Synergy of hyperspectral and microwave remote sensing data to derive bio- and geo-physical parameters for land applications

Retrieval of bio/geophysical variables from remote sensing imagery is an important research field. Due to the development and availability of different EO satellites, especially the ones with hyperspectral sensors, the combined use of radar and optical images is expected to provide the chance for better, more reliable and continuous retrieval of land parameters and to improve the accuracy of retrieval algorithms due to the combined use of complementary observation principles. Synergy of optical and radar data became a challenging task in Remote Sensing. This thesis addresses some of its main aspects. To this aim the thesis has several goals to reach: i) To develop and to evaluate possible strategies for integrating different data types, with the special focus on radar and optical data synergy, and to quantify the added value of their integration. For achieving this goal one of the specific objectives is to develop an algorithm which allows retrieval of land parameters by exclusively using optical, radar and one (or few) different strategies for combining optical and radar images; ii) To study challenges in land parameters retrieval in different environmental conditions. The focus is put on crop fields and on mountain grassland: iii) To provide a detailed description of the target observed from the remote sensor at radar frequencies and to adapt (or to develop) models to simulate the interactions of the radar signal with the area of interest. Based on direct models that predict radar response the retrieval algorithms need to be developed. These inverse methods should be able to use a physical description and the knowledge obtained with the direct models. This thesis focuses on parameter retrieval at the field scale. Since in microwave domain only SAR is able to monitor soil and vegetation proprieties and their variability down to the field scale, SAR data are used in all analyses presented. The special focus is put on soil moisture retrieval. Soil moisture is an Essential Climate Variable which retrieval is very complex and often an ill-posed problem. Estimation of vegetation height and leaf area index is also addressed. The work carried out in this thesis is oriented in developing innovative and improved estimation strategies that can overcome the limitations of the existing methodologies. In particular, the following main novelties are proposed in this dissertation: i) Estimation of soil moisture and vegetation height from hyperspectral imagery with machine learning method, SVR; ii) Soil moisture retrieval in crops by joining SAR discrete radiative transfer model and kernel algorithm. Tor Vergata RTM is used as a direct model to simulate the radar response and to train SVR. The method is evaluated on real radar images; iii) Soil moisture retrieval in Alpine grassland with synergy of optical and SAR images using GPR trained by model simulations. Vegetation parameters in the RTM are extracted from optical images. One temporal dataset is used to calibrate some model parameters and to train GPR, and another to test the algorithm performance; iv)Synergy of multi-sensor observations in soil moisture retrieval in mountain areas with GPR. The retrieval is based on the inference of an experimental model from measured reference samples. For all addressed topics in this thesis, both qualitative and quantitative analysis of results achieved on sensor acquired images verify the good performances and robustness of the proposed techniques.

