Segmentation and recognition using structure from motion point clouds

We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3D world structure that vary with object category. We introduce features that project the 3D cues back to the 2D image plane while modeling spatial layout and context. A randomized decision forest combines many such features to achieve a coherent 2D segmentation and recognize the object categories present. Our main contribution is to show how semantic segmentation is possible based solely on motion-derived 3D world structure. Our method works well on sparse, noisy point clouds, and unlike existing approaches, does not need appearance-based descriptors. Experiments were performed on a challenging new video database containing sequences filmed from a moving car in daylight and at dusk. The results confirm that indeed, accurate segmentation and recognition are possible using only motion and 3D world structure. Further, we show that the motion-derived information complements an existing state-of-the-art appearance-based method, improving both qualitative and quantitative performance. © 2008 Springer Berlin Heidelberg.

The post-processed Galerkin method applied to non-linear shell vibrations

We present the results of a computational study of the post-processed Galerkin methods put forward by Garcia-Archilla et al. applied to the non-linear von Karman equations governing the dynamic response of a thin cylindrical panel periodically forced by a transverse point load. We spatially discretize the shell using finite differences to produce a large system of ordinary differential equations (ODEs). By analogy with spectral non-linear Galerkin methods we split this large system into a 'slowly' contracting subsystem and a 'quickly' contracting subsystem. We then compare the accuracy and efficiency of (i) ignoring the dynamics of the 'quick' system (analogous to a traditional spectral Galerkin truncation and sometimes referred to as 'subspace dynamics' in the finite element community when applied to numerical eigenvectors), (ii) slaving the dynamics of the quick system to the slow system during numerical integration (analogous to a non-linear Galerkin method), and (iii) ignoring the influence of the dynamics of the quick system on the evolution of the slow system until we require some output, when we 'lift' the variables from the slow system to the quick using the same slaving rule as in (ii). This corresponds to the post-processing of Garcia-Archilla et al. We find that method (iii) produces essentially the same accuracy as method (ii) but requires only the computational power of method (i) and is thus more efficient than either. In contrast with spectral methods, this type of finite-difference technique can be applied to irregularly shaped domains. We feel that post-processing of this form is a valuable method that can be implemented in computational schemes for a wide variety of partial differential equations (PDEs) of practical importance.

Parameters identification by a single point free response measurement

When a thin rectangular plate is restrained on the two long edges and free on the remaining edges, the equivalent stiffness of the restraining joints can be identified by the order of the natural frequencies obtained using the free response of the plate at a single location. This work presents a method to identify the equivalent stiffness of the restraining joints, being represented as simply supporting the plate but elastically restraining it in rotation. An integral transform is used to map the autospectrum of the free response from the frequency domain to the stiffness domain in order to identify the equivalent torsional stiffness of the restrained edges of the plate and also the order of natural frequencies. The kernel of the integral transform is built interpolating data from a finite element model of the plate. The method introduced in this paper can also be applied to plates or shells with different shapes and boundary conditions. © 2011 Elsevier Ltd. All rights reserved.

Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

The commercial far-range (>10 m) spatial data collection methods for acquiring infrastructure’s geometric data are not completely automated because of the necessary manual pre- and/or post-processing work. The required amount of human intervention and, in some cases, the high equipment costs associated with these methods impede their adoption by the majority of infrastructure mapping activities. This paper presents an automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras. In this process SURF features are automatically detected and matched between each pair of stereo video frames. 3D coordinates of the matched feature points are then calculated via triangulation. The detected SURF features in two successive video frames are automatically matched and the RANSAC algorithm is used to discard mismatches. The quaternion motion estimation method is then used along with bundle adjustment optimization to register successive point clouds. The method was tested on a database of infrastructure stereo video streams. The validity and statistical significance of the results were evaluated by comparing the spatial distance of randomly selected feature points with their corresponding tape measurements.

