Spectral Pattern Classification in Lidar Data for Rock Identification in Outcrops

Abstract

The present study aimed to develop and implement a method for detection and classification of spectral signatures in point clouds obtained from terrestrial laser scanner in order to identify the presence of different rocks in outcrops and to generate a digital outcrop model. To achieve this objective, a software based on cluster analysis was created, named K-Clouds. This software was developed through a partnership between UNISINOS and the company V3D. This tool was designed to begin with an analysis and interpretation of a histogram from a point cloud of the outcrop and subsequently indication of a number of classes provided by the user, to process the intensity return values. This classified information can then be interpreted by geologists, to provide a better understanding and identification from the existing rocks in the outcrop. Beyond the detection of different rocks, this work was able to detect small changes in the physical-chemical characteristics of the rocks, as they were caused by weathering or compositional changes.

Relationship of Oil Palm Crown Features Extracted Using Terrestrial Laser Scanning for Basal Stem Rot Disease Classification

“…Terrestrial Laser Scanning (TLS), also known as ground-based LiDAR (Light Detection and Ranging) is an active imaging method which is contact-free, precise, cost-effective and user-friendly contributed to its expanding use. These 3D profiling systems have some features that can provide accurate information about tree dimensions and morphology, which relates to plant development and health, such as high degree of accuracy and precision, up to mm (Campos et al, 2014). Recent studies have shown the use of TLS to monitor the plant growth and physiology of plant canopy is promising (Lumme et al, 2008;Keightley & Bawden, 2010;Tilly et al, 2014;Hoffmeister et al, 2016).…”

An approach for automated lithological classification of point clouds

“…Fowler et al (2011) used intensity values to interpret rock face weathering and to distinguish a coal layer from surrounding (more reflective) rocks. Inocencio et al (2014) used a k-means algorithm to segregate points into distinct interpreted lithologies based on intensity values.…”

An intensity recovery algorithm (IRA) for minimizing the edge effect of LIDAR data

“…In each field, methodological approaches have been developed to cope with specific features and problems [Pirotti et al, 2013]. There are many studies about methodologies based on geometric coordinates data of TLS but few studies have provided methodological and operational approaches to use TLS intensity data [Eitel et al, 2010;Burton et al, 2011;Inocencio et al, 2014;Pavi et al, 2015]. The aim of this research is to recover laser intensity data distorted by the so called 'edge effect' [Eitel et al, 2010], in the case data acquisition was operated using TLS.…”

“…Although the problem of the edge effect has been already reported in the literature, no one provided satisfactory solutions to eliminate or minimize its consequences on laser intensity data. As intensity data are related to physical and chemical characteristics of the target object [Inocencio et al, 2014], the reduction of the edge effect is beneficial for research that intends to infer, correlate or interpret these data. The research described here contributes to understand of the edge effect and to provide an algorithm that automatically mitigates its consequences.…”