Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.

Cooperative Wireless Networks for Localization

This thesis adresses the problem of localization, and analyzes its crucial aspects, within the context of cooperative WSNs. The three main issues discussed in the following are: network synchronization, position estimate and tracking. Time synchronization is a fundamental requirement for every network. In this context, a new approach based on the estimation theory is proposed to evaluate the ultimate performance limit in network time synchronization. In particular the lower bound on the variance of the average synchronization error in a fully connected network is derived by taking into account the statistical characterization of the Message Delivering Time (MDT) . Sensor network localization algorithms estimate the locations of sensors with initially unknown location information by using knowledge of the absolute positions of a few sensors and inter-sensor measurements such as distance and bearing measurements. Concerning this issue, i.e. the position estimate problem, two main contributions are given. The first is a new Semidefinite Programming (SDP) framework to analyze and solve the problem of flip-ambiguity that afflicts range-based network localization algorithms with incomplete ranging information. The occurrence of flip-ambiguous nodes and errors due to flip ambiguity is studied, then with this information a new SDP formulation of the localization problem is built. Finally a flip-ambiguity-robust network localization algorithm is derived and its performance is studied by Monte-Carlo simulations. The second contribution in the field of position estimate is about multihop networks. A multihop network is a network with a low degree of connectivity, in which couples of given any nodes, in order to communicate, they have to rely on one or more intermediate nodes (hops). Two new distance-based source localization algorithms, highly robust to distance overestimates, typically present in multihop networks, are presented and studied. The last point of this thesis discuss a new low-complexity tracking algorithm, inspired by the Fano’s sequential decoding algorithm for the position tracking of a user in a WLAN-based indoor localization system.

Camera localization using trajectories and maps

We propose a new Bayesian framework for automatically determining the position (location and orientation) of an uncalibrated camera using the observations of moving objects and a schematic map of the passable areas of the environment. Our approach takes advantage of static and dynamic information on the scene structures through prior probability distributions for object dynamics. The proposed approach restricts plausible positions where the sensor can be located while taking into account the inherent ambiguity of the given setting. The proposed framework samples from the posterior probability distribution for the camera position via data driven MCMC, guided by an initial geometric analysis that restricts the search space. A Kullback-Leibler divergence analysis is then used that yields the final camera position estimate, while explicitly isolating ambiguous settings. The proposed approach is evaluated in synthetic and real environments, showing its satisfactory performance in both ambiguous and unambiguous settings.

Cellular mechanisms for resolving phase ambiguity in the owl's inferior colliculus

Both mammals and birds use the interaural time difference (ITD) for localization of sound in the horizontal plane. They may localize either real or phantom sound sources, when the signal consists of a narrow frequency band. This ambiguity does not occur with broadband signals. A plot of impulse rates or amplitude of excitatory postsynaptic potentials against ITDs (ITD curve) consists of peaks and troughs. In the external nucleus (ICX) of the owl's inferior colliculus, ITD curves show multiple peaks when the signal is narrow-band, such as tones. Of these peaks, one occurs at ITDi, which is independent of frequency, and others at ITDi ± T, where T is the tonal period. The ITD curve of the same neuron shows a large peak (main peak) at ITDi and no or small peaks (side peaks) at ITDi ± T, when the signal is broadband. ITD curves for postsynaptic potentials indicate that ICX neurons integrate the results of binaural cross-correlation in different frequency bands. However, the difference between the main and side peaks is small. ICX neurons further enhance this difference in the process of converting membrane potentials to impulse rates. Inhibition also appears to augment the difference between the main and side peaks.

Source localization methods

One of the most pressing demands on electrophysiology applied to the diagnosis of epilepsy is the non-invasive localization of the neuronal generators responsible for brain electrical and magnetic fields (the so-called inverse problem). These neuronal generators produce primary currents in the brain, which together with passive currents give rise to the EEG signal. Unfortunately, the signal we measure on the scalp surface doesn't directly indicate the location of the active neuronal assemblies. This is the expression of the ambiguity of the underlying static electromagnetic inverse problem, partly due to the relatively limited number of independent measures available. A given electric potential distribution recorded at the scalp can be explained by the activity of infinite different configurations of intracranial sources. In contrast, the forward problem, which consists of computing the potential field at the scalp from known source locations and strengths with known geometry and conductivity properties of the brain and its layers (CSF/meninges, skin and skull), i.e. the head model, has a unique solution. The head models vary from the computationally simpler spherical models (three or four concentric spheres) to the realistic models based on the segmentation of anatomical images obtained using magnetic resonance imaging (MRI). Realistic models – computationally intensive and difficult to implement – can separate different tissues of the head and account for the convoluted geometry of the brain and the significant inter-individual variability. In real-life applications, if the assumptions of the statistical, anatomical or functional properties of the signal and the volume in which it is generated are meaningful, a true three-dimensional tomographic representation of sources of brain electrical activity is possible in spite of the ‘ill-posed’ nature of the inverse problem (Michel et al., 2004). The techniques used to achieve this are now referred to as electrical source imaging (ESI) or magnetic source imaging (MSI). The first issue to influence reconstruction accuracy is spatial sampling, i.e. the number of EEG electrodes. It has been shown that this relationship is not linear, reaching a plateau at about 128 electrodes, provided spatial distribution is uniform. The second factor is related to the different properties of the source localization strategies used with respect to the hypothesized source configuration.

