Point cloud quality assessment based on geometry-aware texture descriptors

2022 ◽  
Author(s):  
Rafael Diniz ◽  
Pedro Garcia Freitas ◽  
Mylene C.Q. Farias
Keyword(s):  
Quality Assessment ◽  
Point Cloud

scholarly journals ASSESSMENT OF THE QUALITY OF DIGITAL TERRAIN MODEL PRODUCED FROM UNMANNED AERIAL SYSTEM IMAGERY

2016 ◽  
Vol XLI-B1 ◽  
pp. 893-899
Author(s):  
M. Kosmatin Fras ◽  
A. Kerin ◽  
M. Mesarič ◽  
V. Peterman ◽  
D. Grigillo
Keyword(s):  
Quality Assessment ◽  
Point Cloud ◽  
Digital Terrain Model ◽  
Quality Parameter ◽  
Unmanned Aerial System ◽  
Test Field ◽  
Absolute Deviation ◽  
Terrain Model ◽  
Digital Terrain

Production of digital terrain model (DTM) is one of the most usual tasks when processing photogrammetric point cloud generated from Unmanned Aerial System (UAS) imagery. The quality of the DTM produced in this way depends on different factors: the quality of imagery, image orientation and camera calibration, point cloud filtering, interpolation methods etc. However, the assessment of the real quality of DTM is very important for its further use and applications. In this paper we first describe the main steps of UAS imagery acquisition and processing based on practical test field survey and data. The main focus of this paper is to present the approach to DTM quality assessment and to give a practical example on the test field data. For data processing and DTM quality assessment presented in this paper mainly the in-house developed computer programs have been used. The quality of DTM comprises its accuracy, density, and completeness. Different accuracy measures like RMSE, median, normalized median absolute deviation and their confidence interval, quantiles are computed. The completeness of the DTM is very often overlooked quality parameter, but when DTM is produced from the point cloud this should not be neglected as some areas might be very sparsely covered by points. The original density is presented with density plot or map. The completeness is presented by the map of point density and the map of distances between grid points and terrain points. The results in the test area show great potential of the DTM produced from UAS imagery, in the sense of detailed representation of the terrain as well as good height accuracy.

scholarly journals Extreme Feature Regions Detection and Accurate Quality Assessment for Point-Cloud 3D Reconstruction

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 37757-37769 ◽  
Author(s):  
Yunbo Rao ◽  
Baijiang Fan ◽  
Qifei Wang ◽  
Jiansu Pu ◽  
Xun Luo ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
Quality Assessment ◽  
Point Cloud

A novel point cloud quality assessment metric based on perceptual color distance patterns

2021 ◽  
Vol 2021 (9) ◽  
pp. 256-1-256-11
Author(s):  
Rafael Diniz ◽  
Pedro Garcia Freitas ◽  
Mylène Farias
Keyword(s):  
Quality Assessment ◽  
Point Cloud ◽  
State Of The Art ◽  
Perceptual Quality ◽  
Great Effort ◽  
Robust Performance ◽  
Wide Range ◽  
Objective Quality ◽  
Novel Method

In recent years, PCs have become very popular for a wide range of applications, such as immersive virtual reality scenarios. As a consequence, in the last couple of years, there has been a great effort to develop novel acquisition, representation, compression, and transmission solutions for PC contents in the research community. In particular, the development of objective quality assessment methods that are able to predict the perceptual quality of PCs. In this paper, we present an effective novel method for assessing the quality of PCs, which is based on descriptors that extract perceptual color distance-based texture information of PC contents, called Perceptual Color Distance Patterns (PCDP). In this framework, the statistics of the extracted information are used to model the PC visual quality. Experimental results show that the proposed framework exhibit good and robust performance when compared with several state-of-the-art point cloud quality assessment (PCQA) methods.

PQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi-view Projection

2021 ◽  
pp. 1-1
Author(s):  
Qi Liu ◽  
Hui Yuan ◽  
Honglei Su ◽  
Hao Liu ◽  
Yu Wang ◽  
...  
Keyword(s):  
Quality Assessment ◽  
Reference Point ◽  
Point Cloud

Multi-Distance Point Cloud Quality Assessment

2020 ◽  
Author(s):  
Rafael Diniz ◽  
Pedro Garcia Freitas ◽  
Mylene C.Q. Farias
Keyword(s):  
Quality Assessment ◽  
Point Cloud
Sign in / Sign up

Export Citation Format

Share Document