Xufeng Xing

Université Laval

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Huang Miao-fen

Guangdong Ocean University

Mir Abolfazl Mostafavi

Centre for Interdisciplinary Research in Rehabilitation

Qingjun Song

National Satellite Ocean Application Service

Zulong Zhao

University of Regina

Chen Wang

California University of Pennsylvania

Zhanqiang Li

Qinghai University

Yuan Liu

Nanchang University

Elisabetta Colucci

Polytechnic University of Turin

N Sabo

Natural Resources Canada

Francesca Noardo

Open Geospatial Consortium

Cooperative Institutions

Chinese Academy of Sciences

Dalian Ocean University

University of Chinese Academy of Sciences

State Key Laboratory of Remote Sensing Science

Dalian Maritime University

Université Laval

Huazhong University of Science and Technology

Beijing Normal University

Polytechnic University of Turin

Shandong University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

AN IMPROVED AUTOMATIC POINTWISE SEMANTIC SEGMENTATION OF A 3D URBAN SCENE FROM MOBILE TERRESTRIAL AND AIRBORNE LIDAR POINT CLOUDS: A MACHINE LEARNING APPROACH

ISPRS annals of the photogrammetry, remote sensing and spatial information sciences (2019)

Xufeng Xing Mir Abolfazl Mostafavi Geoffrey Edwards N Sabo

Abstract. Automatic semantic segmentation of point clouds observed in a 3D complex urban scene is a challenging issue. Semantic segmentation of urban scenes based on machine learning algorithm requires appropriate features to distinguish objects from mobile terrestrial and airborne LiDAR point clouds in point level. In this paper, we propose a pointwise semantic segmentation method based on our proposed features derived from Difference of Normal and the features “directional height above” that compare height difference between a given point and neighbors in eight directions in addition to the features based on normal estimation. Random forest classifier is chosen to classify points in mobile terrestrial and airborne LiDAR point clouds. The results obtained from our experiments show that the proposed features are effective for semantic segmentation of mobile terrestrial and airborne LiDAR point clouds, especially for vegetation, building and ground classes in an airborne LiDAR point clouds in urban areas.

Pointwise

Mobile mapping

10.5194/isprs-annals-iv-4-w8-139-2019

Cite

Citations (7)

BUILDING FEATURES RECOGNITION FROM UNCERTAIN 3D LIDAR POINT CLOUDS: A SEMANTIC APPROACH

The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences (2020)

Xufeng Xing Mir Abolfazl Mostafavi

Abstract. LiDAR technology allows rapid observation of high-resolution and precise 3D point clouds for diverse applications in urban and natural areas. However, uneven density and incomplete point clouds make LiDAR data processing more challenging for the extraction of semantic information on objects and their components. In this paper, we propose a knowledge based semantic reasoning solution for the recognition of building components (e.g. roofs) from segmentation results in the presence of uncertainties in LiDAR point clouds. The proposed solution uses a semantic reasoning approach as well as a similarity evaluation process for object recognition. We apply the proposed method to recognize buildings’ roof styles from a point cloud with uncertainty as a case study.

Similarity (geometry)

10.5194/isprs-archives-xliii-b4-2020-89-2020

Cite

Citations (0)

Analysis of CDOM fluorescence spectrum characteristics in coastal water and its application

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (2014)

Xufeng Xing Xianqiang Lv Fang Liu Yuan Liu Jie Zhan

In accordance with the data which were experiment of mixing-ratio in water tank and collecting water samples in situ from natural seawater and urban sewage discharged into the sea along Dalian coast of the northern Yellow Sea in February and April 2012, with quinine sulfate and sodium humate as a reference, the calibration curve was established among CDOM (Chromophoric dissolved organic matter) concentration and fluorescence intensity and reference wave absorption coefficient. To calibration curve as the foundation, the CDOM samples concentration of various sources was determined after analyzing CDOM sample from Dalian coast of the northern Yellow Sea sewage into the sea and natural sea. Based on the comparative analysis on CDOM fluorescence fingerprint, the main component of water CDOM were determined. The results showed that in Dalian coastal waters of the northern Yellow Sea, the main component of CDOM in natural seawater is tryptophan and in urban sewage discharged into the sea are tryptophan, tyrosine, and humic acid. On the basis of comprehensive analysis of CDOM fluorescence and absorption spectral, the thinking of synergy inversion of CDOM absorption spectral slope S by connecting fluorescence and ocean color remote sensing is put forward.

