Xiaohua Tong

Bio: Xiaohua Tong is an academic researcher from Tongji University. The author has contributed to research in topics: Computer science & Hyperspectral imaging. The author has an hindex of 32, co-authored 332 publications receiving 4855 citations. Previous affiliations of Xiaohua Tong include University of Toronto & Wuhan University.

Global land cover mapping at 30 m resolution: A POK-based operational approach

Abstract: Global Land Cover (GLC) information is fundamental for environmental change studies, land resource management, sustainable development, and many other societal benefits. Although GLC data exists at spatial resolutions of 300 m and 1000 m, a 30 m resolution mapping approach is now a feasible option for the next generation of GLC products. Since most significant human impacts on the land system can be captured at this scale, a number of researchers are focusing on such products. This paper reports the operational approach used in such a project, which aims to deliver reliable data products. Over 10,000 Landsat-like satellite images are required to cover the entire Earth at 30 m resolution. To derive a GLC map from such a large volume of data necessitates the development of effective, efficient, economic and operational approaches. Automated approaches usually provide higher efficiency and thus more economic solutions, yet existing automated classification has been deemed ineffective because of the low classification accuracy achievable (typically below 65%) at global scale at 30 m resolution. As a result, an approach based on the integration of pixel- and object-based methods with knowledge (POK-based) has been developed. To handle the classification process of 10 land cover types, a split-and-merge strategy was employed, i.e. firstly each class identified in a prioritized sequence and then results are merged together. For the identification of each class, a robust integration of pixel-and object-based classification was developed. To improve the quality of the classification results, a knowledge-based interactive verification procedure was developed with the support of web service technology. The performance of the POK-based approach was tested using eight selected areas with differing landscapes from five different continents. An overall classification accuracy of over 80% was achieved. This indicates that the developed POK-based approach is effective and feasible for operational GLC mapping at 30 m resolution.

Mapping essential urban land use categories in China (EULUC-China): preliminary results for 2018

Abstract: Land use reflects human activities on land. Urban land use is the highest level human alteration on Earth, and it is rapidly changing due to population increase and urbanization. Urban areas have widespread effects on local hydrology, climate, biodiversity, and food production. However, maps, that contain knowledge on the distribution, pattern and composition of various land use types in urban areas, are limited to city level. The mapping standard on data sources, methods, land use classification schemes varies from city to city, due to differences in financial input and skills of mapping personnel. To address various national and global environmental challenges caused by urbanization, it is important to have urban land uses at the national and global scales that are derived from the same or consistent data sources with the same or compatible classification systems and mapping methods. This is because, only with urban land use maps produced with similar criteria, consistent environmental policies can be made, and action efforts can be compared and assessed for large scale environmental administration. However, despite of the fact that a number of urban-extent maps exist at global scales [3,4], more detailed urban land use maps do not exist at the same scale. Even at big country or regional levels such as for the United States, China and European Union, consistent land use mapping efforts are rare.

A Multiscale and Hierarchical Feature Extraction Method for Terrestrial Laser Scanning Point Cloud Classification

Abstract: The effective extraction of shape features is an important requirement for the accurate and efficient classification of terrestrial laser scanning (TLS) point clouds. However, the challenge of how to obtain robust and discriminative features from noisy and varying density TLS point clouds remains. This paper introduces a novel multiscale and hierarchical framework, which describes the classification of TLS point clouds of cluttered urban scenes. In this framework, we propose multiscale and hierarchical point clusters (MHPCs). In MHPCs, point clouds are first resampled into different scales. Then, the resampled data set of each scale is aggregated into several hierarchical point clusters, where the point cloud of all scales in each level is termed a point-cluster set. This representation not only accounts for the multiscale properties of point clouds but also well captures their hierarchical structures. Based on the MHPCs, novel features of point clusters are constructed by employing the latent Dirichlet allocation (LDA). An LDA model is trained according to a training set. The LDA model then extracts a set of latent topics, i.e., a feature of topics, for a point cluster. Finally, to apply the introduced features for point-cluster classification, we train an AdaBoost classifier in each point-cluster set and obtain the corresponding classifiers to separate the TLS point clouds with varying point density and data missing into semantic regions. Compared with other methods, our features achieve the best classification results for buildings, trees, people, and cars from TLS point clouds, particularly for small and moving objects, such as people and cars.

