Hierarchical land cover information retrieval in object-oriented remote sensing image databases with native queries

Identifying the degree distribution of land cover networks is helpful to find analytical methods for characterizing complex land cover, including segmentation techniques of remote sensing images of land cover. After segmentation, we can obtain the geographical objects and corresponding relationships. In order to evaluate the segmentation results, we introduce the concept of land cover network and present an analysis method based on statistics of its degree distribution. Considering the object-oriented segmentation and objects merge-based spectral difference segmentation, we construct the land cover networks for different segmentation scales and spatial resolutions under these two segmentation strategies, and study the degree distribution of each land cover network. Experimental results indicate that, for the object-oriented segmentation, the degree distributions of land cover networks follow approximately a Poisson distribution, regardless of the segmentation scales and spatial resolutions. For the objects-merge method based on spectral difference segmentation, degree distributions exhibit heavy tails. Compared with all the segmentation results, the pattern spots after objects-merge better retain the integrity of geographical features and the land cover network can reflect more accurately the topological properties of real land cover when the threshold of objects merge is suitable. This study shows that we can evaluate the reliability of segmentation results objectively by analyzing the degree distribution pattern of land cover networks.

Download Full-text

A MACHINE LEARNING DATASET FOR LARGE-SCOPE HIGH RESOLUTION REMOTE SENSING IMAGE INTERPRETATION CONSIDERING LANDSCAPE SPATIAL HETEROGENEITY

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w13-731-2019 ◽

2019 ◽

Vol XLII-2/W13 ◽

pp. 731-736

Author(s):

Y. Xu ◽

X. Hu ◽

Y. Wei ◽

Y. Yang ◽

D. Wang

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Land Cover ◽

Spatial Heterogeneity ◽

Satellite Remote Sensing ◽

Sampling Method ◽

National Level ◽

Remote Sensing Image ◽

Training Sample ◽

Large Scope

<p><strong>Abstract.</strong> The demand for timely information about earth’s surface such as land cover and land use (LC/LU), is consistently increasing. Machine learning method shows its advantage on collecting such information from remotely sensed images while requiring sufficient training sample. For satellite remote sensing image, however, sample datasets covering large scope are still limited. Most existing sample datasets for satellite remote sensing image built based on a few frames of image located on a local area. For large scope (national level) view, choosing a sufficient unbiased sampling method is crucial for constructing balanced training sample dataset. Dependable spatial sample locations considering spatial heterogeneity of land cover are needed for choosing sample images. This paper introduces an ongoing work on establishing a national scope sample dataset for high spatial-resolution satellite remote sensing image processing. Sample sites been chosen sufficiently using spatial sampling method, and divided sample patches been grouped using clustering method for further uses. The neural network model for road detection trained our dataset subset shows an increased performance on both completeness and accuracy, comparing to two widely used public dataset.</p>

Download Full-text

Land Use/Land Cover Changes in a Disturbed River Watershed Kenya

European Journal of Engineering and Formal Sciences ◽

10.26417/ejef.v3i2.p29-36 ◽

2019 ◽

Vol 3 (2) ◽

pp. 29

Author(s):

Zachary Gichuru Mainuri ◽

John M. Mironga ◽

Samuel M. Mwonga

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Remote Sensing Image ◽

Land Cover Changes ◽

Land Use Land Cover ◽

Human Needs ◽

Observation Systems ◽

Erdas Imagine ◽

Remote Sensing Image Processing

Drivers of land use change were captured by the use of DPSIR model where Drivers (D) represented human needs, Pressures (P), human activities, State (S), the ecosystem, Impact (I) services from the ecosystem and Response (R), the decisions taken by land users. Land sat MSS and Land sat ETM+ (path 185, row 31) were used in this study. The Land sat ETM+ image (June 1987, May, 2000 and July, 2014) was downloaded from USGS Earth Resources Observation Systems data website. Remote sensing image processing was performed by using ERDAS Imagine 9.1. Two land use/land cover (LULC) classes were established as forest and shrub land. Severe land cover changes was found to have occurred from 1987-2000, where shrub land reduced by -19%, and forestry reduced by -72%. In 2000 – 2014 shrub land reduced by-45%, and forestry reduced by -64%. Forestry and shrub land were found to be consistently reducing.

Download Full-text