Generating the Sparse Point Cloud of a Civil Infrastructure Scene Using a Single Video Camera under Practical Constraints

Automating the model generation process of infrastructure can substantially reduce the modeling time and cost. This paper presents a method to generate a sparse point cloud of an infrastructure scene using a single video camera under practical constraints. It is the first step towards establishing an automatic framework for object-oriented as-built modeling. Motion blur and key frame selection criteria are considered. Structure from motion and bundle adjustment are explored. The method is demonstrated in a case study where the scene of a reinforced concrete bridge is videotaped, reconstructed, and metrically validated. The result indicates the applicability, efficiency, and accuracy of the proposed method.

Sparsity-Inducing Optimization Algorithm for the Extraction of Planar Structures in Noisy Point-Cloud Data

Most of the manual labor needed to create the geometric building information model (BIM) of an existing facility is spent converting raw point cloud data (PCD) to a BIM description. Automating this process would drastically reduce the modeling cost. Surface extraction from PCD is a fundamental step in this process. Compact modeling of redundant points in PCD as a set of planes leads to smaller file size and fast interactive visualization on cheap hardware. Traditional approaches for smooth surface reconstruction do not explicitly model the sparse scene structure or significantly exploit the redundancy. This paper proposes a method based on sparsity-inducing optimization to address the planar surface extraction problem. Through sparse optimization, points in PCD are segmented according to their embedded linear subspaces. Within each segmented part, plane models can be estimated. Experimental results on a typical noisy PCD demonstrate the effectiveness of the algorithm.

Calculation of point defects in rutile TiO 2 by the screened-exchange hybrid functional

The formation energies of the oxygen vacancy and titanium interstitial in rutile TiO 2 were calculated by the screened-exchange (sX) hybrid density functional method, which gives a band gap of 3.1 eV, close to the experimental value. The oxygen vacancy gives rise to a gap state lying 0.7 eV below the conduction band edge, whose charge density is localized around the two of three Ti atoms next to the vacancy. The Ti interstitial (Ti int) generates four defect states in the gap, whose unpaired electrons lie on the interstitial and the adjacent Ti 3d orbitals. The formation energy for the neutral oxygen vacancy is 1.9 eV for the O-poor chemical potential. The neutral Ti interstitial has a lower formation energy than the O vacancy under O-poor conditions. This indicates that both the O vacancy and Ti int are relevant for oxygen deficiency in rutile TiO 2 but the O vacancy will dominate under O-rich conditions. This resolves questions about defect localization and defect predominance in the literature. © 2012 American Physical Society.

Scale-invariant vote-based 3D recognition and registration from point clouds

This chapter presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transformations for the first time. We introduce a new distance between poses in this spacethe SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a (real and) challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach. © 2013 Springer-Verlag Berlin Heidelberg.

Density stratified environments: The double-tank method

We present an alternative method of producing density stratifications in the laboratory based on the 'double-tank' method proposed by Oster (Sci Am 213:70-76, 1965). We refer to Oster's method as the 'forced-drain' approach, as the volume flow rates between connecting tanks are controlled by mechanical pumps. We first determine the range of density profiles that may be established with the forced-drain approach other than the linear stratification predicted by Oster. The dimensionless density stratification is expressed analytically as a function of three ratios: the volume flow rate ratio n, the ratio of the initial liquid volumes λ and the ratio of the initial densities ψ. We then propose a method which does not require pumps to control the volume flow rates but instead allows the connecting tanks to drain freely under gravity. This is referred to as the 'free-drain' approach. We derive an expression for the density stratification produced and compare our predictions with saline stratifications established in the laboratory using the 'free-drain' extension of Oster's method. To assist in the practical application of our results we plot the region of parameter space that yield concave/convex or linear density profiles for both forced-drain and free-drain approaches. The free-drain approach allows the experimentalist to produce a broad range of density profiles by varying the initial liquid depths, cross-sectional and drain opening areas of the tanks. One advantage over the original Oster approach is that density profiles with an inflexion point can now be established. © 2008 Springer-Verlag.

A performance evaluation of volumetric 3D interest point detectors

This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the increasing prevalence of 3D shape acquisition techniques and the diminishing returns to be had from appearance alone have seen a surge in 3D shape-based methods. In this work, we investigate the performance of several state of the art interest points detectors in volumetric data, in terms of repeatability, number and nature of interest points. Such methods form the first step in many shape-based applications. Our detailed comparison, with both quantitative and qualitative measures on synthetic and real 3D data, both point-based and volumetric, aids readers in selecting a method suitable for their application. © 2012 Springer Science+Business Media, LLC.

