortions often exist in optical wide-baseline stereo images, and some local regions can include surface discontinuities and occlusions. Digital photogrammetry and computer vision researchers have focused on automatic matching for such images. Deep convolutional neural networks, which can express high-level features and their correlation, have received increasing attention for the task of wide-baseline image matching, and learning-based methods have the potential to surpass methods based on handcrafted features. Therefore, we focus on the dynamic study of wide-baseline image matching and review the main approaches of learning-based feature detection, description, and end-to-end image matching. Moreover, we summarize the current representative research using stepwise inspection and dissection. We present the results of comprehensive experiments on actual wide-baseline stereo images, which we use to contrast and discuss the advantages and disadvantages of several state-of-the-art deep-learning algorithms. Finally, we conclude with a description of the state-of-the-art methods and forecast developing trends with unresolved challenges, providing a guide for future work.

Aerial images are widely used for building detection. However, the performance of building detection methods based on aerial images alone is typically poorer than that of building detection methods using both LiDAR and image data. To overcome these limitations, we present a framework for detecting and regularizing the boundary of individual buildings using a feature-level-fusion strategy based on features from dense image matching (DIM) point clouds, orthophoto and original aerial images. The proposed framework is divided into three stages. In the first stage, the features from the original aerial image and DIM points are fused to detect buildings and obtain the so-called blob of an individual building. Then, a feature-level fusion strategy is applied to match the straight-line segments from original aerial images so that the matched straight-line segment can be used in the later stage. Finally, a new footprint generation algorithm is proposed to generate the building footprint by combining the matched straight-line segments and the boundary of the blob of the individual building. The performance of our framework is evaluated on a vertical aerial image dataset (Vaihingen) and two oblique aerial image datasets (Potsdam and Lunen). The experimental results reveal 89% to 96% per-area completeness with accuracy above almost 93%. Relative to six existing methods, our proposed method not only is more robust but also can obtain a similar performance to the methods based on LiDAR and images.

The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters.

The automatic 3D reconstruction of indoor scenes is of great significance in the application of 3D-scene understanding. The existing methods have poor resilience to the incomplete and noisy point cloud, which leads to low-quality results and tedious post-processing. Therefore, the objective of this work is to automatically reconstruct indoor scenes from an incomplete and noisy point-cloud base on semantics and primitives. In this paper, we propose a semantics-and-primitives-guided indoor 3D reconstruction method. Firstly, a local, fully connected graph neural network is designed for semantic segmentation. Secondly, based on the enumerable features of indoor scenes, a primitive-based reconstruction method is proposed, which retrieves the most similar model in a 3D-ESF indoor model library by using ESF descriptors and semantic labels. Finally, a coarse-to-fine registration method is proposed to register the model into the scene. The results indicate that our method can achieve high-quality results while remaining better resilience to the incompleteness and noise of point cloud. It is concluded that the proposed method is practical and is able to automatically reconstruct the indoor scene from the point cloud with incompleteness and noise.