TOWARDS STRUCTURELESS BUNDLE ADJUSTMENT WITH TWO- AND THREE-VIEW STRUCTURE APPROXIMATION

Abstract. The global approaches solve SfM problems by independently inferring relative motions, followed be a sequential estimation of global rotations and translations. It is a fast approach but not optimal because it relies only on pairs and triplets of images and it is not a joint optimisation. In this publication we present a methodology that increases the quality of global solutions without the usual computational burden tied to the bundle adjustment. We propose an efficient structure approximation approach that relies on relative motions known upfront. Using the approximated structure, we are capable of refining the initial poses at very low computational cost. Compared to different benchmark datasets and software solutions, our approach improves the processing times while maintaining good accuracy.

Download Full-text

Numerical Simulation of AA2024-T3 Friction Stir Welding (FSW) Process: Sensitivity Analyses and Influence of Decisions during Modelling Stages

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.651-653.919 ◽

2015 ◽

Vol 651-653 ◽

pp. 919-924 ◽

Cited By ~ 4

Author(s):

Rui M.F. Paulo ◽

Pierpaolo Carlone ◽

Robertt A.F. Valente ◽

Filipe Teixeira-Dias ◽

Gaetano S. Palazzo

Keyword(s):

Friction Stir Welding ◽

Good Accuracy ◽

Computational Cost ◽

The Other ◽

Sensitivity Analyses ◽

Element Analysis ◽

Shell Elements ◽

Friction Stir ◽

The One ◽

Low Computational Cost

The main objective of the present work is to assess the influence of several parameters relevant for Finite Element Analysis (FEA) in modelling Friction Stir Welding (FSW) processes on AA2024-T3 plates. Several tests were performed including variations on the type of shell elements, number of integration points across thickness direction and mesh refinement levels, aiming for good accuracy and low computational cost. On the one hand, several setups of the mechanical boundary conditions, modelling the clamping systems, were also tested, leading to the conclusion that the results, in terms of longitudinal residual stresses, are significantly affected by this factor. On the other hand, variations on the heat input distribution showed a reduced effect, or almost null, on the final results.

Download Full-text

Designing Compact Convolutional Filters for Lightweight Human Pose Estimation

Wireless Communications and Mobile Computing ◽

10.1155/2021/1333250 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Shili Niu ◽

Weihua Ou ◽

Shihua Feng ◽

Jianping Gou ◽

Fei Long ◽

...

Keyword(s):

Pose Estimation ◽

State Of The Art ◽

Computational Cost ◽

Estimation Accuracy ◽

Human Pose Estimation ◽

Model Parameters ◽

Resource Limited ◽

Benchmark Datasets ◽

Human Pose ◽

Low Computational Cost

Existing methods for human pose estimation usually use a large intermediate tensor, leading to a high computational load, which is detrimental to resource-limited devices. To solve this problem, we propose a low computational cost pose estimation network, MobilePoseNet, which includes encoder, decoder, and parallel nonmaximum suppression operation. Specifically, we design a lightweight upsampling block instead of transposing the convolution as the decoder and use the lightweight network as our downsampling part. Then, we choose the high-resolution features as the input for upsampling to reduce the number of model parameters. Finally, we propose a parallel OKS-NMS, which significantly outperforms the conventional NMS in terms of accuracy and speed. Experimental results on the benchmark datasets show that MobilePoseNet obtains almost comparable results to state-of-the-art methods with a low compilation load. Compared to SimpleBaseline, the parameter of MobilePoseNet is only 4%, while the estimation accuracy reaches 98%.

Download Full-text

An Enhanced Visual Attention Siamese Network That Updates Template Features Online

Security and Communication Networks ◽

10.1155/2021/9719745 ◽

2021 ◽

Vol 2021 ◽

pp. 1-19

Author(s):

Wenqiu Zhu ◽

Guang Zou ◽

Qiang Liu ◽

Zhigao Zeng

Keyword(s):

Visual Attention ◽

Success Rate ◽

Video Sequence ◽

Computational Cost ◽

Superior Performance ◽

Inference Process ◽

Discriminative Ability ◽

Siamese Network ◽

Benchmark Datasets ◽

Low Computational Cost

Recently, Siamese trackers have attracted extensive attention because of their simplicity and low computational cost. However, for most Siamese trackers, only a frame of the video sequence is used as the template, and the template is not updated in inference process, which makes the tracking success rate inferior to the trackers that can update the template online. In the current study, we introduce an enhanced visual attention Siamese network (ESA-Siam). The method is based on a deep convolutional neural network, which integrates channel attention and spatial self-attention to improve the discriminative ability of the tracker for positive and negative samples. Channel attention reflects different targets according to the response value of different channels to achieve better target representation. Spatial self-attention captures the correlation between two arbitrary positions to help locate the target. At the same time, a template search attention module is designed to implicitly update the template features online, which can effectively improve the success rate of the tracker when the target is interfered by the background. The proposed ESA-Siam tracker shows superior performance compared with 18 existing state-of-the-art trackers on five benchmark datasets including OTB50, OTB100, VOT2016, VOT2018, and LaSOT.