Rate allocation and optimized decoding in inter-session network coding

Eirina Bourtsoulatze

Recent advances in data processing and communication systems have led to a continuous increase in the amount of data communicated over today’s networks. These large volumes of data pose new challenges on the current networking infrastructure that only offers a best effort mechanism for data delivery. The emergence of new distributed network architectures, such as peer-to-peer networks and wireless mesh networks, and the need for efficient data delivery mechanisms have motivated researchers to reconsider the way that information is communicated and processed in the networks. This has given rise to a new research field called network coding. The network coding paradigm departs from the traditional routing principle where information is simply relayed by the network nodes towards the destination, and introduces some intelligence in the network through coding at the intermediate nodes. This in-network data processing has been proved to substantially improve the performance of data delivery systems in terms of throughput and error resilience in networks with high path diversity. Motivated by the promising results in the network coding research, we focus in this thesis on the design of network coding algorithms for simultaneous transmission of multiple data sources in overlay networks. We investigate several problems that arise in the context of inter-session network coding, namely (i) decoding delay minimization in inter-session network coding, (ii) distributed rate allocation for inter-session network coding and (iii) correlation-aware decoding of incomplete network coded data. We start by proposing a novel framework for data delivery from multiple sources to multiple clients in an overlay wireline network, where intermediate nodes employ randomized inter-session network coding. We consider networks with high resource diversity, which creates network coding opportunities with possibly large gains in terms of throughput, delay and error robustness. However, the coding operations in the intermediate nodes must be carefully designed in order to enable efficient data delivery. We look at the problem from the decoding delay perspective and design solutions that lead to a small decoding delay at clients through proper coding and rate allocation. We cast the optimization problem as a rate allocation problem, which seeks for the coding operations that minimize the average decoding delay in the client population. We demonstrate the validity of our algorithm through simulations in representative network topologies. The results show that an effective combination of intra- and inter-session network coding based on randomized linear coding permits to reach small decoding delays and to better exploit the available network resources even in challenging network settings. Next, we design a distributed rate allocation algorithm where the users decide locally how many intra- and inter-session network coded packets should be requested from the parent nodes in order to get minimal decoding delay. The capability to take coding decisions locally with only a partial knowledge of the network statistics is of crucial importance for applications where users are organized in dynamic overlay networks. We propose a receiver-driven communication protocol that operates in two rounds. First, the users request and obtain information regarding the network conditions and packet availability in their local neighborhood. Then, every user independently optimizes the rate allocation among different possible intra- and inter-session packet combinations to be requested from its parents. We also introduce the novel concept of equivalent flows, which permits to efficiently estimate the expected number of packets that are necessary for decoding and hence to simplify the rate allocation process. Experimental results indicate that our algorithm is capable of eliminating the bottlenecks and reducing the decoding delay of users with limited resources. We further investigate the application of the proposed distributed rate allocation algorithm to the transmission of video sequences and validate the performance of our system using the NS-3 simulator. The simulation results show that the proposed rate allocation algorithm is successful in improving the quality of the delivered video compared to intra-session network coding based solutions. Finally, we investigate the problem of decoding the source information from an incomplete set of network coded data with the help of source priors in a finite algebraic field. The inability to form a complete decoding system can be often caused by transmission losses or timing constraints imposed by the application. In this case, exact reconstruction of the source data by conventional algorithms such as Gaussian elimination is not feasible; however, partial recovery of the source data may still be possible, which can be useful in applications where approximate reconstruction is informative. We use the statistical characteristics of the source data in order to perform approximate decoding. We first analyze the performance of a hypothetical maximum a posteriori decoder, which recovers the source data from an incomplete set of network coded data given the joint statistics of the sources. We derive an upper bound on the probability of erroneous source sequence decoding as a function of the system parameters. We then propose a constructive solution to the approximate decoding problem and design an iterative decoding algorithm based on message passing, which jointly considers the network coding and the correlation constraints. We illustrate the performance of our decoding algorithm through extensive simulations on synthetic and real data sets. The results demonstrate that, even by using a simple correlation model expressed as a correlation noise between pairs of sources, the original source data can be partially decoded in practice from an incomplete set of network coded symbols. Overall, this thesis addresses several important issues related to the design of efficient data delivery methods with inter-session network coding. Our novel framework for decoding delay minimization can impact the development of practical inter-session network coding algorithms that are appropriate for applications with low delay requirements. Our rate allocation algorithms are able to exploit the high resource diversity of modern networking systems and represent an effective alternative in the development of distributed communication systems. Finally, our algorithm for data recovery from incomplete network coded data using correlation priors can contribute significantly to the improvement of the delivered data quality and provide new insights towards the design of joint source and network coding algorithms.

EPFL2013

Joint image registration and reconstruction from compressed multi-view measurements

Gilles Puy, Pierre Vandergheynst

We present a method for joint reconstruction of a set of images representing a given scene from few multi-view measurements obtained by compressed sensing. We model the correlation between measurements using global geometric transformations represented by few parameters. Then, we propose an algorithm able to jointly estimate these transformation parameters and the observed images from the available measurements. This method is also robust to occlusions appearing in the scene. The reconstruction algorithm minimizes a non-convex functional and generates a sequence of estimates converging to a critical point of this functional. Finally, we demonstrate the efficiency of the proposed method using numerical simulations.

Spie-Int Soc Optical Engineering2013

Joint image registration and reconstruction from compressed multi-view measurements

Gilles Puy, Pierre Vandergheynst

We present a method for joint reconstruction of a set of images representing a given scene from few multi-view measurements obtained by compressed sensing. We model the correlation between measurements using global geometric transformations represented by few parameters. Then, we propose an algorithm able to jointly estimate these transformation parameters and the observed images from the available measurements. This method is also robust to occlusions appearing in the scene. The reconstruction algorithm minimizes a non-convex functional and generates a. sequence of estimates converging to a critical point of this functional. Finally, we demonstrate the efficiency of the proposed method using numerical simulations.

Spie-Int Soc Optical Engineering2013

Rate allocation and optimized decoding in inter-session network coding

Eirina Bourtsoulatze

EPFL2013