Change Vector Analysis using Enhanced PCA and Inverse Triangular Function-based Thresholding

Learning Pairwise Potential CRFs in Deep Siamese Network for Change Detection

Very high resolution (VHR) images change detection plays an important role in many remote sensing applications, such as military reconnaissance, urban planning and natural resource monitoring. Recently, fully connected conditional random field (FCCRF)-facilitated deep convolutional neural networks have shown promising results in change detection. However, the FCCRF in change detection currently is still postprocessing based on the output of the front-end network, which is not a convenient end-to-end network model and cannot combine front-end network knowledge with the knowledge of pairwise potential. Therefore, we propose a new end-to-end deep Siamese pairwise potential CRFs network (PPNet) for VHR images change detection. Specifically, this method adds a conditional random field recurrent neural network (CRF-RNN) unit into the convolutional neural network and integrates the knowledge of unary potential and pairwise potential in the end-to-end training process, aiming to refine the edges of changed areas and to remove the distant noise. In order to correct the front-end network identification errors, the method uses effective channel attention (ECA) to further effectively distinguish the change areas. Our experimental results on two data sets verify that the proposed method has more advanced capability with almost no increase in the number of parameters and effectively avoids the overfitting phenomenon in the training process.

Change Vector Analysis, Tasseled Cap, and NDVI-NDMI for Measuring Land Use/Cover Changes Caused by a Sudden Short-Term Severe Drought: 2011 Texas Event

Sudden short-term severe droughts have major impacts on ecosystem balance. Synoptic and replicable measurements from remotely sensed data are essential for calculating changes to land use/cover caused by severe drought conditions. In the US, Texas experienced a particularly severe drought in 2011, which adversely affected forest and grassland ecosystems in addition to $7.62 billion of agricultural loss. To assess the extent and severity of the drought we use satellite sensor data and image processing techniques to measure changes in land use/cover. Our methodology uses change vector analysis (CVA), the normalized difference vegetation index, the normalized difference moisture index, and three variables-brightness, greenness, and wetness-extracted from tasseled cap transforms (TCT). All are established techniques in remote sensing but have as yet been applied in combination to measure land use/cover changes affected by intense short-term drought conditions. Our objective is to calculate not only vegetation and bare soil indices, but also the intensity of change (magnitude) and the type of change (direction). For CVA direction, we include an improved methodology using the arctangent function based on two arguments, ATAN2 which produces results in all four possible quadrants, and complete characterization of all possible change directions. The three variables of TCT are applied to CVA magnitude and direction using vectors in three dimensions, resulting in eight change categories. Our results are based on Landsat TM sensor data for the years 2009, 2010 and 2011, which represent a short period of severe drought, above average precipitation, and severe drought respectively, for two study sites in Texas. Results indicate that land use/cover changes were affected by both an increase in precipitation in 2010 as well as a considerable decrease of precipitation in 2011 resulting in the devastating sudden drought.

Unsupervised Deep Noise Modeling for Hyperspectral Image Change Detection

Hyperspectral image (HSI) change detection plays an important role in remote sensing applications, and considerable research has been done focused on improving change detection performance. However, the high dimension of hyperspectral data makes it hard to extract discriminative features for hyperspectral processing tasks. Though deep convolutional neural networks (CNN) have superior capability in high-level semantic feature learning, it is difficult to employ CNN for change detection tasks. As a ground truth map is usually used for the evaluation of change detection algorithms, it cannot be directly used for supervised learning. In order to better extract discriminative CNN features, a novel noise modeling-based unsupervised fully convolutional network (FCN) framework is presented for HSI change detection in this paper. Specifically, the proposed method utilizes the change detection maps of existing unsupervised change detection methods to train the deep CNN, and then removes the noise during the end-to-end training process. The main contributions of this paper are threefold: (1) A new end-to-end FCN-based deep network architecture for HSI change detection is presented with powerful learning features; (2) An unsupervised noise modeling method is introduced for the robust training of the proposed deep network; (3) Experimental results on three datasets confirm the effectiveness of the proposed method.

Rayleigh-Rice Mixture Parameter Estimation via EM Algorithm for Change Detection in Multispectral Images

The problem of estimating the parameters of a Rayleigh-Rice mixture density is often encountered in image analysis (e.g., remote sensing and medical image processing). In this paper, we address this general problem in the framework of change detection (CD) in multitemporal and multispectral images. One widely used approach to CD in multispectral images is based on the change vector analysis. Here, the distribution of the magnitude of the difference image can be theoretically modeled by a Rayleigh-Rice mixture density. However, given the complexity of this model, in applications, a Gaussian-mixture approximation is often considered, which may affect the CD results. In this paper, we present a novel technique for parameter estimation of the Rayleigh-Rice density that is based on a specific definition of the expectation-maximization algorithm. The proposed technique, which is characterized by good theoretical properties, iteratively updates the parameters and does not depend on specific optimization routines. Several numerical experiments on synthetic data demonstrate the effectiveness of the method, which is general and can be applied to any image processing problem involving the Rayleigh-Rice mixture density. In the CD context, the Rayleigh-Rice model (which is theoretically derived) outperforms other empirical models. Experiments on real multitemporal and multispectral remote sensing images confirm the validity of the model by returning significantly higher CD accuracies than those obtained by using the state-of-the-art approaches.