ORCID Profile
0000-0003-3846-5172
Current Organisation
University of Luxembourg
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Informa UK Limited
Date: 21-09-2010
Publisher: IEEE
Date: 12-2013
Publisher: Informa UK Limited
Date: 10-08-2015
Publisher: IEEE
Date: 12-2009
Publisher: CRC Press
Date: 18-10-2019
Publisher: IGI Global
Date: 2011
DOI: 10.4018/978-1-60960-551-3.CH020
Abstract: Regression analysis is one of the most important branches of multivariate statistical techniques. It is widely used in almost every field of research and application in multifactor data, which helps to investigate and to fit an unknown model for quantifying relations among observed variables. Nowadays, it has drawn a large attention to perform the tasks with neural networks, support vector machines, evolutionary algorithms, et cetera. Till today, least squares (LS) is the most popular parameter estimation technique to the practitioners, mainly because of its computational simplicity and underlying optimal properties. It is well-known by now that the method of least squares is a non-resistant fitting process even a single outlier can spoil the whole estimation procedure. Data contamination by outlier is a practical problem which certainly cannot be avoided. It is very important to be able to detect these outliers. The authors are concerned about the effect outliers have on parameter estimates and on inferences about models and their suitability. In this chapter the authors have made a short discussion of the most well known and efficient outlier detection techniques with numerical demonstrations in linear regression. The chapter will help the people who are interested in exploring and investigating an effective mathematical model. The goal is to make the monograph self-contained maintaining its general accessibility.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2016
Publisher: Springer US
Date: 2012
Publisher: IEEE
Date: 03-2014
Publisher: IEEE
Date: 03-2009
Publisher: Copernicus GmbH
Date: 25-02-2022
DOI: 10.5194/ISPRS-ARCHIVES-XLVI-2-W1-2022-401-2022
Abstract: Abstract. Most deep learning (DL) methods that are not end-to-end use several multi-scale and multi-type hand-crafted features that make the network challenging, more computationally intensive and vulnerable to overfitting. Furthermore, reliance on empirically-based feature dimensionality reduction may lead to misclassification. In contrast, efficient feature management can reduce storage and computational complexities, builds better classifiers, and improves overall performance. Principal Component Analysis (PCA) is a well-known dimension reduction technique that has been used for feature extraction. This paper presents a two-step PCA based feature extraction algorithm that employs a variant of feature-based PointNet (Qi et al., 2017a) for point cloud classification. This paper extends the PointNet framework for use on large-scale aerial LiDAR data, and contributes by (i) developing a new feature extraction algorithm, (ii) exploring the impact of dimensionality reduction in feature extraction, and (iii) introducing a non-end-to-end PointNet variant for per point classification in point clouds. This is demonstrated on aerial laser scanning (ALS) point clouds. The algorithm successfully reduces the dimension of the feature space without sacrificing performance, as benchmarked against the original PointNet algorithm. When tested on the well-known Vaihingen data set, the proposed algorithm achieves an Overall Accuracy (OA) of 74.64% by using 9 input vectors and 14 shape features, whereas with the same 9 input vectors and only 5PCs (principal components built by the 14 shape features) it actually achieves a higher OA of 75.36% which demonstrates the effect of efficient dimensionality reduction.
Publisher: Copernicus GmbH
Date: 30-05-2022
DOI: 10.5194/ISPRS-ARCHIVES-XLIII-B1-2022-59-2022
Abstract: Abstract. Road surface extraction is crucial for 3D city analysis. Mobile laser scanning (MLS) is the most appropriate data acquisition system for the road environment because of its efficient vehicle-based on-road scanning opportunity. Many methods are available for road pavement, curb and roadside way extraction. Most of them use classical approaches that do not mitigate problems caused by the presence of noise and outliers. In practice, however, laser scanning point clouds are not free from noise and outliers, and it is apparent that the presence of a very small portion of outliers and noise can produce unreliable and non-robust results. A road surface usually consists of three key parts: road pavement, curb and roadside way. This paper investigates the problem of road surface extraction in the presence of noise and outliers, and proposes a robust algorithm for road pavement, curb, road ider/islands, and roadside way extraction using MLS point clouds. The proposed algorithm employs robust statistical approaches to remove the consequences of the presence of noise and outliers. It consists of five sequential steps for road ground and non-ground surface separation, and road related components determination. Demonstration on two different MLS data sets shows that the new algorithm is efficient for road surface extraction and for classifying road pavement, curb, road ider/island and roadside way. The success can be rated in one experiment in this paper, where we extract curb points the results achieve 97.28%, 100% and 0.986 of precision, recall and Matthews correlation coefficient, respectively.