Spectral slope

10.1117/12.2063749

Cite

Citations (0)

The Method for Retrieving Downward Atmospheric Long-wave Radiation Using Remotely Sensing Technique

Miao Huang Xufeng Xing C.-Z. Wang J.-C. Li

Using the measured data acquired from the experiments of the agriculture demonstration field in Xiaotangshan, Beijing in 2004 by automatic weather stations and thermal infrared thermometers, the correlation expression was established between surface radiometric temperature T at the time of Landsat /TM passing by the study area and air temperature T ₀ . Through analyzing the data from 21 regular weather stations in Beijing and 5 scenes TM images in 2004, Beijing, the experience expression between the thermal inertia (P) and air vapor pressure (e ₀ ) was created. Furthermore, the model of Izionmon(2003) was used based on the two expressions, and the spatial model was given that retrieve the pixel downward atmospheric radiation under clear day using the remote sensing parameters, such as thermal inertia and surface net radiation fluxes. The retrieve results were validated using experiment measuring data in practice. The improvement on the precision rather than 9.5% of estimating the surface net radiation fluxes by using the calculated downward atmospheric radiation on the pixel basis. It shows that is feasible to estimate the downward atmospheric radiation by making use of the thermal inertia and the surface radiometric temperature.

Atmospheric temperature

Atmospheric models

10.1109/igarss.2006.380

Cite

Citations (0)

An experimental study on the feasibility of monitoring petroleum-polluted waters with remote sensing technology

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (2009)

Huang Miao-fen Qingjun Song Xufeng Xing Junwu Tang W. S. Yu

An experimental study was carried out in order to prove the feasibility of monitoring petroluem-polluted waters with remote sensing technology. The field data was collected in the rivers threatened by petroleum pollution. The measured items mainly included (1) the absorption coefficients of yellow substance, de-pigmented particles and phytoplankton pigments; (2) the backscattering coefficients data of water; (3) water quality parameters; (4) in-situ fine water spectral data. First, absorption spectral features and backscattering coefficients of petroleum-polluted water were analyzed. Secondly, the field spectral data were processed as corresponding bands of ENVISAT/MERIS using the spectral respond function of ENVISAT/MERIS in order to probe into the contribution of the various constituent concentrations in waters on the leaving-water radiation and remote sensing reflectance. The results showed that (1) with the increase of the petroleum pollution concentration, the absorption coefficients of petroleum-polluted water are also increased; (2) the spectra slope of exponential function of petroleum-polluted water is larger than that of petroleum-unpolluted water; (3) Emulsificated oil and decomposed oil in water can be absorbed by suspended particles and influence the scattering properties of the particles. Moreover it will change the spectral model of the inorganic particles backscattering coefficient with petroleum-polluted water; (4) the correlation between petroleum pollution concentration and remote sensing reflectance based on ENVISAT/MERIS is negative. These features of inherent optical parameters and apparent optical parameters obtained from the experiment provide the feasibility for monitoring petroleum-polluted waters with remote sensing technology.

Petroleum product

10.1117/12.873279

Cite

Citations (1)

A new algorithm of retrieving a petroleum substances absorption coefficient in sea water based on a remote sensing image

Acta Oceanologica Sinica (2016)

Huang Miao-fen Xufeng Xing Qingjun Song Yang Liu Wentong Dong

Petroleum product

10.1007/s13131-016-0952-4

Cite

Citations (1)

