Abstract
Point cloud classification is an important task in point cloud data analysis. Traditional point cloud classification is conducted primarily on the basis of specific handcrafted features with a specific classifier and is often capable of producing satisfactory results. However, the extraction of crucial handcrafted features hinges on sufficient knowledge of the field and substantial experience. In contrast, while powerful deep learning algorithms possess the ability to learn features automatically, it normally requires complex network architecture and a considerable amount of calculation time to attain better accuracy of classification. In order to combine the advantages of both the methods, in this study, we integrated the handcrafted features, whose benefits were confirmed by previous studies, into a deep learning network, in the hopes of solving the problem of insufficient extraction of specific features and enabling the network to recognise other effective features through automatic learning. This was done to achieve the performance of a complex model by using a simple model and fulfil the application requirements of the remote sensing domain. As indicated by the experimental results, the integration of handcrafted features into the simple and fast-calculating PointNet model could generate a classification result that bore comparison with that generated by a complex network model such as PointNet++ or KPConv.
Highlights
The development of 3D scanning and 3D imaging technologies has resulted in easier acquisition and a wider range of application of point cloud data
In consideration of the advantages of the two models, such as the simplicity of the model, the small number of parameters, and speedy calculation, in this study, we focused on examining these two deep learning models and assessing their effects on the efficacy of point cloud classification after the models incorporated the handcrafted features
In order to assess the efficacy of each model in point cloud classification, we used the classification performance metrics, which are frequently used in machine learning and include overall accuracy (OA), precision, recall, and F1-score, and Matthews correlation coefficient (MCC) [56]
Summary
The development of 3D scanning and 3D imaging technologies has resulted in easier acquisition and a wider range of application of point cloud data. Many DL models applicable to point cloud classification have recently been proposed, such as PointNet++ [30], PointCNN [31], PointSIFT [32], and KPConv [33] These DL models lack a common framework, and some of the model structures have been deliberately expanded to enhance the classification efficacy, which increases the model complexity and the calculation time and results in overfitting [34], rendering the trained model inapplicable to other scenes. The primary purpose of this study was to enhance the performance of point cloud classification by combining the advantages of handcrafted features and learned features without having to increase the complexity of the network model This was done on the basis of the existing 3D DL models and the accumulative experience and knowledge of remote sensing. Remote Sens. 2020, 12, 3713 will achieve, and even exceed, the performance of a complex DL model, and fulfil the application requirements of the remote sensing domain
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call