Shape Of Object Research Articles

Equalized shape feature enhancement method for multiple ferromagnetic objects

When magnetic measuring instruments are used to measure the shape of ferromagnetic objects, the objects far away from the observation plane are likely to have blurred shape features because the magnetic field decays rapidly with distance. A bigger challenge is to measure multiple objects at the same time. When the relative positions of multiple measured objects and the observation plane are inappropriate, it is easy to have problems that the shape features of the deeper measured objects are not obvious and the magnetic signals of multiple measured objects are aliased, which usually leads to shape feature measurement failed. To address this issue, we propose an equalized shape feature enhancement method for multiple ferromagnetic objects. The method enhances shape features by evaluating the trends of the total horizontal derivative and vertical derivative of the magnetic field within the measurement area using the standard deviation. Meanwhile, the method combines the theory of ratio equalization and normalization to improve the shape features convergence of deeper objects and balance the signal aliasing interference between objects of different depths. Model simulation and experimental results show that the shape feature measurement results of the proposed method are clear and in good agreement with the ideal model. The method can effectively balance the magnetic anomaly amplitudes of the measured objects with different depths, and improve the accuracy and stability of shape feature measurement. We compare and analyze the processing effects of the proposed method and the traditional normalized standard deviation method (NSTD). It is calculated that the standard deviations of the results obtained by the proposed method and the NSTD method are 0.146 and 0.136, and the average peak-to-trough differences are 0.368 and 0.352, respectively. Therefore, the proposed method can better enhance the shape characteristics of ferromagnetic objects and has more practical application value.

CMFAN: Cross-Modal Feature Alignment Network for Few-Shot Single-View 3D Reconstruction.

Few-shot single-view 3D reconstruction learns to reconstruct the novel category objects based on a query image and a few support shapes. However, since the query image and the support shapes are of different modalities, there is an inherent feature misalignment problem damaging the reconstruction. Previous works in the literature do not consider this problem. To this end, we propose the cross-modal feature alignment network (CMFAN) with two novel techniques. One is a strategy for model pretraining, namely, cross-modal contrastive learning (CMCL), here the 2D images and 3D shapes of the same objects compose the positives, and those from different objects form the negatives. With CMCL, the model learns to embed the 2D and 3D modalities of the same object into a tight area in the feature space and push away those from different objects, thus effectively aligning the global cross-modal features. The other is cross-modal feature fusion (CMFF), which further aligns and fuses the local features. Specifically, it first re-represents the local features with the cross-attention operation, making the local features share more information. Then, CMFF generates a descriptor for the support features and attaches it to each local feature vector of the query image with dense concatenation. Moreover, CMFF can be applied to multilevel local features and brings further advantages. We conduct extensive experiments to evaluate the effectiveness of our designs, and CMFAN sets new state-of-the-art performance in all of the 1-/10-/25-shot tasks of ShapeNet and ModelNet datasets.

A fast and scalable computational topology framework for the Euler characteristic

Parallel algorithms exploit structure to compute the Euler characteristic (a powerful topological descriptor that is used to quantify shape of data) at significantly less computational expense than traditional software tools.

Robotic Kinesthesia: Estimating Object Geometry and Material With Robot's Haptic Senses.

Humans excel at determining the shape and material of objects through touch. Drawing inspiration from this ability, we propose a robotic system that incorporates haptic sensing capability into its artificial recognition system to jointly learn the shape and material types of an object. To achieve this, we employ a serially connected robotic arm and develop a supervised learning task that learns and classifies target surface geometry and material types using multivariate time-series data from joint torque sensors. Additionally, we propose a joint torque-to-position generation task to derive a one-dimensional surface profile based on torque measurements. Experimental results successfully validate the proposed torque-based classification and regression tasks, suggesting that a robotic system can employ haptic sensing (i.e., perceived force) from each joint to recognize material types and geometry, akin to human abilities.

Minimally designed thermo-magnetic dual responsive soft robots for complex applications.

