A Semiautomated Probabilistic Framework for Tree-Cover Delineation From 1-m NAIP Imagery Using a High-Performance Computing Architecture

Basu, Supratim; Ganguly, Sangram; Nemani, Ramakrishna R.; Mukhopadhyay, Supratik; Zhang, Gong; Milesi, C.; Michaelis, Andrew; Votava, P.; Dubayah, R.; Duncanson, Laura; Cook, Bruce D.; Yu, Yifan; Saatchi, Sassan; DiBiano, Robert; Manohar, Krishpersad; Boyda, Edward; Kumar, Uttam; Li, Shuang

doi:10.1109/tgrs.2015.2428197

Cited by 43 publications

(38 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Deep Neural Networks are trained by stacking -1) Restricted Boltzmann Machines (RBM) and 2) Denoising Autoencoders (SDAE). Both the models are then discriminatively 4 Note that we extract n×n sliding window blocks from the various texture datasets for uniformity of analysis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A theoretical analysis of Deep Neural Networks for texture classification

Basu

Manohar

Mukhopadhyay

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity.

show abstract

Section: Methodsmentioning

confidence: 99%

“…These features have also been shown to useful descriptors for aerial imagery datasets ( [3], [4]). For n×n images with κ color levels, the following results can be derived 2 .…”

Section: Sample Complexity Of Haralick Features and The Fat-shatterinmentioning

confidence: 99%

A theoretical analysis of Deep Neural Networks for texture classification

Basu

Manohar

Mukhopadhyay

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The future extension of this study will include (i) analysis of the models with MODIS data that may reveal additional differences between the algorithm's performance; and (ii) use of S-V-D abundance maps for the classification of other spatial features such as buildings, highways, crop types, etc. The fractional LC maps can also be used as an input to ensemble classifiers such as deep learning frameworks [63,64] to further improve the classification accuracy.…”

Section: Subpixel Land Cover Classificationmentioning

confidence: 99%

Exploring Subpixel Learning Algorithms for Estimating Global Land Cover Fractions from Satellite Data Using High Performance Computing

et al. 2017

Self Cite

View full text Add to dashboard Cite

Land cover (LC) refers to the physical and biological cover present over the Earth's surface in terms of the natural environment such as vegetation, water, bare soil, etc. Most LC features occur at finer spatial scales compared to the resolution of primary remote sensing satellites. Therefore, observed data are a mixture of spectral signatures of two or more LC features resulting in mixed pixels. One solution to the mixed pixel problem is the use of subpixel learning algorithms to disintegrate the pixel spectrum into its constituent spectra. Despite the popularity and existing research conducted on the topic, the most appropriate approach is still under debate. As an attempt to address this question, we compared the performance of several subpixel learning algorithms based on least squares, sparse regression, signal-subspace and geometrical methods. Analysis of the results obtained through computer-simulated and Landsat data indicated that fully constrained least squares (FCLS) outperformed the other techniques. Further, FCLS was used to unmix global Web-Enabled Landsat Data to obtain abundances of substrate (S), vegetation (V) and dark object (D) classes. Due to the sheer nature of data and computational needs, we leveraged the NASA Earth Exchange (NEX) high-performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into four classes, namely forest, farmland, water and urban areas (in conjunction with nighttime lights data) over California, USA using a random forest classifier. Validation of these LC maps with the National Land Cover Database 2011 products and North American Forest Dynamics static forest map shows a 6% improvement in unmixing-based classification relative to per-pixel classification. As such, abundance maps continue to offer a useful alternative to high-spatial-resolution classified maps for forest inventory analysis, multi-class mapping, multi-temporal trend analysis, etc.

show abstract

“…In forest management, land cover classifications are frequently used to inform management activities such as timber harvest [6], forest restoration [7], fire risk mitigation [8], and preservation of rare habitats [9]. From land cover classification datasets, relevant objectives such as locating forested and non-forested areas [10] or determining the proportion of impervious surface occupying landscape [11] can be quickly addressed. Land cover classifications can also be used as a component of more complex analyses of landscape characteristics [12] and can be used to describe important characteristics of forest and woodland ecosystems, such as percent canopy cover, understory composition within open forests, and the degree of fragmentation.…”

Section: Introductionmentioning

confidence: 99%

“…Alternative classification methodologies such as object-orient classifiers have also received attention recently [20]. There has been less focus on addressing the limitations of applying these classification techniques to fine resolution imagery across large extents, with a few notable exceptions [10,21,22].…”

Section: Introductionmentioning

confidence: 99%

Fine Resolution Probabilistic Land Cover Classification of Landscapes in the Southeastern United States

Peter

Hogland

Anderson

et al. 2018

IJGI

View full text Add to dashboard Cite

Abstract:Land cover classification provides valuable information for prioritizing management and conservation operations across large landscapes. Current regional scale land cover geospatial products within the United States have a spatial resolution that is too coarse to provide the necessary information for operations at the local and project scales. This paper describes a methodology that uses recent advances in spatial analysis software to create a land cover classification over a large region in the southeastern United States at a fine (1 m) spatial resolution. This methodology used image texture metrics and principle components derived from National Agriculture Imagery Program (NAIP) aerial photographic imagery, visually classified locations, and a softmax neural network model. The model efficiently produced classification surfaces at 1 m resolution across roughly 11.6 million hectares (28.8 million acres) with less than 10% average error in modeled probability. The classification surfaces consist of probability estimates of 13 visually distinct classes for each 1 m cell across the study area. This methodology and the tools used in this study constitute a highly flexible fine resolution land cover classification that can be applied across large extents using standard computer hardware, common and open source software and publicly available imagery.

show abstract

A Semiautomated Probabilistic Framework for Tree-Cover Delineation From 1-m NAIP Imagery Using a High-Performance Computing Architecture

Cited by 43 publications

References 35 publications

A theoretical analysis of Deep Neural Networks for texture classification

A theoretical analysis of Deep Neural Networks for texture classification

Exploring Subpixel Learning Algorithms for Estimating Global Land Cover Fractions from Satellite Data Using High Performance Computing

Fine Resolution Probabilistic Land Cover Classification of Landscapes in the Southeastern United States

Contact Info

Product

Resources

About