Luyan Ji

Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data

We have produced the first 30 m resolution global land-cover maps using Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) data. We have classified over 6600 scenes of Landsat TM data after 2006, and over 2300 scenes of Landsat TM and ETM+ data before 2006, all selected from the green season. These images cover most of the worlds land surface except Antarctica and Greenland. Most of these images came from the United States Geological Survey in level L1T (orthorectified). Four classifiers that were freely available were employed, including the conventional maximum likelihood classifier (MLC), J4.8 decision tree classifier, Random Forest (RF) classifier and support vector machine (SVM) classifier. A total of 91,433 training samples were collected by traversing each scene and finding the most representative and homogeneous samples. A total of 38,664 test samples were collected at preset, fixed locations based on a globally systematic unaligned sampling strategy. Two software tools, Global Analyst and Global Mapper developed by extending the functionality of Google Earth, were used in developing the training and test sample databases by referencing the Moderate Resolution Imaging Spectroradiometer enhanced vegetation index (MODIS EVI) time series for 2010 and high resolution images from Google Earth. A unique land-cover classification system was developed that can be crosswalked to the existing United Nations Food and Agriculture Organization (FAO) land-cover classification system as well as the International Geosphere-Biosphere Programme (IGBP) system. Using the four classification algorithms, we obtained the initial set of global land-cover maps. The SVM produced the highest overall classification accuracy (OCA) of 64.9% assessed with our test samples, with RF (59.8%), J4.8 (57.9%), and MLC (53.9%) ranked from the second to the fourth. We also estimated the OCAs using a subset of our test samples (8629) each of which represented a homogeneous area greater than 500 m × 500 m. Using this subset, we found the OCA for the SVM to be 71.5%. As a consistent source for estimating the coverage of global land-cover types in the world, estimation from the test samples shows that only 6.90% of the world is planted for agricultural production. The total area of cropland is 11.51% if unplanted croplands are included. The forests, grasslands, and shrublands cover 28.35%, 13.37%, and 11.49% of the world, respectively. The impervious surface covers only 0.66% of the world. Inland waterbodies, barren lands, and snow and ice cover 3.56%, 16.51%, and 12.81% of the world, respectively.

A Fast Volume-Gradient-Based Band Selection Method for Hyperspectral Image

In this paper, a subtle relationship is found between the volume of a subsimplex and the volume gradient of a simplex with respect to hyperspectral images. By using this relationship, we propose an efficient band selection method, namely, the volume-gradient-based band selection (VGBS) method. The VGBS method is an unsupervised method, which tries to remove the most redundant band successively. Interestingly, the VGBS method can find the most redundant band based only on the gradient of volume instead of calculating the volumes of all subsimplexes. Experiments on simulated and real hyperspectral data verify the efficiency of the proposed method.

A New Band Selection Method for Hyperspectral Image Based on Data Quality

Most unsupervised band selection methods take the information of bands into account, but few of them pay attention to the quality of bands. In this paper, by combining idea of noiseadjusted principal components (NAPCs) with a state-of-art band selection method [maximum determinant of covariance matrix (MDCM)], we define a new index to quantitatively measure the quality of the hyperspectral data cube. Both signal-to-noise ratios (SNRs) and correlation of bands are simultaneously considered in . Based on the new index defined in this article, we propose an unsupervised band selection method called minimum noise band selection (MNBS). Taking the quality (Q) of the data cube as selection criterion, MNBS tries to find the bands with both high SNRs and low correlation (high ). The subset selection method, sequential backward selection (SBS), is used in MNBS to improve the search efficiency. Some comparative experiments based on simulated as well as real hyperspectral data are conducted to evaluate the performance of MNBS in this study. The experimental results show that the bands selected by MNBS are always more effective than those selected by other methods in terms of classification.

Exemplar Component Analysis: A Fast Band Selection Method for Hyperspectral Imagery

How to find the representative bands is a key issue in band selection for hyperspectral data. Very often, unsupervised band selection is associated with data clustering, and the cluster centers (or exemplars) are considered ideal representatives. However, partitioning the bands into clusters may be very time-consuming and affected by the distribution of the data points. In this letter, we propose a new band selection method, i.e., exemplar component analysis (ECA), aiming at selecting the exemplars of bands. Interestingly, ECA does not involve actual clustering. Instead, it prioritizes the bands according to their exemplar score, which is an easy-to-compute indicator defined in this letter measuring the possibility of bands to be exemplars. As a result, ECA is of high efficiency and immune to distribution structures of the data. The experiments on real hyperspectral data set demonstrate that ECA is an effective and efficient band selection method.