The fabrication of thermo-magnetic dual-responsive soft robots often requires intricate designs to implement complex locomotion patterns and utilize the implemented responsive behaviors. This work demonstrates a minimally designed soft robot based on poly-N-isopropylacrylamide (pNIPAM) and ferromagnetic particles, showcasing excellent control over both thermo- and magnetic responses. Free radical polymerization enables the magnetic particles to be entrapped homogeneously within the polymeric network. The integration of magnetic shape programming and temperature response allows the robot to perform various tasks including shaping, locomotion, pick-and-place, and release maneuvers of objects using independent triggers. The robot can be immobilized in a gripping state through magnetic actuation, and a subsequent increase in temperature transitions the robot from a swollen to a collapsed state. The temperature switch enables the robot to maintain a secured configuration while executing other movements via magnetic actuation. This approach offers a straightforward yet effective solution for achieving full control over both stimuli in dual-responsive soft robotics.

3D Shape Contrastive Representation Learning with Adversarial Examples

Current supervised methods for 3D shape representation learning have achieved satisfying performance, yet require extensive human-labeled datasets. Unsupervised learning-based methods provide a viable solution by learning shape representations without using ground truth labels. In this study, we develop a contrastive learning framework for unsupervised representation learning of 3D shapes. Specifically, in order to encourage models to pay more attention to useful information during representation learning, we first introduce a new paradigm for critical points search based on the adversarial mechanism. We extract critical points with a larger impact on the global feature by attacking a pre-trained auto-encoder model, and apply data augmentations on these points to generate adversarial examples. Taking a pair of adversarial examples as inputs, we obtain their intermediate embeddings and global representations of corresponding inputs, which are then transformed into latent spaces by two predictor heads. Finally, we train the proposed model by maximizing the agreements on these latent spaces via Normalized Temperature-scaled Cross Entropy (NT-Xent) loss and a newly designed Cross-layer Normalized Temperature-scaled Cross Entropy (Cross-NT-Xent) loss, where the latter is proposed in this paper to enforce cross-layer feature similarities. The effectiveness, robustness, and transferability of learned representations are validated on three downstream tasks, including object classification, few-shot classification, and shape retrieval. Experiments on three benchmark datasets show that our learned representations achieve better or competitive performance than current state-of-the-art methods in these downstream tasks. Moreover, our model can easily be extended to 3D part segmentation and scene segmentation tasks.

Adaptation of the inferior temporal neurons and efficient visual processing.

Numerous studies examining the responses of individual neurons in the inferior temporal (IT) cortex have revealed their characteristics such as two-dimensional or three-dimensional shape tuning, objects, or category selectivity. While these basic selectivities have been studied assuming that their response to stimuli is relatively stable, physiological experiments have revealed that the responsiveness of IT neurons also depends on visual experience. The activity changes of IT neurons occur over various time ranges; among these, repetition suppression (RS), in particular, is robustly observed in IT neurons without any behavioral or task constraints. I observed a similar phenomenon in the ventral visual neurons in macaque monkeys while they engaged in free viewing and actively fixated on one consistent object multiple times. This observation indicates that the phenomenon also occurs in natural situations during which the subject actively views stimuli without forced fixation, suggesting that this phenomenon is an everyday occurrence and widespread across regions of the visual system, making it a default process for visual neurons. Such short-term activity modulation may be a key to understanding the visual system; however, the circuit mechanism and the biological significance of RS remain unclear. Thus, in this review, I summarize the observed modulation types in IT neurons and the known properties of RS. Subsequently, I discuss adaptation in vision, including concepts such as efficient and predictive coding, as well as the relationship between adaptation and psychophysical aftereffects. Finally, I discuss some conceptual implications of this phenomenon as well as the circuit mechanisms and the models that may explain adaptation as a fundamental aspect of visual processing.

Высокоточная схема для уравнения переноса в задаче нейтронной защиты

The paper considers the problems of calculating the stationary transport of high-energy neutrons from an external source in a hollow metal structure. The spatial grid for calculation consists of tetrahedra, which allows to model complicated geometric shapes of objects. The calculated area is highly heterogeneous, since it consists of metal parts with strong absorption and scattering and practically non-absorbing internal parts. A scheme based on a minimal stencil, within a single tetrahedron for the calculation. The scheme has a high approximation order and is based on characteristic approaches. For a smooth solution and a constant absorption coefficient in each cell, the scheme has a third order of convergence. The cells are traversed using the graph topological sorting algorithm. A new version of the parallelization of the calculation for the OpenMP standard has been proposed. For discretization by an angular variable, a cubature formula of the direct product type over two angles with an algebraic order of accuracy of nine is used. The angular grid is constructed in such a way as to correctly calculate the moments for narrowly directed beams of external radiation. The standard 26-group approximation of the BNAB library is used for energy sampling. A decrease in the neutron flux inside the structure is shown for groups with an energy above 1 MeV. Graphs of the angular distribution inside the structure are given.

