We present a novel lossless (reversible) data-embedding technique, which enables the exact recovery of the original host signal upon extraction of the embedded information. A generalization of the well-known least significant bit (LSB) modification is proposed as the data-embedding method, which introduces additional operating points on the capacity-distortion curve. Lossless recovery of the original is achieved by compressing portions of the signal that are susceptible to embedding distortion and transmitting these compressed descriptions as a part of the embedded payload. A prediction-based conditional entropy coder which utilizes unaltered portions of the host signal as side-information improves the compression efficiency and, thus, the lossless data-embedding capacity.

No abstract

No abstract

In recent years, the acquisition of image and video information for processing, analysis, understanding, and exploitation of the underlying content in various applications, ranging from remote sensing to biomedical imaging, has grown at an unprecedented rate. Analysis by human observers is quite laborious, tiresome, and time consuming, if not infeasible, given the large and continuously rising volume of data. Hence the need for systems capable of automatically and effectively analyzing the aforementioned imagery for a variety of uses that span the spectrum from homeland security to elderly care. In order to achieve the above, tools such as image segmentation provide the appropriate foundation for expediting and improving the effectiveness of subsequent high-level tasks by providing a condensed and pertinent representation of image information. We provide a comprehensive survey of color image segmentation strategies adopted over the last decade, though notable contributions in the gray scale domain will also be discussed. Our taxonomy of segmentation techniques is sampled from a wide spectrum of spatially blind (or feature-based) approaches such as clustering and histogram thresholding as well as spatially guided (or spatial domain-based) methods such as region growing/splitting/merging, energy-driven parametric/geometric active contours, supervised/unsupervised graph cuts, and watersheds, to name a few. In addition, qualitative and quantitative results of prominent algorithms on several images from the Berkeley segmentation dataset are shown in order to furnish a fair indication of the current quality of the state of the art. Finally, we provide a brief discussion on our current perspective of the field as well as its associated future trends.

No abstract

Image segmentation is a fundamental task in many computer vision applications. In this paper, we propose a new unsupervised color image segmentation algorithm, which exploits the information obtained from detecting edges in color images in the CIE L *a *b * color space. To this effect, by using a color gradient detection technique, pixels without edges are clustered and labeled individually to identify some initial portion of the input image content. Elements that contain higher gradient densities are included by the dynamic generation of clusters as the algorithm progresses. Texture modeling is performed by color quantization and local entropy computation of the quantized image. The obtained texture and color information along with a region growth map consisting of all fully grown regions are used to perform a unique multiresolution merging procedure to blend regions with similar characteristics. Experimental results obtained in comparison to published segmentation techniques demonstrate the performance advantages of the proposed method.

In this paper, we present a convolutional neural network (CNN)-based method to efficiently combine information from multisensor remotely sensed images for pixel-wise semantic classification. The CNN features obtained from multiple spectral bands are fused at the initial layers of deep neural networks as opposed to final layers. The early fusion architecture has fewer parameters and thereby reduces the computational time and GPU memory during training and inference. We also propose a composite fusion architecture that fuses features throughout the network. The methods were validated on four different datasets: ISPRS Potsdam, Vaihingen, IEEE Zeebruges and Sentinel-1, Sentinel-2 dataset. For the Sentinel-1,-2 datasets, we obtain the ground truth labels for three classes from OpenStreetMap. Results on all the images show early fusion, specifically after layer three of the network, achieves results similar to or better than a decision level fusion mechanism. The performance of the proposed architecture is also on par with the state-of-the-art results.

Remotely sensed infrared images are often used to assess wildland fire conditions. Separately, fire propagation models are in use to forecast future conditions. In the Dynamic Data Driven Application System (DDDAS) concept, the fire propagation model will react to the image data, which should produce more accurate predictions of fire propagation. In this study we describe a series of image processing tools that can be used to extract fire propagation parameters from multispectral infrared images so that the parameters can be used to drive a fire propagation model built upon the DDDAS concept. The method is capable of automatically determining the fire perimeter, active fire line, and fire propagation direction. A multi-band image gradient calculation, the Normalized Difference Vegetation Index, and the Normalized Difference Burn Ratio along with several standard image processing techniques are used to identify and constrain the fire propagation parameters. These fire propagation parameters can potentially be used within the DDDAS modeling framework for model update and adjustment.