“…Li [14] proposed a geometry-aware convolution, which aims to learn the high-level features from the low-level handcrafted features, so that the geometric awareness can be emphasized by the prior knowledge of the neighborhood. To avoid overfitting, Arief [17] refined a trained PointCNN model by combing the strict pairwise penalties that are used in the CRF procedure on the unseen data. To address the challenges of uneven density distribution, Li [70] introduced a density-aware convolutional module which adds an inverse density function to reweight the convolutional kernel.…”
Section: ) Deep Learning For the Classification Of Als Point Cloudsmentioning
confidence: 99%
“…Most reported results were obtained with different experimental setups, such as the generation of training patches in pre-processing, class balancing strategies and learning rate schedule [16]. Moreover, the models are mostly trained and evaluated on the ISPRS Vaihingen 3D dataset [14,15,17,18]. Although these benchmark point clouds provide the possibility for performance comparison of different models, it only covers a small area with limited diversity in the scenes [12].…”
The success achieved by deep learning techniques in image labelling has triggered a growing interest in applying deep learning for 3D point cloud classification. To provide better insights into different deep learning architectures and their applications to ALS point cloud classification, this paper presents a comprehensive comparison among three state-of-theart deep learning networks: PointNet++, SparseCNN and KPConv, on two different ALS datasets. The performances of these three deep learning networks are compared w.r.t. classification accuracy, computation time, generalization ability as well as the sensitivity to the choices of hyper-parameters. Overall, we observed that PointNet++, SparseCNN and KPConv all outperform Random Forest on the classification results. Moreover, SparseCNN leads to a slightly better classification result compared to PointNet++ and KPConv, while requiring less computation time and memory. At the same time, it shows a better ability to generalize and is less impacted by the different choices of hyper-parameters.
“…Li [14] proposed a geometry-aware convolution, which aims to learn the high-level features from the low-level handcrafted features, so that the geometric awareness can be emphasized by the prior knowledge of the neighborhood. To avoid overfitting, Arief [17] refined a trained PointCNN model by combing the strict pairwise penalties that are used in the CRF procedure on the unseen data. To address the challenges of uneven density distribution, Li [70] introduced a density-aware convolutional module which adds an inverse density function to reweight the convolutional kernel.…”
Section: ) Deep Learning For the Classification Of Als Point Cloudsmentioning
confidence: 99%
“…Most reported results were obtained with different experimental setups, such as the generation of training patches in pre-processing, class balancing strategies and learning rate schedule [16]. Moreover, the models are mostly trained and evaluated on the ISPRS Vaihingen 3D dataset [14,15,17,18]. Although these benchmark point clouds provide the possibility for performance comparison of different models, it only covers a small area with limited diversity in the scenes [12].…”
The success achieved by deep learning techniques in image labelling has triggered a growing interest in applying deep learning for 3D point cloud classification. To provide better insights into different deep learning architectures and their applications to ALS point cloud classification, this paper presents a comprehensive comparison among three state-of-theart deep learning networks: PointNet++, SparseCNN and KPConv, on two different ALS datasets. The performances of these three deep learning networks are compared w.r.t. classification accuracy, computation time, generalization ability as well as the sensitivity to the choices of hyper-parameters. Overall, we observed that PointNet++, SparseCNN and KPConv all outperform Random Forest on the classification results. Moreover, SparseCNN leads to a slightly better classification result compared to PointNet++ and KPConv, while requiring less computation time and memory. At the same time, it shows a better ability to generalize and is less impacted by the different choices of hyper-parameters.
“…Several state-of-the-art algorithms for sequence modelling, including Convolutional LSTM [ 117 ] and Attention model [ 118 ], have provided significant improvement in terms of accuracy, by considering the temporal dependencies within the input data. In addition, a graphical model, such as Conditional Random Field (CRF) principle [ 119 ], can also be used to cross-correlate the spatiotemporal structure of the distributed sensors, tying together the spatiotemporal relationship among each spatial channel and their neighbouring channels in the spatial domain as well as in the time domain.…”
Real-time monitoring of multiphase fluid flows with distributed fibre optic sensing has the potential to play a major role in industrial flow measurement applications. One such application is the optimization of hydrocarbon production to maximize short-term income, and prolong the operational lifetime of production wells and the reservoir. While the measurement technology itself is well understood and developed, a key remaining challenge is the establishment of robust data analysis tools that are capable of providing real-time conversion of enormous data quantities into actionable process indicators. This paper provides a comprehensive technical review of the data analysis techniques for distributed fibre optic technologies, with a particular focus on characterizing fluid flow in pipes. The review encompasses classical methods, such as the speed of sound estimation and Joule-Thomson coefficient, as well as their data-driven machine learning counterparts, such as Convolutional Neural Network (CNN), Support Vector Machine (SVM), and Ensemble Kalman Filter (EnKF) algorithms. The study aims to help end-users establish reliable, robust, and accurate solutions that can be deployed in a timely and effective way, and pave the wave for future developments in the field.
“…The overfitting and poor generalization problems are discussed in [ 22 ]. The proposed Addressing Overfitting on Pointcloud Classification (AOPC) aims to address the inducing controlled noise generated by conditional random field parallel penalties using adjacent features of [ 22 ]. The authors proposed new algorithm named Atrous XCRF to overcome the overfitting problem and enhance the classification of pointcloud data.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The SVM-RBF, SVM-Linear, MLC, and MDC have been compared both from a mathematical perspective and with the experiment results to show their different levels of accuracy and efficiency. Moreover, SVM-RBF, SVM-Linear have also been compared with current state-of-the-art algorithms: NDCI [ 8 ], SCMask R-CNN [ 17 ], CIAs [ 18 ], KCA [ 21 ], and AOPC [ 22 ] from the change detection accuracy, and reliability viewpoint.…”
Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.