Edge-Aware Network for Flow-Based Video Frame Interpolation.

Video frame interpolation can up-convert the frame rate and enhance the video quality. In recent years, although interpolation performance has achieved great success, image blur usually occurs at object boundaries owing to the large motion. It has been a long-standing problem and has not been addressed yet. In this brief, we propose to reduce the image blur and get the clear shape of objects by preserving the edges in the interpolated frames. To this end, the proposed edge-aware network (EA-Net) integrates the edge information into the frame interpolation task. It follows an end-to-end architecture and can be separated into two stages, i.e., edge-guided flow estimation and edge-protected frame synthesis. Specifically, in the flow estimation stage, three edge-aware mechanisms are developed to emphasize the frame edges in estimating flow maps, so that the edge maps are taken as auxiliary information to provide more guidance to boost the flow accuracy. In the frame synthesis stage, the flow refinement module is designed to refine the flow map, and the attention module is carried out to adaptively focus on the bidirectional flow maps when synthesizing the intermediate frames. Furthermore, the frame and edge discriminators are adopted to conduct the adversarial training strategy, so as to enhance the reality and clarity of synthesized frames. Experiments on three benchmarks, including Vimeo90k, UCF101 for single-frame interpolation, and Adobe240-fps for multiframe interpolation, have demonstrated the superiority of the proposed EA-Net for the video frame interpolation task.

Visual sensitivity at the service of action control in posterior parietal cortex.

The posterior parietal cortex (PPC) serves as a crucial hub for the integration of sensory with motor cues related to voluntary actions. Visual input is used in different ways along the dorsomedial and the dorsolateral visual pathways. Here we focus on the dorsomedial pathway and recognize a visual representation at the service of action control. Employing different experimental paradigms applied to behaving monkeys while single neural activity is recorded from the medial PPC (area V6A), we show how plastic visual representation can be, matching the different contexts in which the same object is proposed. We also present data on the exchange between vision and arm actions and highlight how this rich interplay can be used to weight different sensory inputs in order to monitor and correct arm actions online. Indeed, neural activity during reaching or reach-to-grasp actions can be excited or inhibited by visual information, suggesting that the visual perception of action, rather than object recognition, is the most effective factor for area V6A. Also, three-dimensional object shape is encoded dynamically by the neural population, according to the behavioral context of the monkey. Along this line, mirror neuron discharges in V6A indicate the plasticity of visual representation of the graspable objects, that changes according to the context and peaks when the object is the target of one's own action. In other words, object encoding in V6A is a visual encoding for action.

Magnetostrictive-based multimodal tactile sensors for object recognition

Tactile perception of the human hand plays a critical role in everyday object recognition. The development of multimodal tactile sensors that can sense stimuli with high sensitivity and low cost is important for intelligent perception. In this article, a multimodal tactile sensor attached on a mechanical hand is studied, which consists of a magnetostrictive tactile sensor, a temperature sensor, and a flex sensor. By applying multimodal tactile sensors to a robotic hand to grasp objects, the output voltage of the magnetotactictive tractile tactile sensor can be used for object shape and softness recognition. The bending angle of the knuckles can be obtained by the flex sensor for object contour size recognition, while the temperature distribution of objects can be obtained through temperature sensors. In order to improve the accuracy, a 1-D convolutional neural network-extreme learning machine (CNN-ELM) pattern recognition model based on the combination of 1-D CNN and ELM is presented, with the accuracy of 97.14% for 21 objects. This multimodal tactile sensor has promising applications in the field of tactile intelligence and humanoid robotics.

