Application of Automatic Trajectory Basis Selection Method for Non-rigid Structure from Motion

Dense surface reconstruction from monocular image sequences — known as Non-Rigid Structure from Motion (NRSfM) — is a highly ill-posed inverse problem. The objective of NRSfM is to learn 3D shapes from 2D point tracks in an unsupervised manner. While existing methods rely on low-rank models, we propose the concept of High Dimensional Space Model (HDSM). In HDSM, time-varying geometry is encoded by a high-dimensional static structure projected into different metric subspaces. To express non-rigid deformations, instead of directly modelling in the 3D space, we gradually increase space dimensionality as the complexity of the scene increases. HDSM allows for a compact representation with deformation localisation and can be interpreted as a generalisation of the previously proposed models for NRSfM. Relying on HDSM, we develop an algorithm for dense monocular surface recovery. Experiments show that the proposed method achieves high accuracy while allowing for the fine-grained control.

Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear combination of K basis shapes; the solution is then obtained as the low-rank factorization of an input observation matrix. An important but overlooked problem with this approach is that non-linear deformations are often observed; these deformations lead to a weakened low-rank constraint due to the need to use additional basis shapes to linearly model points that move along curves. Here, we demonstrate how the kernel trick can be applied in standard NRSFM. As a result, we model complex, deformable 3D shapes as the outputs of a non-linear mapping whose inputs are points within a low-dimensional shape space. This approach is flexible and can use different kernels to build different non-linear models. Using the kernel trick, our model complements the low-rank constraint by capturing non-linear relationships in the shape coefficients of the linear model. The net effect can be seen as using non-linear dimensionality reduction to further compress the (shape) space of possible solutions.

In this paper, we present a new framework for non-rigid structure from motion (NRSFM) that simultaneously addresses three significant challenges: severe occlusion, perspective camera projection, and large non-linear deformation. We introduce a concept called a model graph, which greatly reduces the computational cost of discovering groups of input images that depict consistent 3D shapes. A 3D model is constructed for each input image by traversing the model graph along multiple evolutionary paths. A compressive shape representation is constructed, which (1) consolidates the multiple 3D models for each image reconstructed during model evolution and (2) reduces the number of models needed to represent the input image set. Assuming feature correspondences are known, we demonstrate our algorithm on both real and synthetic data sets that exemplify all three aforementioned challenges.

We present a new FEM (Finite Element Method) model for the 3D reconstruction of a deforming scene using as sole input a calibrated video sequence. Our approach extends the recently proposed 2D thin-plate FEM+EKF (Extended Kalman Filter) combination. Thin-plate FEM is an approximation that models a deforming 3D thin solid as a surface, and then discretizes the surface as a mesh of planar triangles. In contrast, we propose a full-fledged 3D FEM formulation where the deforming 3D solid is discretized as a mesh of 3D wedge elements. The new 3D FEM formulation provides better conditioning for the rank analysis stage necessary to remove the rigid boundary points from the formulation. We show how the proposed formulation accurately estimates deformable scenes from real imagery even for strong deformations. Crucially we also show, for the first time to the best of our knowledge, NRSfM (Non-Rigid Structure from Motion) at 30Hz real-time over real imagery. Real-time can be achieved for our 3D FEM formulation combined with an EKF resulting in accurate estimates even for small size maps.

Trajectory basis Non-Rigid Structure From Motion (NRSFM) currently faces two problems: the limit of reconstructability and the need to tune the basis size for different sequences. This paper provides a novel theoretical bound on 3D reconstruction error, arguing that the existing definition of reconstructability is fundamentally flawed in that it fails to consider system condition. This insight motivates a novel strategy whereby the trajectory's response to a set of high-pass filters is minimised. The new approach eliminates the need to tune the basis size and is more efficient for long sequences. Additionally, the truncated DCT basis is shown to have a dual interpretation as a high-pass filter. The success of trajectory filter reconstruction is demonstrated quantitatively on synthetic projections of real motion capture sequences and qualitatively on real image sequences.

