Land cover classification in multispectral imagery using clustering of sparse approximations over learned feature dictionaries

Abstract

Abstract. We present results from an ongoing effort to extend neuromimetic machine vision algorithms to multispectral data using adaptive signal processing combined with compressive sensing and machine learning techniques. Our goal is to develop a robust classification methodology that will allow for automated discretization of the landscape into distinct units based on attributes such as vegetation, surface hydrological properties, and topographic/geomorphic characteristics. We use a Hebbian learning rule to build spectral-textural dictionaries that are tailored for classification. We learn our dictionaries from millions of overlapping multispectral image patches and then use a pursuit search to generate classification features. Land cover labels are automatically generated using unsupervised clustering of sparse approximations (CoSA). We demonstrate our method on multispectral WorldView-2 data from a coastal plain ecosystem in Barrow, Alaska. We explore learning from both raw multispectral imagery and normalized band difference indices. We explore a quantitative metric to evaluate the spectral properties of the clusters in order to potentially aid in assigning land cover categories to the cluster labels. Our results suggest CoSA is a promising approach to unsupervised land cover classification in highresolution satellite imagery.

Upscaling CH4 Fluxes Using High-Resolution Imagery in Arctic Tundra Ecosystems

“…The methods were chosen because of their ability to discriminate among vegetation classes and likely can capture the tundra variability within the tower footprint. For example, Muster et al [39], Langford et al [41], and Moody et al [52] have successfully used the k-means classifier to map tundra vegetation at the landscape scale. Bratsch et al [53] have used LDA previously to distinguish between different lowland tundra types and it has also been used by Gong et al [54] and Clark et al [55], for example, to map different vegetation types across other ecosystem types.…”

Classification of Tundra Vegetation in the Krkonoše Mts. National Park Using APEX, AISA Dual and Sentinel-2A Data

“…Many studies from different areas of the world focusing on tundra ecosystem were published over the last decades. Multispectral data were often used, applying pixel-based, object-oriented, and other special classification methods [Král, 2009;Atkinson and Treitz, 2012;Moody et al, 2014;Reese et al, 2014;Virtanen and Ek, 2014]. Time series of imagery from satellite and aircraft platforms was employed by Lin et al [2012].…”

Change detection in Arctic satellite imagery using clustering of sparse approximations (CoSA) over learned feature dictionaries

“…In [15,16] we showed results from one of the most widely used remote-sensing software packages, the ENvironment for Visualizing Imagery (ENVI), distributed by Exelis Visual Information Solutions out of Boulder, Colorado. We also showed some CoSA land cover classification results for the July Barrow control image in [15,16], using features learned both from multispectral data, as well as normalized band difference data. In [27] we also included preliminary land cover results on the August image.…”

“…In [27] we also included preliminary land cover results on the August image. In this paper, we will focus on normalized band difference analysis, summarized below, which seemed to provide the most separable classification labels according to our self-defined metric [16], and at a reduced computational cost.…”

“…The CoSA algorithm is derived from previous work, and was first introduced and demonstrated on a selected dataset in [13,14]. Here we focus on a particular Arctic ecosystem study area, and pre-process the satellite imagery into normalized band difference index data, which is a novel approach we introduced in [15,16]. A modified Hebbian rule is then used to learn multiresolution dictionaries directly from the index data.…”