Download Full-text

Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification

Remote Sensing ◽

10.3390/rs11242908 ◽

2019 ◽

Vol 11 (24) ◽

pp. 2908 ◽

Cited By ~ 7

Author(s):

Yakoub Bazi ◽

Mohamad M. Al Rahhal ◽

Haikel Alhichri ◽

Naif Alajlan

Keyword(s):

Remote Sensing ◽

State Of The Art ◽

Computational Cost ◽

Feature Learning ◽

Extraction Methods ◽

Fine Tuning ◽

Scene Classification ◽

Negative Effect ◽

Benchmark Datasets ◽

Low Computational Cost

The current literature of remote sensing (RS) scene classification shows that state-of-the-art results are achieved using feature extraction methods, where convolutional neural networks (CNNs) (mostly VGG16 with 138.36 M parameters) are used as feature extractors and then simple to complex handcrafted modules are added for additional feature learning and classification, thus coming back to feature engineering. In this paper, we revisit the fine-tuning approach for deeper networks (GoogLeNet and Beyond) and show that it has not been well exploited due to the negative effect of the vanishing gradient problem encountered when transferring knowledge to small datasets. The aim of this work is two-fold. Firstly, we provide best practices for fine-tuning pre-trained CNNs using the root-mean-square propagation (RMSprop) method. Secondly, we propose a simple yet effective solution for tackling the vanishing gradient problem by injecting gradients at an earlier layer of the network using an auxiliary classification loss function. Then, we fine-tune the resulting regularized network by optimizing both the primary and auxiliary losses. As for pre-trained CNNs, we consider in this work inception-based networks and EfficientNets with small weights: GoogLeNet (7 M) and EfficientNet-B0 (5.3 M) and their deeper versions Inception-v3 (23.83 M) and EfficientNet-B3 (12 M), respectively. The former networks have been used previously in the context of RS and yielded low accuracies compared to VGG16, while the latter are new state-of-the-art models. Extensive experimental results on several benchmark datasets reveal clearly that if fine-tuning is done in an appropriate way, it can settle new state-of-the-art results with low computational cost.

Download Full-text

Binary Competitive Swarm Optimizer Approaches for Feature Selection

Computation ◽

10.3390/computation7020031 ◽

2019 ◽

Vol 7 (2) ◽

pp. 31 ◽

Cited By ~ 4

Author(s):

Jingwei Too ◽

Abdul Rahim Abdullah ◽

Norhashimah Mohd Saad

Keyword(s):

Feature Selection ◽

Transfer Functions ◽

Computational Cost ◽

Combinatorial Problem ◽

Search Space ◽

Relevant Information ◽

Classification Performance ◽

Feature Size ◽

Benchmark Datasets ◽

Low Computational Cost

Feature selection is known as an NP-hard combinatorial problem in which the possible feature subsets increase exponentially with the number of features. Due to the increment of the feature size, the exhaustive search has become impractical. In addition, a feature set normally includes irrelevant, redundant, and relevant information. Therefore, in this paper, binary variants of a competitive swarm optimizer are proposed for wrapper feature selection. The proposed approaches are used to select a subset of significant features for classification purposes. The binary version introduced here is performed by employing the S-shaped and V-shaped transfer functions, which allows the search agents to move on the binary search space. The proposed approaches are tested by using 15 benchmark datasets collected from the UCI machine learning repository, and the results are compared with other conventional feature selection methods. Our results prove the capability of the proposed binary version of the competitive swarm optimizer not only in terms of high classification performance, but also low computational cost.

Download Full-text

A Linear-RBF Multikernel SVM to Classify Big Text Corpora

BioMed Research International ◽

10.1155/2015/878291 ◽

2015 ◽

Vol 2015 ◽

pp. 1-14 ◽

Cited By ~ 8

Author(s):

R. Romero ◽

E. L. Iglesias ◽

L. Borrajo

Keyword(s):

Good Accuracy ◽

Computational Cost ◽

Support Vector ◽

Brute Force ◽

New Approach ◽

Text Corpora ◽

Input Size ◽

Recent Developments ◽

Low Computational Cost

Support vector machine (SVM) is a powerful technique for classification. However, SVM is not suitable for classification of large datasets or text corpora, because the training complexity of SVMs is highly dependent on the input size. Recent developments in the literature on the SVM and other kernel methods emphasize the need to consider multiple kernels or parameterizations of kernels because they provide greater flexibility. This paper shows a multikernel SVM to manage highly dimensional data, providing an automatic parameterization with low computational cost and improving results against SVMs parameterized under a brute-force search. The model consists in spreading the dataset into cohesive term slices (clusters) to construct a defined structure (multikernel). The new approach is tested on different text corpora. Experimental results show that the new classifier has good accuracy compared with the classic SVM, while the training is significantly faster than several other SVM classifiers.