A new research paradigm for global land cover mapping

ABSTRACT In this paper, we introduced major challenges in mapping croplands, settlements, water and wetlands, and discussed challenges in the use of multi-temporal and multi-sensor data. We then summarized some of the on-going efforts in improving qualities of global land cover maps. Existing technologies provide sufficient data for better map making if extra efforts can be made instead of harmonizing and integrating various global land cover products. Developing and selecting better algorithms, including more input variables (new types of data or features) for classification, having representative training samples are among conventional measures generally believed effective in improving mapping accuracies at local scales. We pointed out that data were more important in improving mapping accuracies than algorithms. Finally, we proposed a new paradigm for global land cover mapping, which included a view of vegetation classes based on their types and form, canopy cover and height. The new paradigm suggests that a universally applicable training sample set is not only possible but also effective in improving land cover classification at the continental and global scales. To ensure an easy transition from traditional land cover mapping to the new paradigm, we recommended that an all-in-one data management and analysis system be constructed.

A New Sparsity-Based Band Selection Method for Target Detection of Hyperspectral Image

Band selection (BS) plays an important role in the dimensionality reduction of hyperspectral data. However, as to the existing BS methods, few are specially designed for target detection. In this letter, we combine the target detection and BS process together and put forward a new BS method for target detection, named least absolute shrinkage and selection operator (LASSO)-based BS (LBS). Interestingly, by using a linear regression model with L1 regularization (LASSO model), LBS transforms the discrete BS problem into the continuous optimization problem, which cannot only avoid the complicated subset selection process but also evaluate the importance of all the bands simultaneously. The experiments on real hyperspectral data demonstrate that LBS is a very effective BS method for target detection.

CEM: More Bands, Better Performance

Target detection has recently drawn considerable interest in hyperspectral image processing. People tend to exclude corrupted or badly damaged bands before applying the target detection algorithm to the data for better detection results. In this letter, it is proved that adding any band independent of the original image, even a noisy band, would be always beneficial to the performance of constrained energy minimization in terms of output energy. Finally, several tests are conducted to further justify our viewpoint.

A New Endmember Generation Algorithm Based on a Geometric Optimization Model for Hyperspectral Images

This letter presents a new endmember generation method, which is called the geometric optimization model (GOM). The algorithm exploits the following fact: an L-dimensional (L-D) simplex can be divided into L + 1 L-D smaller simplexes by any point within the simplex, and the sum of the volumes of the L + 1 smaller simplexes is equal to the volume of the simplex. Based on this geometrical property, we propose a new objective function for endmember generation, whose variable only includes the mixing matrix. As a result, all the problems caused by the abundance matrix can be avoided. Experiments using both simulated and real hyperspectral data show that the GOM is effective in searching the optimal solution.

A High-Order Statistical Tensor Based Algorithm for Anomaly Detection in Hyperspectral Imagery

Recently, high-order statistics have received more and more interest in the field of hyperspectral anomaly detection. However, most of the existing high-order statistics based anomaly detection methods require stepwise iterations since they are the direct applications of blind source separation. Moreover, these methods usually produce multiple detection maps rather than a single anomaly distribution image. In this study, we exploit the concept of coskewness tensor and propose a new anomaly detection method, which is called COSD (coskewness detector). COSD does not need iteration and can produce single detection map. The experiments based on both simulated and real hyperspectral data sets verify the effectiveness of our algorithm.

Improving the Accuracy of the Water Surface Cover Type in the 30 m FROM-GLC Product

The finer resolution observation and monitoring of the global land cover (FROM-GLC) product makes it the first 30 m resolution global land cover product from which one can extract a global water mask. However, two major types of misclassification exist with this product due to spectral similarity and spectral mixing. Mountain and cloud shadows are often incorrectly classified as water since they both have very low reflectance, while more water pixels at the boundaries of water bodies tend to be misclassified as land. In this paper, we aim to improve the accuracy of the 30 m FROM-GLC water mask by addressing those two types of errors. For the first, we adopt an object-based method by computing the topographical feature, spectral feature, and geometrical relation with cloud for every water object in the FROM-GLC water mask, and set specific rules to determine whether a water object is misclassified. For the second, we perform a local spectral unmixing using a two-endmember linear mixing model for each pixel falling in the water-land boundary zone that is 8-neighborhood connected to water-land boundary pixels. Those pixels with big enough water fractions are determined as water. The procedure is automatic. Experimental results show that the total area of inland water has been decreased by 15.83% in the new global water mask compared with the FROM-GLC water mask. Specifically, more than 30% of the FROM-GLC water objects have been relabeled as shadows, and nearly 8% of land pixels in the water-land boundary zone have been relabeled as water, whereas, on the contrary, fewer than 2% of water pixels in the same zone have been relabeled as land. As a result, both the user’s accuracy and Kappa coefficient of the new water mask (UA = 88.39%, Kappa = 0.87) have been substantially increased compared with those of the FROM-GLC product (UA = 81.97%, Kappa = 0.81).