MERIS-based aquatic petroleum pollution monitoring mode

Huang Miao-fen Zhang Xiang-ping Kejie Lu Xufeng Xing

This paper presents a study of satellite-based aquatic petroleum pollution monitoring mode. First, four field data collections were made in 2006 and 2008. The sampling sites were in where the rivers were all threaten by petroleum pollution. The most important feature of water spectra in visible and near-infrared wavelength influenced by petroleum pollution was discovered after analysis in detail. It exhibited three peaks and two troughs in the water spectral curves influenced by petroleum contamination. Secondly, the spectral data collected from the polluted rivers were processed to remote reflectance as corresponding bands of ENVISAT/MERIS. At the same time the detecting wave of MERIS data obtained above were taken into account. And then the MERIS-based monitoring mode of petroleum pollution concentration was established according to Fisher multi-class discriminant rule and combining with corresponding water quality data. Finally, the mode was applied to the ENVISAT/MERIS data overpass on June 5, 2007 in order to obtain the distributing image of petroleum pollution concentration in the rivers. By mean of the image the temporal change and spatial distribute of the petroleum concentration within the rivers were analyzed.

10.1109/igarss.2009.5417464

Cite

Citations (0)

Comparison of aerosol optical properties retrieved from different ground-based sky radiance observation

Donghui Li Zhengqiang Li Kaitao Li Xufeng Xing

In this paper, we compared the aerosol optical properties (single scattering albedo(SSA), real part part of refractive index(mr)) at 0.44 µm retrieved from two different (principal plane(PP) and almucantar(ALM)) measurement of sky radiance, which observed from ground-based sun-sky radiometer CE318. We found 75% cases of SSA and mr retrieval are higher retrieved from ALM compared with PP, and SSA has a high correlation (R ² =0.848) between these two measurement, while mr has a low(R ² =0.019).

10.1109/igarss.2012.6350342

Cite

Citations (0)

A Knowledge Base for Automatic Feature Recognition from Point Clouds in an Urban Scene

ISPRS International Journal of Geo-Information (2018)

Xufeng Xing Mir Abolfazl Mostafavi Seyed Hossein Chavoshi

LiDAR technology can provide very detailed and highly accurate geospatial information on an urban scene for the creation of Virtual Geographic Environments (VGEs) for different applications. However, automatic 3D modeling and feature recognition from LiDAR point clouds are very complex tasks. This becomes even more complex when the data is incomplete (occlusion problem) or uncertain. In this paper, we propose to build a knowledge base comprising of ontology and semantic rules aiming at automatic feature recognition from point clouds in support of 3D modeling. First, several modules for ontology are defined from different perspectives to describe an urban scene. For instance, the spatial relations module allows the formalized representation of possible topological relations extracted from point clouds. Then, a knowledge base is proposed that contains different concepts, their properties and their relations, together with constraints and semantic rules. Then, instances and their specific relations form an urban scene and are added to the knowledge base as facts. Based on the knowledge and semantic rules, a reasoning process is carried out to extract semantic features of the objects and their components in the urban scene. Finally, several experiments are presented to show the validity of our approach to recognize different semantic features of buildings from LiDAR point clouds.

Feature (linguistics)

Spatial relation

Representation

Semantic feature

3D city models

10.3390/ijgi7010028

Cite

Citations (15)

EXTENSION OF RCC TOPOLOGICAL RELATIONS FOR 3D COMPLEX OBJECTS COMPONENTS EXTRACTED FROM 3D LIDAR POINT CLOUDS

The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences (2016)

Xufeng Xing Mir Abolfazl Mostafavi Chen Wang

Abstract. Topological relations are fundamental for qualitative description, querying and analysis of a 3D scene. Although topological relations for 2D objects have been extensively studied and implemented in GIS applications, their direct extension to 3D is very challenging and they cannot be directly applied to represent relations between components of complex 3D objects represented by 3D B-Rep models in R3. Herein we present an extended Region Connection Calculus (RCC) model to express and formalize topological relations between planar regions for creating 3D model represented by Boundary Representation model in R3. We proposed a new dimension extended 9-Intersection model to represent the basic relations among components of a complex object, including disjoint, meet and intersect. The last element in 3*3 matrix records the details of connection through the common parts of two regions and the intersecting line of two planes. Additionally, this model can deal with the case of planar regions with holes. Finally, the geometric information is transformed into a list of strings consisting of topological relations between two planar regions and detailed connection information. The experiments show that the proposed approach helps to identify topological relations of planar segments of point cloud automatically.

Disjoint sets

Representation

Spatial relation

10.5194/isprs-archives-xli-b3-425-2016

Cite

Citations (3)