Publisher: Informa UK Limited
Date: 08-03-2011
Publisher: Copernicus GmbH
Date: 27-10-2022
DOI: 10.5194/ISPRS-ARCHIVES-XLVIII-3-W2-2022-43-2022
Abstract: Abstract. The building footprint is crucial for a volumetric 3D representation of a building that is applied in urban planning, 3D city modeling, cadastral and topographic map generation. Aerial laser scanning (ALS) has been recognized as the most suitable means of large-scale 3D point cloud data (PCD) acquisition. PCD can produce geometric detail of a scanned surface. However, it is almost impossible to get point clouds without noise and outliers. Besides, data incompleteness and occlusions are two common phenomena for PCD. Most of the existing methods for building footprint extraction employ classification, segmentation, voting techniques (e.g., Hough-Transform or RANSAC), or Principal Component Analysis (PCA) based methods. It is known that classical PCA is highly sensitive to outliers, even RANSAC which is known as a robust technique for shape detection is not free from outlier effects. This paper presents a novel algorithm that employs MCMD (maximum consistency within minimum distance), MSAC (a robust variant of RANSAC) and a robust regression to extract reliable building footprints in the presence of outliers, missing points and irregular data distributions. The algorithm is successfully demonstrated through two sets of ALS PCD.
Publisher: Elsevier BV
Date: 04-2015
Publisher: Copernicus GmbH
Date: 30-05-2022
DOI: 10.5194/ISPRS-ARCHIVES-XLIII-B2-2022-617-2022
Abstract: Abstract. A validation data set plays a pivotal role in tweaking a machine learning model trained in a supervised manner. Many existing algorithms select a part of available data by using random s ling to produce a validation set. However, this approach can be prone to overfitting. One should follow careful data splitting to have reliable training and validation sets that can produce a generalized model with a good performance for the unseen (test) data. Data splitting based on res ling techniques involves repeatedly drawing s les from the available data. Hence, res ling methods can give better generalization power to a model, because they can produce and use many training and/or validation sets. These techniques are computationally expensive, but with increasingly available high-performance computing facilities, one can exploit them. Though a multitude of res ling methods exist, investigation of their influence on the generality of deep learning (DL) algorithms is limited due to its non-linear black-box nature. This paper contributes by: (1) investigating the generalization capability of the four most popular res ling methods: k-fold cross-validation (k-CV), repeated k-CV (Rk-CV), Monte Carlo CV (MC-CV) and bootstrap for creating training and validation data sets used for developing, training and validating DL based point cloud classifiers (e.g., PointNet Qi et al., 2017a), (2) justifying Mean Square Error (MSE) as a statistically consistent estimator, and (3) exploring the use of MSE as a reliable performance metric for supervised DL. Experiments in this paper are performed on both synthetic and real-world aerial laser scanning (ALS) point clouds.
Publisher: IEEE
Date: 04-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Copernicus GmbH
Date: 28-06-2021
DOI: 10.5194/ISPRS-ARCHIVES-XLIII-B1-2021-31-2021
Abstract: Abstract. Ground surface extraction is one of the classic tasks in airborne laser scanning (ALS) point cloud processing that is used for three-dimensional (3D) city modelling, infrastructure health monitoring, and disaster management. Many methods have been developed over the last three decades. Recently, Deep Learning (DL) has become the most dominant technique for 3D point cloud classification. DL methods used for classification can be categorized into end-to-end and non end-to-end approaches. One of the main challenges of using supervised DL approaches is getting a sufficient amount of training data. The main advantage of using a supervised non end-to-end approach is that it requires less training data. This paper introduces a novel local feature-based non end-to-end DL algorithm that generates a binary classifier for ground point filtering. It studies feature relevance, and investigates three models that are different combinations of features. This method is free from the limitations of point clouds’ irregular data structure and varying data density, which is the biggest challenge for using the elegant convolutional neural network. The new algorithm does not require transforming data into regular 3D voxel grids or any rasterization. The performance of the new method has been demonstrated through two ALS datasets covering urban environments. The method successfully labels ground and non-ground points in the presence of steep slopes and height discontinuity in the terrain. Experiments in this paper show that the algorithm achieves around 97% in both F1-score and model accuracy for ground point labelling.