GeoAI Dataset for Training Deep Learning-Based Optical Satellite Image Matching Model

Satellite imagery is being used to monitor the Earth, as it allows for the continuous provision of multi-temporal observations with consistent quality. To analyze time series remote sensing data with high accuracy, the process of image registration must be conducted beforehand. Image registration techniques are mainly divided into region-based registration and feature-based registration, and both techniques extract the same points based on the similarity of spectral characteristics and object shapes between master and slave images. In addition, recently, deep learning-based siamese neural network and convolutional neural network models have been utilized to match images. This has high performance compared to previous non-deep learning algorithms, but a very large amount of data is required to train a deep learning-based image registration model. In this study, we aim to generate a dataset for training a deep learning-based optical image registration model. To build the data, we acquired Satellite Side-Looking (S2Looking) data, an open dataset, and performed preprocessing and data augmentation on the data to create input data. After that, we added offsets to the X and Y directions between the master and slave images to create label data. The preprocessed input data and labeled data were used to build a dataset suitable for image registration. The data is expected to be useful for training deep learning-based satellite image registration models.

Heat treatment and tensile test of 3D-printed parts manufactured at different build orientations

Abstract Additive manufacturing has been gaining popularity in many industries and has made significant growth over the last 5 years. Many industries use additive manufacturing three-dimensional (3D) printing to produce complex shape objects that is a challenge to be manufactured by casting or conventional methods. In this study, the impact of heat treatment and build orientation is examined for the mechanical characteristics of 3D-printed parts. The study used samples constructed of titanium alloy Ti-6Al-4V, which is frequently used in AM applications. The parts were printed at various build orientations such as 0°, 45°, and 90°. Following printing, the samples underwent four distinct heat-treatments at 0, 700, 800, and 900°C. The variation in mechanical properties (Young’s modulus, strain-stress, and tensile strength) has been monitored to determine the best heat treatment and tilt orientation to obtain the best mechanical properties. These findings provide a systematic analysis and support the 3D printing of the parts used with a desired mechanical strength.

Terracotta in Architecture: Overview on Historical and Contemporary Practice in Bangladesh

Although Terracotta is one of the oldest in almost all sub-continents and was spread out across the whole world now-a-days it has been a common, traditional, and indigenous object in Bangladesh for everyday life. Inspired by the religion or rituals, terracotta art has evolved in many ways in Bengal over time. From Babylon walls to high-performance rain screens, terracotta claddings have proven repeatedly to be technologically superior and aesthetically rich. Realizing the evolution of terracotta prepares architects to add new, creative chapters to a superior history. Through an extensive inventory of recent examples, project case studies and architectural details, this study provides a foundation for understanding the nature of the material and the opportunities it offers in the urban life. The objective of the paper is to know the evolution of terracotta as a historic, artistic and cultural materials and shapes of objects with aesthetical and technical aspects that plays an important role for place making in both exterior and interior of architectural design and building practice. The paper explores the evolution of terracotta in Bangladesh and prepares architects and builders to make new, creative uses of the timeless material. Validating the examples of expressive possibilities, this precious study can be an inspiration for students and professionals alike who are interested in creating sustainable spaces by using visual and cultural components.

The possibility of detecting non-x-ray fragments in the body of the wounded by the contact method

The types of injuries and types of striking elements were analyzed, the conditions of patients requiring urgent surgical intervention were assessed. The possibilities of existing means of diagnosing fragments in the patient's body were analyzed, and it was concluded that for non-X-ray contrast fragments, the proposed method of mechanical contact with a special flexible and elastic probe is appropriate and effective.A special tool for examining wound canals has been developed, consisting of a flexible probe for individual use and a handle-holder with a microphone capsule, the membrane of which is directly connected to the probe and reacts to mechanical contact with an obstacle, and the capsule itself is directly connected to the oscilloscope through a signal amplifier . which has spectral signal processing circuits.The problem of the interaction of the elastic contact of a non-rigid element with a fragment located in a viscous medium is set, provided that the properties of the medium are not constant. Typical solutions of this problem for various types of fragments and parameters of the contacting element itself are presented. A picture of the noise emission accompanying the contact is shown.The functional dependence of noise emission parameters on the shape and type of the foreign object in the wound canal was revealed. The expediency of using the frequency-amplitude characteristic of noise radiation as a controlled parameter has been proven. A conclusion was made about the functional conditioning of the width of the signal spectrum and basic frequencies at the time of mechanical contact with a foreign object in the wound, depending on its shape and type; it was established that the use of an oscilloscope with a spectral analysis channel allows for the fairly accurate identification of a non-radiocontrast foreign object in a wound.