This study proposes an automatic training data selection method for Autoencoder-based defect detection in hammering inspection, designed to address the severe class imbalance between normal and defective sounds. The proposed method employs a physically grounded indicator, Acoustic Energy per Impact, to automatically select and collect only the sound data considered normal. An Autoencoder is then trained exclusively on the collected normal sounds to identify defects based on reconstruction errors. To evaluate the effectiveness of the proposed method, experiments were conducted using concrete specimens with cracks. The results demonstrate that the proposed method achieves higher defect detection performance than a conventional approach, even under highly imbalanced class conditions.

Recently, there has been an increase in the number of photos taken by people in especially unusual situations such as travel and ceremony. The photo groups taken in unusual situations have similar images and low-quality images such as under/overexposure and blurred images. For that reason, it is time consuming to summarize photos for creating photo albums. Therefore, we propose a method of automatic photo selection for photo albums. The proposed method can avoid to select low-quality images as candidate images automatically. Additionally, similar images are grouped and narrowed down the only most high-quality image that is selected as candidate image. The proposed method calculates the score of each candidate image, and selects final-images according to the score and scenes.

Self-calibration of projective camera based on trajectory basis

Automatic reference selection for quantitative EEG interpretation: Identification of diffuse/localised activity and the active earlobe reference, iterative detection of the distribution of EEG rhythms

The volume measurement of various organs by single photon emission computed tomography (SPECT) has generally been performed by summing up the voxels lying within the outer edge of the organ determined by thresholding as a function of the maximum reconstructed counts within a volume of interest. The optimum threshold level, however, is influenced by various factors. To eliminate this problem, Mortelmans et al. (1986) proposed to use an automatic threshold selection method (ATSM) based on discriminant criteria and to correct the errors induced by the imperfect system response using the method based on linear regression analysis, which has some problems in practical application. We tried to use ATSM combined with a V filter. The correlation coefficient (r) and the regression equation between the true (x) and the calculated volume (y) obtained by experimentation using 22 phantoms with a volume ranging between 26 ml and 380 ml were as follows: r = 0.994 and y(ml) = 1.015 x +1.09 using ATSM combined with a V filter, while r = 0.993 and y(ml) = 1.110 x +30.55 using only ATSM. The relative error between the true and the calculated volumes decreased significantly (P less than 0.01) from 37.7% +/- 26.9% to 5.5% +/- 4.2%. The results suggest that ATSM combined with a V filter is useful for correcting the errors caused by an imperfect system response, and is available and reliable for SPECT volume determination even when the organ volume is small.

This paper presents an automatic selected channel method for improving brain-computer interface (BCI) performance. Finding an effective channel composition in a BCI system is important for parsing the complexity of these systems. In this study, several statistical methods based on an energy extraction method were used to automatically detect the composition of selected channels. We introduce four techniques for automatic channel selection to optimize the energy extraction method, such as mean, high mean, box, and high in box. The performance of all of the proposed techniques was evaluated based on performance accuracy, compression ratio, and channel mapping on a brain scalp. The performance of the proposed BCI framework was compared against a BCI framework that used a manual technique as the energy extraction method. The proposed BCI framework system used a conventional common spatial pattern (CSP) to extract features from two-class motor imagery EEG signals before employing extreme learning machine (ELM) to classify the features of the EEG signal. As a result, the proposed automatic channel selection methods were found effective in finding optimal channels and provided better performance accuracy. In general, the proposed method improved the conventional BCI performance by up to 16% accuracy and 87% channel compression size. Besides that, the automatic technique also yielded better BCI performance accuracy of up to 5% compared to the BCI system that used the manual technique of energy extraction as its EEG channel selection method.

