Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

On robust estimation of the location parameter

A random forest (RF) classifier is an ensemble classifier that produces multiple decision trees, using a randomly selected subset of training samples and variables. This classifier has become popular within the remote sensing community due to the accuracy of its classifications. The overall objective of this work was to review the utilization of RF classifier in remote sensing. This review has revealed that RF classifier can successfully handle high data dimensionality and multicolinearity, being both fast and insensitive to overfitting. It is, however, sensitive to the sampling design. The variable importance (VI) measurement provided by the RF classifier has been extensively exploited in different scenarios, for example to reduce the number of dimensions of hyperspectral data, to identify the most relevant multisource remote sensing and geographic data, and to select the most suitable season to classify particular target classes. Further investigations are required into less commonly exploited uses of this classifier, such as for sample proximity analysis to detect and remove outliers in the training samples.

Random forest in remote sensing: A review of applications and future directions

Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning.

In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

An assessment of the effectiveness of a random forest classifier for land-cover classification

Airborne laser scanning (ALS) is an active remote sensing technique providing range data as 3D point clouds. This paper aims at presenting a survey of the literature related to such techniques, with emphasis on the new sensors called full-waveform lidar systems. Indeed, an emitted laser pulse interacts with complex natural and man-made objects leading to a temporal distortion of the returned energy profile. The new technology of full-waveform laser scanning systems permits one to digitize the complete waveform of each backscattered pulse. Full-waveform lidar data give more control to an end user in the interpretation process of the physical measurement and provide additional information about the structure and the physical backscattering characteristics of the illuminated surfaces. In this paper, the theoretical principles of full-waveform airborne laser scanning are first described. Afterwards, a review of the main sensors as well as signal processing techniques are presented. We then discuss the interpretation of full-waveform measures with special interest on vegetated and urban areas.

Full-waveform topographic lidar : State-of-the-art

3D scene analysis in terms of automatically assigning 3D points a respective semantic label has become a topic of great importance in photogrammetry, remote sensing, computer vision and robotics. In this paper, we address the issue of how to increase the distinctiveness of geometric features and select the most relevant ones among these for 3D scene analysis. We present a new, fully automated and versatile framework composed of four components: (i) neighborhood selection, (ii) feature extraction, (iii) feature selection and (iv) classification. For each component, we consider a variety of approaches which allow applicability in terms of simplicity, efficiency and reproducibility, so that end-users can easily apply the different components and do not require expert knowledge in the respective domains. In a detailed evaluation involving 7 neighborhood definitions, 21 geometric features, 7 approaches for feature selection, 10 classifiers and 2 benchmark datasets, we demonstrate that the selection of optimal neighborhoods for individual 3D points significantly improves the results of 3D scene analysis. Additionally, we show that the selection of adequate feature subsets may even further increase the quality of the derived results while significantly reducing both processing time and memory consumption.

Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers

Airborne lidar systems have become a source for the acquisition of elevation data. They provide georeferenced, irregularly distributed 3D point clouds of high altimetric accuracy. Moreover, these systems can provide for a single laser pulse, multiple returns or echoes, which correspond to different illuminated objects. In addition to multi-echo laser scanners, full-waveform systems are able to record 1D signals representing a train of echoes caused by reflections at different targets. These systems provide more information about the structure and the physical characteristics of the targets. Many approaches have been developed, for urban mapping, based on aerial lidar solely or combined with multispectral image data. However, they have not assessed the importance of input features. In this paper, we focus on a multi-source framework using aerial lidar (multi-echo and full waveform) and aerial multispectral image data. We aim to study the feature relevance for dense urban scenes. The Random Forests algorithm is chosen as a classifier: it runs efficiently on large datasets, and provides measures of feature importance for each class. The margin theory is used as a confidence measure of the classifier, and to confirm the relevance of input features for urban classification. The quantitative results confirm the importance of the joint use of optical multispectral and lidar data. Moreover, the relevance of full-waveform lidar features is demonstrated for building and vegetation area discrimination.

http://recherche.ign.fr/labos/matis/pdf/articles_revues/chehata_etal_IJPRS10.pdf

Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests

We present a novel and robust method for modeling cities from 3D-point data. Our algorithm provides a more complete description than existing approaches by reconstructing simultaneously buildings, trees and topologically complex grounds. A major contribution of our work is the original way of modeling buildings which guarantees a high generalization level while having semantized and compact representations. Geometric 3D-primitives such as planes, cylinders, spheres or cones describe regular roof sections, and are combined with mesh-patches that represent irregular roof components. The various urban components interact through a non-convex energy minimization problem in which they are propagated under arrangement constraints over a planimetric map. Our approach is experimentally validated on complex buildings and large urban scenes of millions of points, and is compared to state-of-the-art methods.

/pdf/creating-large-scale-city-models-from-3d-point-clouds-a-4vdk5mcc00.pdf

Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation

Various multi-echo and Full-waveform (FW) lidar features can be processed. In this paper, multiple classifers are applied to lidar feature selection for urban scene classification. Random forests are used since they provide an accurate classification and run efficiently on large datasets. Moreover, they return measures of variable importance for each class. The feature selection is obtained by backward elimination of features depending on their importance. This is crucial to analyze the relevance of each lidar feature for the classification of urban scenes. The Random Forests classification using selected variables provide an overall accuracy of 94.35%.

/pdf/airborne-lidar-feature-selection-for-urban-classification-4k06nvjjfv.pdf

Clément Mallet

Papers

Full-waveform topographic lidar : State-of-the-art

Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers

Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests

Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation

Airborne lidar feature selection for urban classification using random forests