Building-damage detection using pre- and post-seismic high-resolution satellite stereo imagery: A case study of the May 2008 Wenchuan earthquake

Abstract: To address the disadvantage of traditional methods providing only two-dimensional (2D) damage change of the collapsed buildings, this paper presents an approach for the detection of the buildings that have collapsed in an earthquake based on 3D geometric changes, particularly height change of the buildings, using pre- and post-seismic IKONOS stereo image pairs. One of the critical issues – the accuracy of the 3D ground point determination from high-resolution satellite imagery (HRSI) – is first addressed employing a bias-compensation model based on the rational function polynomial coefficient bundle adjustment. With the refined 3D ground coordinates, two ways of detecting the collapsed buildings are proposed: (1) detection of an individual collapsed building by comparing the height differences at the corner points of the building calculated from the pre- and post-seismic IKONOS stereo pairs and (2) determination of the region of collapsed buildings by calculating the difference between the pre- and post-seismic digital elevation models (DEMs) generated again from the pre- and post-seismic stereo images. At the same time, a pre-seismic DEM based on a topographical map is generated for detection comparison in the study. The experiment results for Dujiangyan using two IKONOS stereo pairs before and after the Wenchuan earthquake demonstrated the following. (1) Accuracy of better than 1.1 m in planimetry and 1.5 m in height can be achieved from the pre- and post-seismic IKONOS stereo image pairs using the affine bias compensation model. This accuracy guarantees the feasibility of detecting the 3D geometric changes of the earthquake-induced building collapses from pre- and post-seismic HRSI stereo images. (2) Using the refined 3D coordinates of the ground points computed from the pre- and post-seismic IKONOS stereo pairs, the status (i.e., totally collapsed, partially collapsed or not collapsed) and the number of collapsed storeys can be estimated for an individual building being assessed. (3) The region of collapsed buildings can be determined by differencing the pre- and post-seismic DEMs created from the pre- and post-seismic IKONOS stereo pairs. An overall accuracy of better than 90% is achieved for the detection of the collapsed buildings based on the difference DEM using the pixel- and object-based assessment methods.

SoilGrids250m: Global gridded soil information based on machine learning

Abstract: This paper describes the technical development and accuracy assessment of the most recent and improved version of the SoilGrids system at 250m resolution (June 2016 update). SoilGrids provides global predictions for standard numeric soil properties (organic carbon, bulk density, Cation Exchange Capacity (CEC), pH, soil texture fractions and coarse fragments) at seven standard depths (0, 5, 15, 30, 60, 100 and 200 cm), in addition to predictions of depth to bedrock and distribution of soil classes based on the World Reference Base (WRB) and USDA classification systems (ca. 280 raster layers in total). Predictions were based on ca. 150,000 soil profiles used for training and a stack of 158 remote sensing-based soil covariates (primarily derived from MODIS land products, SRTM DEM derivatives, climatic images and global landform and lithology maps), which were used to fit an ensemble of machine learning methods-random forest and gradient boosting and/or multinomial logistic regression-as implemented in the R packages ranger, xgboost, nnet and caret. The results of 10-fold cross-validation show that the ensemble models explain between 56% (coarse fragments) and 83% (pH) of variation with an overall average of 61%. Improvements in the relative accuracy considering the amount of variation explained, in comparison to the previous version of SoilGrids at 1 km spatial resolution, range from 60 to 230%. Improvements can be attributed to: (1) the use of machine learning instead of linear regression, (2) to considerable investments in preparing finer resolution covariate layers and (3) to insertion of additional soil profiles. Further development of SoilGrids could include refinement of methods to incorporate input uncertainties and derivation of posterior probability distributions (per pixel), and further automation of spatial modeling so that soil maps can be generated for potentially hundreds of soil variables. Another area of future research is the development of methods for multiscale merging of SoilGrids predictions with local and/or national gridded soil products (e.g. up to 50 m spatial resolution) so that increasingly more accurate, complete and consistent global soil information can be produced. SoilGrids are available under the Open Data Base License.

