http://www.geog.ucl.ac.uk/~mdisney/teaching/PPRS/papers/foody.pdf

Status of land cover classification accuracy assessment

Timely and accurate change detection of Earth's surface features is extremely important for understanding relationships and interactions between human and natural phenomena in order to promote better decision making. Remote sensing data are primary sources extensively used for change detection in recent decades. Many change detection techniques have been developed. This paper summarizes and reviews these techniques. Previous literature has shown that image differencing, principal component analysis and post-classification comparison are the most common methods used for change detection. In recent years, spectral mixture analysis, artificial neural networks and integration of geographical information system and remote sensing data have become important techniques for change detection applications. Different change detection algorithms have their own merits and no single approach is optimal and applicable to all cases. In practice, different algorithms are often compared to find the best change detection results for a specific application. Research of change detection techniques is still an active topic and new techniques are needed to effectively use the increasingly diverse and complex remotely sensed data available or projected to be soon available from satellite and airborne sensors. This paper is a comprehensive exploration of all the major change detection approaches implemented as found in the literature.

/pdf/change-detection-techniques-4g34rgajio.pdf

Change detection techniques

Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image-processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non-parametric classifiers such as neural network, decision tree classifier, and knowledge-based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image-processing chain to improve classification accuracy.

/pdf/a-survey-of-image-classification-methods-and-techniques-for-5bc5ltr9dq.pdf

A survey of image classification methods and techniques for improving classification performance

https://www.clw.csiro.au/aclep/documents/McBratney%20et%20al.%202003.pdf

On digital soil mapping

Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning.

In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

An assessment of the effectiveness of a random forest classifier for land-cover classification

Introduction Why Accuracy Assessment? Overview Historical Review Aerial Photography Digital Assessments Data Collection Considerations Classification Scheme Statistical Considerations Data Distribution Randomness Spatial Autocorrelation Sample Size Sampling Scheme Sample Unit Reference Data Collection Basic Collection Forms Basic Analysis Techniques Non-Site Specific Assessments Site Specific Assessments Area Estimation/Correction Practicals Impact of Sample Design on Cost Recommendations for Collecting Reference Data ASources of Variation in Reference Data Photo Interpretation vs. Ground Visitation Interpreter Variability Observations vs. Measurements What is Correct? Labeling Map vs. Labeling the Reference Data Qualitative vs. Quantitative Analysis Local vs. Regional vs. Global Assessments Advanced Topics Beyond the Error Matrix Modifying the Error Matrix Fuzzy Set Theory Measuring Variability Complex Data Sets Change Detection Multi-Layer Assessments California Hardwood Rangeland Monitoring Project Case Study Balancing Statistical Validity with Practical Reality Bibliography

Assessing the accuracy of remotely sensed data : principles and practices

The need for assessing the accuracy of spatial data derived from remote sensing techniques and used in geographic information system (GIS) analyses has been recognized as a critical component of many projects The results of this assessment are typically represented by an error matrix presenting the overall accuracy, the accuracies of each category, and the omission and commission errors This paper presents a discussion of the various sources of confusion that are represented within an error matrix Ideally, the matrix is representative of only classification error However, other factors can be significant and substantially lower the accuracy as represented by the matrix An example is presented from mapping old growth forests on the Rogue River National Forest in Oregon

A practical look at the sources of confusion in error matrix generation

A process for integrating remote sensing and spatial data analysis to accurately map and monitor agricultural crops and other land cover in the Lower Colorado River Basin is described. These maps were then used as input into a model that accounts for consumptive use throughout the basin. Water is an important and incredibly valuable resource in this area. International treaties and court decrees dictate water allocation to the states of Arizona, Nevada, and California, and to Mexico. Maps of the agricultural crops with a required overall accuracy of 93 percent for use in the water model were generated from Landsat Thematic Mapper data four times per year. An automated signature extraction process and data exploration techniques were developed to aid in achieving these required accuracies. A11 maps were subjected to quantitative accuracy assessment, and error matrices were produced to evaluate overall and per-class accuracies.

Mapping and Monitoring Agricultural Crops and Other Land Cover in the Lower Colorado River Basin

This project incorporated the use of remotely sensed data to produce a GIS database and map of old growth forest lands on National Forest and Park lands in Oregon and Washington. The GIS layers include slope, aspect, elevation, hydrology, location of research and inventory plots, crown closure, size class/stand structure, species, current vegetation type polygons, suitable spotted owl habitat, suitable lands for timber production, flight line maps, habitat conservation areas, forest boundaries, potential Pacific yew habitat, historical distribution of vegetation, and old growth. The mapping was performed using field measurements, aerial photography, and Landsat Thematic Mapper satellite data []

Kass Green

Papers

Assessing the accuracy of remotely sensed data : principles and practices

A practical look at the sources of confusion in error matrix generation

Mapping and Monitoring Agricultural Crops and Other Land Cover in the Lower Colorado River Basin

Mapping old growth forests on National Forest and Park Lands in the Pacific Northwest from remotely sensed data

FIRE! Using GIS to Predict Fire Behavior