Standard convolution is inherently limited for semantic segmentation of point cloud due to its isotropy about features. It neglects the structure of an object, results in poor object delineation and small spurious regions in the segmentation result. This paper proposes a novel graph attention convolution (GAC), whose kernels can be dynamically carved into specific shapes to adapt to the structure of an object. Specifically, by assigning proper attentional weights to different neighboring points, GAC is designed to selectively focus on the most relevant part of them according to their dynamically learned features. The shape of the convolution kernel is then determined by the learned distribution of the attentional weights. Though simple, GAC can capture the structured features of point clouds for fine-grained segmentation and avoid feature contamination between objects. Theoretically, we provided a thorough analysis on the expressive capabilities of GAC to show how it can learn about the features of point clouds. Empirically, we evaluated the proposed GAC on challenging indoor and outdoor datasets and achieved the state-of-the-art results in both scenarios.

Automatic registration of multimodal remote sensing data [e.g., optical, light detection and ranging (LiDAR), and synthetic aperture radar (SAR)] is a challenging task due to the significant nonlinear radiometric differences between these data. To address this problem, this paper proposes a novel feature descriptor named the histogram of orientated phase congruency (HOPC), which is based on the structural properties of images. Furthermore, a similarity metric named HOPCncc is defined, which uses the normalized correlation coefficient (NCC) of the HOPC descriptors for multimodal registration. In the definition of the proposed similarity metric, we first extend the phase congruency model to generate its orientation representation and use the extended model to build HOPCncc. Then, a fast template matching scheme for this metric is designed to detect the control points between images. The proposed HOPCncc aims to capture the structural similarity between images and has been tested with a variety of optical, LiDAR, SAR, and map data. The results show that HOPCncc is robust against complex nonlinear radiometric differences and outperforms the state-of-the-art similarities metrics (i.e., NCC and mutual information) in matching performance. Moreover, a robust registration method is also proposed in this paper based on HOPCncc, which is evaluated using six pairs of multimodal remote sensing images. The experimental results demonstrate the effectiveness of the proposed method for multimodal image registration.

While image matching has been studied in remote sensing community for decades, matching multimodal data [e.g., optical, light detection and ranging (LiDAR), synthetic aperture radar (SAR), and map] remains a challenging problem because of significant nonlinear intensity differences between such data. To address this problem, we present a novel fast and robust template matching framework integrating local descriptors for multimodal images. First, a local descriptor [such as histogram of oriented gradient (HOG) and local self-similarity (LSS) or speeded-up robust feature (SURF)] is extracted at each pixel to form a pixelwise feature representation of an image. Then, we define a fast similarity measure based on the feature representation using the fast Fourier transform (FFT) in the frequency domain. A template matching strategy is employed to detect correspondences between images. In this procedure, we also propose a novel pixelwise feature representation using orientated gradients of images, which is named channel features of orientated gradients (CFOG). This novel feature is an extension of the pixelwise HOG descriptor with superior performance in image matching and computational efficiency. The major advantages of the proposed matching framework include: 1) structural similarity representation using the pixelwise feature description and 2) high computational efficiency due to the use of FFT. The proposed matching framework has been evaluated using many different types of multimodal images, and the results demonstrate its superior matching performance with respect to the state-of-the-art methods.

This paper presents a solution framework for the segmentation and reconstruction of polyhedral building roofs from aerial LIght Detection And Ranging (lidar) point clouds. The eigenanalysis is first carried out for each roof point of a building within its Voronoi neighborhood. Such analysis not only yields the surface normal for each lidar point but also separates the lidar points into planar and nonplanar ones. In the second step, the surface normals of all planar points are clustered with the fuzzy k-means method. To optimize this clustering process, a potential-based approach is used to estimate the number of clusters, while considering both geometry and topology for the cluster similarity. The final step of segmentation separates the parallel and coplanar segments based on their distances and connectivity, respectively. Building reconstruction starts with forming an adjacency matrix that represents the connectivity of the segmented planar segments. A roof interior vertex is determined by intersecting all planar segments that meet at one point, whereas constraints in the form of vertical walls or boundary are applied to determine the vertices on the building outline. Finally, an extended boundary regularization approach is developed based on multiple parallel and perpendicular line pairs to achieve topologically consistent and geometrically correct building models. This paper describes the detail principles and implementation steps for the aforementioned solution framework. Results of a number of buildings with diverse roof complexities are presented and evaluated.