Publisher: Elsevier BV
Date: 05-2019
Publisher: Copernicus GmbH
Date: 23-12-2021
DOI: 10.5194/ISPRS-ARCHIVES-XLVI-4-W5-2021-397-2021
Abstract: Abstract. Semantic segmentation of point clouds is indispensable for 3D scene understanding. Point clouds have credibility for capturing geometry of objects including shape, size, and orientation. Deep learning (DL) has been recognized as the most successful approach for image semantic segmentation. Applied to point clouds, performance of the many DL algorithms degrades, because point clouds are often sparse and have irregular data format. As a result, point clouds are regularly first transformed into voxel grids or image collections. PointNet was the first promising algorithm that feeds point clouds directly into the DL architecture. Although PointNet achieved remarkable performance on indoor point clouds, its performance has not been extensively studied in large-scale outdoor point clouds. So far, we know, no study on large-scale aerial point clouds investigates the sensitivity of the hyper-parameters used in the PointNet. This paper evaluates PointNet’s performance for semantic segmentation through three large-scale Airborne Laser Scanning (ALS) point clouds of urban environments. Reported results show that PointNet has potential in large-scale outdoor scene semantic segmentation. A remarkable limitation of PointNet is that it does not consider local structure induced by the metric space made by its local neighbors. Experiments exhibit PointNet is expressively sensitive to the hyper-parameters like batch-size, block partition and the number of points in a block. For an ALS dataset, we get significant difference between overall accuracies of 67.5% and 72.8%, for the block sizes of 5m × 5m and 10m × 10m, respectively. Results also discover that the performance of PointNet depends on the selection of input vectors.
Publisher: Copernicus GmbH
Date: 16-10-2013
DOI: 10.5194/ISPRSANNALS-II-5-W2-217-2013
Abstract: Abstract. A new robust way for ground surface extraction from mobile laser scanning 3D point cloud data is proposed in this paper. Fitting polynomials along 2D/3D points is one of the well-known methods for filtering ground points, but it is evident that unorganized point clouds consist of multiple complex structures by nature so it is not suitable for fitting a parametric global model. The aim of this research is to develop and implement an algorithm to classify ground and non-ground points based on statistically robust locally weighted regression which fits a regression surface (line in 2D) by fitting without any predefined global functional relation among the variables of interest. Afterwards, the z (elevation)-values are robustly down weighted based on the residuals for the fitted points. The new set of down weighted z-values along with x (or y) values are used to get a new fit of the (lower) surface (line). The process of fitting and down-weighting continues until the difference between two consecutive fits is insignificant. Then the final fit represents the ground level of the given point cloud and the ground surface points can be extracted. The performance of the new method has been demonstrated through vehicle based mobile laser scanning 3D point cloud data from urban areas which include different problematic objects such as short walls, large buildings, electric poles, sign posts and cars. The method has potential in areas like building/construction footprint determination, 3D city modelling, corridor mapping and asset management.