An eigen decomposition based rank parameter selection approach for the NRSFM algorithm

Landmarks are essential in non-rigid shape registration for identifying the correspondence between designs and actual products. In 3D printing, manual selection of landmarks becomes labor-intensive, due to complex product geometries and their non-uniform shape deviations. Automatic selection, however, has to pinpoint landmarks indicative of geometric regions prone to deviations for accuracy qualification. Existing automatic landmarking methods often generate clustered and redundant landmarks for prominent features with high curvatures, compromising the balance between global and local registration errors. To address these issues, we propose an automatic landmark selection method through deviation-aware segmentation and landmarking. As opposed to segmentation for semantic feature identification, deviation-aware segmentation partitions a freeform product for high-curvature region identification. Prone to deviation, these regions are generated through curvature-sensitive remeshing to extract vertices of high curvature and automatic clustering of vertices based on vertex density. Within each segment or high-curvature region, a curvature-weighted function is tailored for the Gaussian process landmarking to sequentially select landmarks with the highest local curvatures. Furthermore, we propose a new evaluation criterion to assess the effectiveness of selected landmarks through registration. The proposed approach is tested through automatic landmarking of printed dental models.

<p>The small baseline subset of spaceborne interferometric synthetic aperture radar (SBAS-InSAR) technology has become a classical method for monitoring slow deformations through time series analysis with an accuracy in the centimeter or even millimeter range. Additionally, the process of calculating interferograms itself directly affects the accuracy of the SBAS-InSAR measurements, whereby the selection of high-quality interferogram pairs is crucial for SBAS data processing. Especially in the era of big data, the demand for an automatic and effective selection method of high-quality interferograms in SBAS-InSAR technology is growing. However, there are some methods including simulated annealing (SA) searching strategy, the graph theory (GT) and others. Until now, the most effective approach of high-quality interferogram selection still relies on the traditional manual method. Due to the high degree of human interaction and a large risk of repetitive work, this traditional manual method increases the instability and inconsistency of the deformation calculation.<br>Considering that the different qualities of interference pairs show different color characteristics, the DCNN method is adopted in this study. The ResNet50 model (one of DCNN models) has the advantages of representing a standard network structure and easy programming. The idea is based on the fact that interferograms less contaminated by different noise sources display smaller color phase changes within a certain phase range. Hence, training sets containing almost 3000 interferograms obtained from land subsidences in several subregions of Shenzhen in China with varying contaminations of noise were established. Up next, the ResNet50–DCNN model was set up, the respective parameters were determined through analysis of the data sets trained, and traditional interferogram selection methods were used to evaluate the performance. For simulation experiments and the evaluation and validation of real data, phase unwrapping interferograms obtained by the time-spatial baseline threshold method are used to classify high and low quality interferograms based on the ResNet50 model. The quantity of high quality interferograms extracted by the ResNet50–DCNN method is above 90% for the simulation experiment and above 87% concerning the real data experiment, which reflects the accuracy and reliability of the proposed method. A comparison of the overall surface subsidence rates and the deformation information of local PS points reveals little difference between the land subsidence rates obtained by the ResNet50–DCNN method and the actual simulations or the manual method. <br>The proposed advanced method provides an automatized and fast interferogram selection process for high quality data, which contributes significantly to the application of SBAS-InSAR engineering. For future research, we will expand the training samples and study DCNN models to further improve the general accuracy for a wider applicability of this method.</p>

In many high dimensional problems, the dependence structure among the variables can be quite complex. An appropriate use of the regularization techniques coupled with other classical statistical methods can often improve estimation and prediction accuracy and facilitate model interpretation, by seeking a parsimonious model representation that involves only the subset of revelent variables. We propose two regularized stochastic regression approaches, for efficiently estimating certain sparse dependence structure in the data. We first consider a multivariate regression setting, in which the large number of responses and predictors may be associated through only a few channels/pathways and each of these associations may only involve a few responses and predictors. We propose a regularized reduced-rank regression approach, in which the model estimation and rank determination are conducted simultaneously and the resulting regularized estimator of the coefficient matrix admits a sparse singular value decomposition (SVD). Secondly, we consider model selection of subset autoregressive moving-average (ARMA) modelling, for which automatic selection methods do not directly apply because the innovation process is latent. We propose to identify the optimal subset ARMA model by fitting a penalized regression, e.g. adaptive Lasso, of the time series on its lags and the lags of the residuals from a long autoregression fitted to the time-series data, where the residuals serve as proxies for the innovations. Computation algorithms and regularization parameter selection methods for both proposed approaches are developed, and their properties are ex-