Download Full-text

Assessing Facial Symmetry and Attractiveness using Augmented Reality

Pattern Analysis and Applications ◽

10.1007/s10044-021-00975-z ◽

2021 ◽

Author(s):

Wei Wei ◽

Edmond S. L. Ho ◽

Kevin D. McCay ◽

Robertas Damaševičius ◽

Rytis Maskeliūnas ◽

...

Keyword(s):

Augmented Reality ◽

Computational Cost ◽

Video Stream ◽

Facial Features ◽

Face Database ◽

Facial Symmetry ◽

Facial Landmarks ◽

Android Os ◽

Benchmark Datasets ◽

Low Computational Cost

AbstractFacial symmetry is a key component in quantifying the perception of beauty. In this paper, we propose a set of facial features computed from facial landmarks which can be extracted at a low computational cost. We quantitatively evaluated the proposed features for predicting perceived attractiveness from human portraits on four benchmark datasets (SCUT-FBP, SCUT-FBP5500, FACES and Chicago Face Database). Experimental results showed that the performance of the proposed features is comparable to those extracted from a set with much denser facial landmarks. The computation of facial features was also implemented as an augmented reality (AR) app developed on Android OS. The app overlays four types of measurements and guidelines over a live video stream, while the facial measurements are computed from the tracked facial landmarks at run time. The developed app can be used to assist plastic surgeons in assessing facial symmetry when planning reconstructive facial surgeries.

Download Full-text

Driving Torsion Scans with Wavefront Propagation

10.26434/chemrxiv.12044673.v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Yudong Qiu ◽

Daniel Smith ◽

Chaya Stern ◽

mudong feng ◽

Lee-Ping Wang

Keyword(s):

Potential Energy ◽

Force Field ◽

Degrees Of Freedom ◽

Computational Cost ◽

Initial Guess ◽

Field Development ◽

Force Field Development ◽

Wavefront Propagation ◽

Open Source Software Package

<div>The parameterization of torsional / dihedral angle potential energy terms is a crucial part of developing molecular mechanics force fields.</div><div>Quantum mechanical (QM) methods are often used to provide samples of the potential energy surface (PES) for fitting the empirical parameters in these force field terms.</div><div>To ensure that the sampled molecular configurations are thermodynamically feasible, constrained QM geometry optimizations are typically carried out, which relax the orthogonal degrees of freedom while fixing the target torsion angle(s) on a grid of values.</div><div>However, the quality of results and computational cost are affected by various factors on a non-trivial PES, such as dependence on the chosen scan direction and the lack of efficient approaches to integrate results started from multiple initial guesses.</div><div>In this paper we propose a systematic and versatile workflow called \textit{TorsionDrive} to generate energy-minimized structures on a grid of torsion constraints by means of a recursive wavefront propagation algorithm, which resolves the deficiencies of conventional scanning approaches and generates higher quality QM data for force field development.</div><div>The capabilities of our method are presented for multi-dimensional scans and multiple initial guess structures, and an integration with the MolSSI QCArchive distributed computing ecosystem is described.</div><div>The method is implemented in an open-source software package that is compatible with many QM software packages and energy minimization codes.</div>

Download Full-text

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

10.26434/chemrxiv.7151435.v2 ◽

2018 ◽

Author(s):

Roman Zubatyuk ◽

Justin S. Smith ◽

Jerzy Leszczynski ◽

Olexandr Isayev

Keyword(s):

Neural Network ◽

Molecular System ◽

Computational Cost ◽

Chemical Properties ◽

The State ◽

Molecular Properties ◽

Training Data ◽

Dft Methods ◽

Benchmark Datasets ◽

Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Download Full-text

Fast Multi-Focus Fusion Based on Deep Learning for Early-Stage Embryo Image Enhancement

Sensors ◽

10.3390/s21030863 ◽

2021 ◽

Vol 21 (3) ◽

pp. 863

Author(s):

Vidas Raudonis ◽

Agne Paulauskaite-Taraseviciene ◽

Kristina Sutiene

Keyword(s):

Deep Learning ◽

Image Fusion ◽

Early Stage ◽

Image Data ◽

Cell Detection ◽

Processing Times ◽

Fused Image ◽

Stage Embryo ◽

Early Stage Embryo

Background: Cell detection and counting is of essential importance in evaluating the quality of early-stage embryo. Full automation of this process remains a challenging task due to different cell size, shape, the presence of incomplete cell boundaries, partially or fully overlapping cells. Moreover, the algorithm to be developed should process a large number of image data of different quality in a reasonable amount of time. Methods: Multi-focus image fusion approach based on deep learning U-Net architecture is proposed in the paper, which allows reducing the amount of data up to 7 times without losing spectral information required for embryo enhancement in the microscopic image. Results: The experiment includes the visual and quantitative analysis by estimating the image similarity metrics and processing times, which is compared to the results achieved by two wellknown techniques—Inverse Laplacian Pyramid Transform and Enhanced Correlation Coefficient Maximization. Conclusion: Comparatively, the image fusion time is substantially improved for different image resolutions, whilst ensuring the high quality of the fused image.

Download Full-text