A method for analysing operational complexity in supply chains

This paper proposes a method for analysing the operational complexity in supply chains by using an entropic measure based on information theory. The proposed approach estimates the operational complexity at each stage of the supply chain and analyses the changes between stages. In this paper a stage is identified by the exchange of data and/or material. Through analysis the method identifies the stages where the operational complexity is both generated and propagated (exported, imported, generated or absorbed). Central to the method is the identification of a reference point within the supply chain. This is where the operational complexity is at a local minimum along the data transfer stages. Such a point can be thought of as a 'sink' for turbulence generated in the supply chain. Where it exists, it has the merit of stabilising the supply chain by attenuating uncertainty. However, the location of the reference point is also a matter of choice. If the preferred location is other than the current one, this is a trigger for management action. The analysis can help decide appropriate remedial action. More generally, the approach can assist logistics management by highlighting problem areas. An industrial application is presented to demonstrate the applicability of the method. © 2013 Operational Research Society Ltd. All rights reserved.

Average corotation of line segments near a point and vortex identification

An easy-to-interpret kinematic quantity measuring the average corotation of material line segments near a point is introduced and applied to vortex identification. At a given point, the vector of average corotation of line segments is defined as the average of the instantaneous local rigid-body rotation over "all planar cross sections" passing through the examined point. The vortex-identification method based on average corotation is a one-parameter, region-type local method sensitive to the axial stretching rate as well as to the inner configuration of the velocity gradient tensor. The method is derived from a well-defined interpretation of the local flow kinematics to determine the "plane of swirling" and is also applicable to compressible and variable-density flows. Practical application to direct numerical simulation datasets includes a hairpin vortex of boundary-layer transition, the reconnection process of two Burgers vortices, a flow around an inclined flat plate, and a flow around a revolving insect wing. The results agree well with some popular local methods and perform better in regions of strong shearing. Copyright © 2013 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.

SLP: A zero-contact non-invasive method for pulmonary function testing

Structured Light Plethysmography (SLP) is a novel non-invasive method that uses structured light to perform pulmonary function testing that does not require physical contact with a patient. The technique produces an estimate of chest wall volume changes over time. A patient is observed continuously by two cameras and a known pattern of light (i.e. structured light) is projected onto the chest using an off-the-shelf projector. Corner features from the projected light pattern are extracted, tracked and brought into correspondence for both camera views over successive frames. A novel self calibration algorithm recovers the intrinsic and extrinsic camera parameters from these point correspondences. This information is used to reconstruct a surface approximation of the chest wall and several novel ideas for 'cleaning up' the reconstruction are used. The resulting volume and derived statistics (e.g. FVC, FEV) agree very well with data taken with a spirometer. © 2010. The copyright of this document resides with its authors.

Iris recognition algorithm based on point covering of high-dimensional space and neural network

In this paper, we constructed a Iris recognition algorithm based on point covering of high-dimensional space and Multi-weighted neuron of point covering of high-dimensional space, and proposed a new method for iris recognition based on point covering theory of high-dimensional space. In this method, irises are trained as "cognition" one class by one class, and it doesn't influence the original recognition knowledge for samples of the new added class. The results of experiments show the rejection rate is 98.9%, the correct cognition rate and the error rate are 95.71% and 3.5% respectively. The experimental results demonstrate that the rejection rate of test samples excluded in the training samples class is very high. It proves the proposed method for iris recognition is effective.

A new beam propagation method based on least-squares expansion approximating

A new finite difference wide-angle beam propagation method is developed by introducing the least-squares expansion approximant in the propagator expansion. In this new method it is not necessary to select the reference index point because of the whole region approaching the lease-square expansion. This method avoids the problems induced by error selection of the reference index in the old methods based on Taylor or Pade expansion. Several typical structures are simulated by the new method and the results prove the validity of it.