RivaMap: An Automated River Analysis and Mapping Engine

Related papers

* Isikdogan, F., A.C. Bovik, and P. Passalacqua (2016). LarMap: A Framework for Creating Large-scale River Maps using Satellite Imagery, unpublished. * Isikdogan, F., A.C. Bovik, and P. Passalacqua (2015). Automatic Channel Network Extraction From Remotely Sensed Images by Singularity Analysis, *IEEE Geoscience and Remote Sensing Letters*, 12, 11, 2218-2221. [[**Read at IEEExplore**]](http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7192616), [[**PDF**]](http://live.ece.utexas.edu/publications/2015/Isikdogan_GRSL_2015_Channel_Network_Extraction.pdf)

Dependencies

• python 2.7
• numpy
• scipy
• cv2
• matplotlib
• osgeo

Example Use

For an example use of the framework please see example.ipynb

Example Results

Reference

Function	Description
preprocess.mndwi	Computes the modified normalized difference water index. Inputs: green: green band (e.g. Landsat 8 band 3) mir: middle infrared band (e.g. Landsat 8 band 6) Returns: mndwi: mndwi response
preprocess.contrastStretch	Applies contrast stretch to an input image. Inputs and outputs an image.
preprocess.im2double	Converts image datatype to float. Inputs and outputs an image.
preprocess.double2im	Converts double data array to image. Inputs and outputs an image.
singularity_index.SingularityIndexFilters	Creates the filters that are needed for computing the modified multiscale singularity index response. The filters can be used for processing many input images once the filters are created. Keyword arguments: minScale: minimum scale sigma (default 1.2 pixels) nrScales: number of scales (default 15)
singularity_index.applyMMSI	Applies the filters to a given input image to compute the modified multiscale singularity index response. Estimates the width and the dominant orientation angle for each spatial location. Inputs: I1: input image (e.g. Landsat NIR band or MNDWI) filters: an instance of SingularityIndexFilters class that contains precomputed filters togglePolarity: changes polarity, use if the rivers are darker than land in the input image (i.e. SAR images) Returns: psi: the singularity index response widthMap: estimated width at each spatial location (x,y) orient: local orientation at each spatial location (x,y)
delineate.extractCenterlines	Uses the previously computed singularity index response (psi) and the dominant orientation (orient) to extract centerlines. Inputs: (can be obtained by running applyMMSI function) psi: the singularity index response orient: local orientation at each spatial location (x,y) Returns: nms: Non-maxima suppressed singularity index response (centerlines)
delineate.thresholdCenterlines	Uses a continuity-preserving hysteresis thresholding to classify centerlines. Inputs: nms: Non-maxima suppressed singularity index response Keyword Arguments: bimodal: true if the areas of rivers in the image are sufficiently large that the distribution of psi is bimodal tLow: lower threshold (automatically set if bimodal=True) tHigh: higher threshold (automatically set if bimodal=True) Returns: centerlines: a binary matrix that indicates centerline locations
georef.loadGeoMetadata	Reads metadata from a geotiff file. Inputs: filepath: path to the file Returns: gm: metadata
georef.saveAsGeoTiff	Saves a raster image as a geotiff file Inputs: gm: georeferencing metadata I: raster image filepath: save destination
georef.pix2lonlat	Convers pixel coordinates into longitude and latitude. Inputs: gm: georeferencing metadata x, y: pixel coordinates Returns: lon, lat: longitude and latitude
georef.lonlat2pix	Convers longitude and latitude into pixel coordinates. Inputs: gm: georeferencing metadata lon, lat: longitude and latitude Returns: x, y: pixel coordinates
georef.exportCSVfile	Exports (coordinate, width) pairs to a comma separated text file. Inputs: centerlines: a binary matrix that indicates centerline locations widthMap: estimated width at each spatial location (x,y) gm: georeferencing metadata filepath: path to the file
visualization.generateRasterMap	Generates a raster map of channels. It draws a line of length w(x, y) and orientation θ(x, y) at each spatial location. Inputs: centerlines: a binary matrix that indicates centerline locations orient: local orientation at each spatial location (x,y) widthMap: estimated width at each spatial location (x,y) Keyword Arguments: thickness: thickness of the lines (default 3) Returns: raster: the raster map
visualization.generateVectorMap	Generates a vector map of channels. It draws a line of length w(x, y) and orientation θ(x, y) at each spatial location. Inputs: centerlines: a binary matrix that indicates centerline locations orient: local orientation at each spatial location (x,y) widthMap: estimated width at each spatial location (x,y) saveDest: output figure save destination Keyword Arguments: thickness: thickness of the lines (default 0.2) Returns: None (saves the figure at saveDest)
visualization.quiverPlot	Generates a quiver plot that shows channel orientation and singularity index response strength. Inputs: psi: singularity index response orient: local orientation at each spatial location (x,y) saveDest: output figure save destination Returns: None (saves the figure at saveDest)