Computational approach to localization using global energy minimization

Damage localization induced by strain softening can be predicted by the direct minimization of a global energy function. This article concerns the computational strategy for implementing this principle for softening materials such as concrete. Instead of using heuristic global optimization techniques, our strategies are a hybrid of local optimization methods with a path-finding approach to ensure a global optimum. With admissible nodal displacements being independent variables, it is easy to deal with the geometric (mesh) constraint conditions. The direct search optimization methods recover the localized solutions for a range of softening lattice models which are representative of quasi-brittle structures

Extended GNSS ambiguity resolution models with regularization criterion and constraints

This paper firstly presents an extended ambiguity resolution model that deals with an ill-posed problem and constraints among the estimated parameters. In the extended model, the regularization criterion is used instead of the traditional least squares in order to estimate the float ambiguities better. The existing models can be derived from the general model. Secondly, the paper examines the existing ambiguity searching methods from four aspects: exclusion of nuisance integer candidates based on the available integer constraints; integer rounding; integer bootstrapping and integer least squares estimations. Finally, this paper systematically addresses the similarities and differences between the generalized TCAR and decorrelation methods from both theoretical and practical aspects.

Three Carrier Ambiguity Resolutions : Generalised problems, models and solutions

In this paper, the problems of three carrier phase ambiguity resolution (TCAR) and position estimation (PE) are generalized as real time GNSS data processing problems for a continuously observing network on large scale. In order to describe these problems, a general linear equation system is presented to uniform various geometry-free, geometry-based and geometry-constrained TCAR models, along with state transition questions between observation times. With this general formulation, generalized TCAR solutions are given to cover different real time GNSS data processing scenarios, and various simplified integer solutions, such as geometry-free rounding and geometry-based LAMBDA solutions with single and multiple-epoch measurements. In fact, various ambiguity resolution (AR) solutions differ in the floating ambiguity estimation and integer ambiguity search processes, but their theoretical equivalence remains under the same observational systems models and statistical assumptions. TCAR performance benefits as outlined from the data analyses in some recent literatures are reviewed, showing profound implications for the future GNSS development from both technology and application perspectives.

Automation of an underground mining vehicle using reactive navigation and opportunistic localization

This paper describes the implementation of an autonomous navigation system onto a 30 tonne Load-Haul-Dump truck. The control architecture is based on a robust reactive wall-following behaviour. To make it purposeful we provide driving hints derived from an approximate nodal-map. For most of the time, the vehicle is driven with weak localization (odometry). This need only be improved at intersections where decisions must be made - a technique we refer to as opportunistic localization. The truck has achieved full-speed autonomous operation at an artificial test mine, and subsequently, at a operational underground mine.

Robust outdoor visual localization using a three-dimensional-edge map

Visual localization systems that are practical for autonomous vehicles in outdoor industrial applications must perform reliably in a wide range of conditions. Changing outdoor conditions cause difficulty by drastically altering the information available in the camera images. To confront the problem, we have developed a visual localization system that uses a surveyed three-dimensional (3D)-edge map of permanent structures in the environment. The map has the invariant properties necessary to achieve long-term robust operation. Previous 3D-edge map localization systems usually maintain a single pose hypothesis, making it difficult to initialize without an accurate prior pose estimate and also making them susceptible to misalignment with unmapped edges detected in the camera image. A multihypothesis particle filter is employed here to perform the initialization procedure with significant uncertainty in the vehicle's initial pose. A novel observation function for the particle filter is developed and evaluated against two existing functions. The new function is shown to further improve the abilities of the particle filter to converge given a very coarse estimate of the vehicle's initial pose. An intelligent exposure control algorithm is also developed that improves the quality of the pertinent information in the image. Results gathered over an entire sunny day and also during rainy weather illustrate that the localization system can operate in a wide range of outdoor conditions. The conclusion is that an invariant map, a robust multihypothesis localization algorithm, and an intelligent exposure control algorithm all combine to enable reliable visual localization through challenging outdoor conditions.

Mapping a suburb with a single camera using a biologically inspired SLAM system

This paper describes a biologically inspired approach to vision-only simultaneous localization and mapping (SLAM) on ground-based platforms. The core SLAM system, dubbed RatSLAM, is based on computational models of the rodent hippocampus, and is coupled with a lightweight vision system that provides odometry and appearance information. RatSLAM builds a map in an online manner, driving loop closure and relocalization through sequences of familiar visual scenes. Visual ambiguity is managed by maintaining multiple competing vehicle pose estimates, while cumulative errors in odometry are corrected after loop closure by a map correction algorithm. We demonstrate the mapping performance of the system on a 66 km car journey through a complex suburban road network. Using only a web camera operating at 10 Hz, RatSLAM generates a coherent map of the entire environment at real-time speed, correctly closing more than 51 loops of up to 5 km in length.