A5046281951- Remote Sensing and Land Use
- Remote-Sensing Image Classification
- Advanced Computational Techniques and Applications
- Geographic Information Systems Studies
- Hydrology and Watershed Management Studies
- Environmental and Agricultural Sciences
- Soil Moisture and Remote Sensing
- Environmental Changes in China
- Advanced Image and Video Retrieval Techniques
- Rough Sets and Fuzzy Logic
- Grey System Theory Applications
- Climate variability and models
- Soil and Land Suitability Analysis
- Image Retrieval and Classification Techniques
- Energy Load and Power Forecasting
- Advanced Algorithms and Applications
- Data Management and Algorithms
- Remote Sensing in Agriculture
- Cryospheric studies and observations
Chinese Academy of Surveying and Mapping
2011-2017
National Administration of Surveying, Mapping and Geoinformation of China
2015
Abstract. Image segmentation is the foundation of further object-oriented image analysis, understanding and recognition. It one key technologies in high resolution remote sensing applications. In this paper, a new fast algorithm for imagery proposed, which based on graph theory fractal net evolution approach (FNEA). Firstly, an modelled as weighted undirected graph, where nodes correspond to pixels, edges connect adjacent pixels. An initial object layer can be obtained efficiently from...
Abstract. GEOBIA (Geographic Object-Based Image Analysis) is not only a hot topic of current remote sensing and geographical research. It believed to be paradigm in GIScience. The lack systematic approach designed conceptualize formalize the class definitions makes highly subjective difficult method reproduce. This paper aims put forward framework for based on geographic ontology theory, which could implement "Geographic entities - objects Geographic objects" true reappearance. consists...
Electricity load forecasting is one of the important tasks power marketing department, and accurate extremely to ensure real-time dispatch security system. In order obtain reliable results, an ultra-short-term model based on improved random forest regression algorithm proposed in this paper. First, data pre-processing performed original dataset. Then pre-processed time historical are used as inputs model, optimization using Gaussian mixture-based tree-structured Parzen estimator carried out....
Abstract. Quick mosaicking of wide range remote sensing imagery is an important foundation for land resource survey and dynamic monitoring environment nature disasters. It also technically basis geographic information acquiring product updating. This paper mainly focuses on one key technique mosaicking, color balancing Remote Sensing imagery. Due to huge amount data, large covering rage, great variety climate geographical condition, a difficult problem. In this we use Ecogeographic...
Abstract. The research on coupling both data source is very important for improving the accuracy of Image information interpretation and target recognition. In this paper a classifier presented, which based integration active passive remote sensing Maximum Likelihood classification inversion soil moisture method tested in Heihe river basin, semi-arid area north-west china. algorithm wavelet transform IHS are combined to integrate TM3, TM4, TM5 ASAR data. maximum distance substitution local...
Abstract. Land Cover is the basis of geographic national conditions monitoring, extracting land cover information timely and accurately has become one important tasks in surveying project. For current situation complex type large amount data, there emerged various new classification techniques methods. However, big difficult classification，the heavy workload post-editing other factors have seriously hampered progress In this paper, it chooses high-resolution remote sensing image as original...
A classifier based on Bayesian theory and MRF is presented to classify the active microwave passive optical remote sensing data, which have demonstrated their respective advantages in inversion of surface soil moisture content. In method, VV, VH polarization ASAR all 7 TM bands are taken as input get class labels each pixel images. And model validated for necessities integration ASAR, it shows that, total precision classification this paper 89.4%. Comparing with single TM, accuracy increase...
Abstract. A classifier based on Bayesian theory and Markov random field (MRF) is presented to classify the active microwave passive optical remote sensing data, which have demonstrated their respective advantages in inversion of surface soil moisture content. In method, VV, VH polarization ASAR all 7 TM bands are taken as input get class labels each pixel images. And model validated for necessities integration ASAR, it shows that, total precision classification this paper 89.4%. Comparing...
Abstract. Classification rule set is important for Land Cover classification, which refers to features and decision rules. The selection of are based on an iterative trial-and-error approach that often utilized in GEOBIA, however, it time-consuming has a poor versatility. This study put forward building method cover classification human knowledge machine learning. use learning build sets effectively will overcome the approach. solve shortcomings existing insufficient usage prior knowledge,...