Semantic Segmentation of Natural Materials on a Point Cloud Using Spatial and Multispectral Features.

The characterization of natural spaces by the precise observation of their material properties is highly demanded in remote sensing and computer vision. The production of novel sensors enables the collection of heterogeneous data to get a comprehensive knowledge of the living and non-living entities in the ecosystem. The high resolution of consumer-grade RGB cameras is frequently used for the geometric reconstruction of many types of environments. Nevertheless, the understanding of natural spaces is still challenging. The automatic segmentation of homogeneous materials in nature is a complex task because there are many overlapping structures and an indirect illumination, so the object recognition is difficult. In this paper, we propose a method based on fusing spatial and multispectral characteristics for the unsupervised classification of natural materials in a point cloud. A high-resolution camera and a multispectral sensor are mounted on a custom camera rig in order to simultaneously capture RGB and multispectral images. Our method is tested in a controlled scenario, where different natural objects coexist. Initially, the input RGB images are processed to generate a point cloud by applying the structure-from-motion (SfM) algorithm. Then, the multispectral images are mapped on the three-dimensional model to characterize the geometry with the reflectance captured from four narrow bands (green, red, red-edge and near-infrared). The reflectance, the visible colour and the spatial component are combined to extract key differences among all existing materials. For this purpose, a hierarchical cluster analysis is applied to pool the point cloud and identify the feature pattern for every material. As a result, the tree trunk, the leaves, different species of low plants, the ground and rocks can be clearly recognized in the scene. These results demonstrate the feasibility to perform a semantic segmentation by considering multispectral and spatial features with an unknown number of clusters to be detected on the point cloud. Moreover, our solution is compared to other method based on supervised learning in order to test the improvement of the proposed approach.

Modeling of the 3D Tree Skeleton Using Real-World Data: A Survey.

Tree modeling has been extensively studied in computer graphics. Recent advances in the development of high-resolution sensors and data processing techniques are extremely useful for collecting 3D datasets of real-world trees and generating increasingly plausible branching structures. The wide availability of versatile acquisition platforms allows us to capture multi-view images and scanned data that can be used for guided 3D tree modeling. In this paper, we carry out a comprehensive review of the state-of-the-art methods for the 3D modeling of botanical tree geometry by taking input data from real scenarios. A wide range of studies has been proposed following different approaches. The most relevant contributions are summarized and classified into three categories: (1) procedural reconstruction, (2) geometry-based extraction, and (3) image-based modeling. In addition, we describe other approaches focused on the reconstruction process by adding additional features to achieve a realistic appearance of the tree models. Thus, we provide an overview of the most effective procedures to assist researchers in the photorealistic modeling of trees in geometry and appearance. The article concludes with remarks and trends for promising research opportunities in 3D tree modeling using real-world data.

Local geometric deformations in the DHT domain with applications.

Local rotation, translation and scaling of the image domain represent a basic toolkit in adaptive image processing such as image registration, template matching, local invariant feature detection, super-resolution imaging, among others. In this article, it is shown how the local rotation, scaling and translations can be performed in the discrete Hermite transform (DHT) domain. As the DHT satisfies the generalized steerability property, basic geometric operations are expressed as linear mappings in the DHT domain and hence can facilitate the solution of many image processing problems. The local rotation and scaling were previously shown in the continuous domain using the Hermite Transform, the former is used here as a good approximation for discrete images, whereas the latter is extended to a discrete domain. In addition, the local translation operation is fully developed in the discrete domain. The application of these three operations is illustrated with three exemplar applications including 1) mathematical morphology, 2) template matching and 3) depth from defocus. The simple yet effective methods presented in the paper indicate that local image decompositions satisfying the steerability property, such as the DHT, are desirable for solving a number of interesting image processing problems.

The multiscale hermite transform for local orientation analysis.

The efficient representation of local differential structure at various resolutions has been a matter of great interest for adaptive image processing and computer vision tasks. In this paper, we derive a multiscale model to represent natural images based on the scale-space representation: a model that has an inspiration in the human visual system. We first derive the one-dimensional case and then extend the results to two and three dimensions. The operators obtained for analysis and synthesis stages are derivatives of the Gaussian smoothing kernel, so that, for the two-dimensional case, we can represent them either in a rotated coordinate system or in terms of directional derivatives. The method to perform the rotation is efficient because it is implemented by means of the application of the so-called generalized binomial filters. Such a family of discrete sequences fulfills a number of properties that allows estimating the local orientation for several image structures. We also define the discrete counterpart in which the coordinate normalization of the continuous case is approximated as a subsampling of the discrete domain.

Neuropad for the detection of cardiovascular autonomic neuropathy in patients with type 2 diabetes.

BACKGROUND: Cardiovascular autonomic neuropathy (CAN) is a prevalent and neglected chronic complication of diabetes, with a large impact on morbidity and mortality. Part of the reason why it is not detected and treated opportunely is because of the complexity of the tests required for its diagnosis. We evaluated the Neuropad®, a test based on sudomotor function, as a screening tool for CAN in adult patients with type 2 diabetes in Bogotá, Colombia. METHODS: This was a cross-sectional evaluation of Neuropad® for the detection of CAN. Patients were 20-75years of age and did not suffer from any other type of neuropathy. CAN was diagnosed using the Ewing battery of tests for R-R variability during deep breathing, Valsalva and lying-to-standing maneuvers. Additionally, distal symmetric polyneuropathy (DSP) was diagnosed using a sign-based scale (Michigan Neuropathy Disability Score - NDS) and a symptom-based score (Total Symptom Score - TSS). The primary outcome was the sensitivity and specificity of the Neuropad® for the diagnosis of CAN, and secondary outcomes were the sensitivity and specificity of Neuropad® for DSP. RESULTS: We studied 154 patients (74 men and 80 women). Prevalence of CAN was extremely high (68.0% of study participants), but also DSP was prevalent, particularly according to the signs-based definition (45%). The sensitivity of the Neuropad® for any degree of CAN was 70.1%, being slightly higher for the deep breathing and Valsalva tests than for lying-to-standing. The specificity of the Neuropad® for any type of CAN was only 37.0%, as expected for a screening exam. The negative predictive value was higher for the deep breathing and Valsalva tests (69.4 and 81.6%, respectively). Neuropad showed also a good sensitivity and negative predictive value for DSP. The sensitivity and specificity of Neuropad were better among men, and among patients with diabetes duration above the group median. CONCLUSIONS: The Neuropad is a simple and inexpensive device that demonstrated an adequate performance as a screening tool for cardiovascular autonomic neuropathy in Latin American patients with DM2.