Signal and Image Processing for Remote Sensing

Abstract

Spatial information plays a very important role in high-level image understanding tasks. Contextual models that exploit spatial information through the quantification of region spatial relationships can be used for resolving the uncertainties in low-level features used for image classification and object detection. We describe intuitive, flexible and efficient methods for modeling pairwise directional spatial relationships and the ternary between relationship using fuzzy mathematical morphology. These methods define a fuzzy landscape where each image point is assigned a value that quantifies its relative position with respect to the reference object(s) and the type of the relationship. Directional mathematical dilation with fuzzy structuring elements is used to compute this landscape. We provide flexible definitions of fuzzy structuring elements that are tunable along both radial and angular dimensions. Examples using synthetic images show that our models produce more intuitive results than the competitors. We also illustrate the use of the models described in this chapter as spatial contextual constraints for two image analysis tasks. First, we show how these spatial relationships can be incorporated into a Bayesian classification framework for land cover classification to reduce the amount of commission among spectrally similar classes. Then, we show how the use of spatial constraints derived from shadow regions improves building detection accuracy. The significant improvement in accuracy in these applications confirms the importance of spatial information and the effectiveness of the relationship models described in this chapter in modeling and quantifying this information.

An Integrated Method for Simulation of Synthetic Aperture Radar (SAR) Raw Data in Moving Target Detection

“…The IOK method has an interpolation step that is not perfectly inverted of the direct method and some errors appear in the final data [26]. IPFA and IRD methods also contain interpolation processes whose computational load is very high [26].…”

Fast and Efficient Satellite Imagery Fusion Using DT-CWT Proportional and Wavelet Zero-Padding

“…Conversely, if and only if the highest spatial resolution is obtained whenever no spectral diversity is required (Chen, 2012), the image fusion or the pan-sharpening aims to improve the geometric information of the original LRM image. However, we cannot obtain an ideal HRM image due to the abovementioned limitation (Choi et al, 2013;Wang et al, 2005).…”

An Advanced Neural Network-Based Approach for Military Ground Vehicle Recognition in Sar Aerial Imagery

“…A typical target recognition system consists of a detection module (filtering and segmentation) and a recognition module (feature selection and classification) [1]. Moreover, the speckle noise specific to SAR images makes segmentation and recognition difficult tasks [2], [6]. We further propose application and development of new and challenging neural network models both for target detection (filtering and segmentation) and also for classification tasks.…”

“…Radar imagery brings the advantage of independence from a passive illumination source, such as sunlight or starlight, thus offers imaging capability at night and through clouds. Modern day radar imaging systems are capable of comparatively high resolution by using synthetic aperture radar (SAR) imagery [2]. The area of Automatic Target Recognition (ATR) for SAR imagery is an ongoing research in many branches of the military and large research institutions [6], [7], [16], [17], [20].…”

“…The area of Automatic Target Recognition (ATR) for SAR imagery is an ongoing research in many branches of the military and large research institutions [6], [7], [16], [17], [20]. On the other side, there has been an increasing interest in using artificial neural networks (ANN) for image processing and pattern recognition [1], [2], [7], [11], [12], [13], [14], [15], [17]. A typical target recognition system consists of a detection module (filtering and segmentation) and a recognition module (feature selection and classification) [1].…”