Publisher: Copernicus GmbH
Date: 02-12-2022
DOI: 10.5194/ISPRS-ARCHIVES-XLVIII-4-W3-2022-111-2022
Abstract: Abstract. This study investigates the inability of two popular data splitting techniques: train/test split and k-fold cross-validation that are to create training and validation data sets, and to achieve sufficient generality for supervised deep learning (DL) methods. This failure is mainly caused by their limited ability of new data creation. In response, the bootstrap is a computer based statistical res ling method that has been used efficiently for estimating the distribution of a s le estimator and to assess a model without having knowledge about the population. This paper couples cross-validation and bootstrap to have their respective advantages in view of data generation strategy and to achieve better generalization of a DL model. This paper contributes by: (i) developing an algorithm for better selection of training and validation data sets, (ii) exploring the potential of bootstrap for drawing statistical inference on the necessary performance metrics (e.g., mean square error), and (iii) introducing a method that can assess and improve the efficiency of a DL model. The proposed method is applied for semantic segmentation and is demonstrated via a DL based classification algorithm, PointNet, through aerial laser scanning point cloud data.
Publisher: Copernicus GmbH
Date: 30-05-2017
DOI: 10.5194/ISPRS-ARCHIVES-XLII-1-W1-63-2017
Abstract: Abstract. This paper investigates the problems of cylinder fitting in laser scanning three-dimensional Point Cloud Data (PCD). Most existing methods require full cylinder data, do not study the presence of outliers, and are not statistically robust. But especially mobile laser scanning often has incomplete data, as street poles for ex le are only scanned from the road. Moreover, existence of outliers is common. Outliers may occur as random or systematic errors, and may be scattered and/or clustered. In this paper, we present a statistically robust cylinder fitting algorithm for PCD that combines Robust Principal Component Analysis (RPCA) with robust regression. Robust principal components as obtained by RPCA allow estimating cylinder directions more accurately, and an existing efficient circle fitting algorithm following robust regression principles, properly fit cylinder. We demonstrate the performance of the proposed method on artificial and real PCD. Results show that the proposed method provides more accurate and robust results: (i) in the presence of noise and high percentage of outliers, (ii) for incomplete as well as complete data, (iii) for small and large number of points, and (iv) for different sizes of radius. On 1000 simulated quarter cylinders of 1m radius with 10% outliers a PCA based method fit cylinders with a radius of on average 3.63 meter (m) the proposed method on the other hand fit cylinders of on average 1.02 m radius. The algorithm has potential in applications such as fitting cylindrical (e.g., light and traffic) poles, diameter at breast height estimation for trees, and building and bridge information modelling.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Elsevier BV
Date: 2020
Publisher: Elsevier BV
Date: 09-2018
Publisher: Informa UK Limited
Date: 20-12-2013
Publisher: IGI Global
Date: 2012
DOI: 10.4018/978-1-4666-1830-5.CH016
Abstract: The use of logistic regression, its modelling and decision making from the estimated model and subsequent analysis has been drawn a great deal of attention since its inception. The current use of logistic regression methods includes epidemiology, biomedical research, criminology, ecology, engineering, pattern recognition, machine learning, wildlife biology, linguistics, business and finance, et cetera. Logistic regression diagnostics have attracted both theoreticians and practitioners in recent years. Detection and handling of outliers is considered as an important task in the data modelling domain, because the presence of outliers often misleads the modelling performances. Traditionally logistic regression models were used to fit data obtained under experimental conditions. But in recent years, it is an important issue to measure the outliers scale before putting the data as a logistic model input. It requires a higher mathematical level than most of the other material that steps backward to its study and application in spite of its inevitability. This chapter presents several diagnostic aspects and methods in logistic regression. Like linear regression, estimates of the logistic regression are sensitive to the unusual observations: outliers, high leverage, and influential observations. Numerical ex les and analysis are presented to demonstrate the most recent outlier diagnostic methods using data sets from medical domain.
Publisher: IEEE
Date: 05-2013
DOI: 10.1109/CRV.2013.28
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2016
Publisher: IEEE
Date: 12-2012
Publisher: Elsevier BV
Date: 11-2023
Location: Bangladesh
Start Date: 2016
End Date: 2019
Funder: Irish Research Council
View Funded ActivityStart Date: 2016
End Date: 2019
Funder: Japan Society for the Promotion of Science
View Funded ActivityStart Date: 2016
End Date: 2019
Funder: Central Queensland University
View Funded ActivityStart Date: 2016
End Date: 2019
Funder: University of Ballarat
View Funded Activity