An inventory of gaseous and primary aerosol emissions in Asia in the year 2000 : NASA global tropospheric experiment transport and chemical evolution over the pacific (TRACE-P): Measurements and analysis (TRACEP1)

Abstract: [i] An inventory of air pollutant emissions in Asia in the year 2000 is developed to support atmospheric modeling and analysis of observations taken during the TRACE-P experiment funded by the National Aeronautics and Space Administration (NASA) and the ACE-Asia experiment funded by the National Science Foundation (NSF) and the National Oceanic and Atmospheric Administration (NOAA). Emissions are estimated for all major anthropogenic sources, including biomass burning, in 64 regions of Asia. We estimate total Asian emissions as follows: 34.3 Tg SO 2 , 26.8 Tg NO x , 9870 Tg CO 2 , 279 Tg CO, 107 Tg CH 4 , 52.2 Tg NMVOC, 2.54 Tg black carbon (BC), 10.4 Tg organic carbon (OC), and 27.5 Tg NH 3 . In addition, NMVOC are speciated into 19 subcategories according to functional groups and reactivity. Thus we are able to identify the major source regions and types for many of the significant gaseous and particle emissions that influence pollutant concentrations in the vicinity of the TRACE-P and ACE-Asia field measurements. Emissions in China dominate the signature of pollutant concentrations in this region, so special emphasis has been placed on the development of emission estimates for China. China's emissions are determined to be as follows: 20.4 Tg SO 2 , 11.4 Tg NO x , 3820 Tg CO 2 , 116 Tg CO, 38.4 Tg CH 4 , 17.4 Tg NMVOC, 1.05 Tg BC, 3.4 Tg OC, and 13.6 Tg NH 3 . Emissions are gridded at a variety of spatial resolutions from 1° × 1° to 30 s x 30 s, using the exact locations of large point sources and surrogate GIS distributions of urban and rural population, road networks, landcover, ship lanes, etc. The gridded emission estimates have been used as inputs to atmospheric simulation models and have proven to be generally robust in comparison with field observations, though there is reason to think that emissions of CO and possibly BC may be underestimated. Monthly emission estimates for China are developed for each species to aid TRACE-P and ACE-Asia data interpretation. During the observation period of March/ April, emissions are roughly at their average values (one twelfth of annual). Uncertainties in the emission estimates, measured as 95% confidence intervals, range from a low of ±16% for SO 2 to a high of ±450% for OC.

Remote Sensing And Image Interpretation

Abstract: Thank you very much for downloading remote sensing and image interpretation. As you may know, people have look hundreds times for their favorite novels like this remote sensing and image interpretation, but end up in malicious downloads. Rather than reading a good book with a cup of tea in the afternoon, instead they are facing with some malicious virus inside their computer. remote sensing and image interpretation is available in our digital library an online access to it is set as public so you can get it instantly. Our book servers spans in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Merely said, the remote sensing and image interpretation is universally compatible with any devices to read.

Remote Sensing Image Scene Classification: Benchmark and State of the Art

Abstract: Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning datasets and methods for scene classification is still lacking. In addition, almost all existing datasets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale dataset, termed "NWPU-RESISC45", which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 (i) is large-scale on the scene classes and the total image number, (ii) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion, and (iii) has high within-class diversity and between-class similarity. The creation of this dataset will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed dataset and the results are reported as a useful baseline for future research.