Voting-based patch sequence autoregression network for adaptive point cloud completion

Point cloud completion aims to estimate the whole shapes of objects from their partial scans, and one of the main obstacles that prevents current methods from being applied in real-world scenarios is the variety of structural losses in real-scanned objects, which can hardly be fully included and reflected by the training samples. In this paper, we introduce Patch Sequence Autoregression Network (PSA-Net), a learning-based method that can be trained without the partial point clouds in dataset and is inherently adaptable to input scans with different levels of shape incompleteness: It makes restoring the unseen parts of objects be equivalent to predicting the missing tokens in local patch embedding sequences, and such prediction can start from any initial states. Specifically, we first introduce a Sequential Patch AutoEncoder that reconstructs complete point clouds from quantized patch feature sequences. Second, we establish a Mixed Patch Autoregression pipeline that can flexibly infer the whole sequence from any number of known tokens at any positions. Third, we propose a Voting-Based Mapping module that makes input points softly vote for their possible related tokens in sequences based on their local areas, which transforms partial point clouds to masked sequences in test. Quantitative and qualitative evaluations on two synthetic and four real-world datasets illustrate the competitive performances of our network when comparing with existing approaches.

СИНТЕТИЧЕСКОЕ ПРЕДСТАВЛЕНИЕ ПРЕОБРАЗОВАНИЯ "КОСАЯ СИММЕТРИЯ" НА ПРИМЕРЕ ПРЕОБРАЗОВАНИЯ ЭЛЛИПСА

Geometric transformations play a pivotal role in computer graphics, determining the position and shape of objects. In machine learning, they are applied for processing and analyzing data, such as in images. In geometric surface modeling, they are utilized for the creation and transformation of three-dimensional forms. In physics, geometric transformations assist in describing the motion of objects in space and time.
 The aim of this work is to analyse and study the geometric transformation known as "oblique symmetry." Primarily, the article seeks to elucidate a number of important properties of this transformation, expanding the field of knowledge in perspective-affine correspondence.
 Throughout the study, the principal directions of oblique symmetry are identified, and their relationship with the axis and direction of the transformation is established. It is crucial to emphasise that the analysis makes it evident that the axis and the direction of symmetry are equivalent and interchangeable. Additionally, the article addresses the challenge of transforming an arbitrary ellipse, defined by its semi-axes, into a circle of equal area. In this context, a method is proposed to determine the axis and direction of oblique symmetry for a given ellipse.
 Based on the results obtained and the analysis conducted, the authors propose a geometric algorithm that provides the capacity to resolve positional problems in the field of descriptive geometry. This algorithm also offers a novel method for constructing ellipses with given semi-axes, which holds practical significance in various engineering and geometric issues.
 In the conclusion of the article, a specific example of applying the developed method is provided, clearly demonstrating its practical value and real capabilities in solving positional problems in the field of descriptive geometry. Moreover, directions for future research in the field of shape formation are suggested, utilising the "oblique symmetry" transformation in the spaces and .

Образная (изобразительная) лексика в якутском и бурятском эпосах: лексические параллели

Introduction. The article presents a comparative analysis of the figurative vocabulary of the Yakut and Buryat languages on the basis of epic texts. The figurative vocabulary in both languages is specific part of its lexicon which have a common roots. The purpose of the study is to identify the features of the use of lexical parallels of the Yakut and Buryat figurative vocabulary in the texts of the Buryat uliger and Yakut olonkho. The relevance of the study is determined by the growing interest in linguistic folklore in the study of language based on the material of epic texts in order to identify the specifics of the language of the epic as a whole. For research a lexical and semantic analysis and comparative historical method were used. Materials. The texts of the Buryat uliger “Alamzhi Bergen” by E. Shalbykov and the Yakut olonkho “Kyys Debiliye” by N. P. Burnashev, “Mighty Er Sogotokh” by V. O. Karataev, “Khaan Dzhargystai” by unknown olonkhosut from Verkhoyansk were used as material for the study. The three olonkho texts are represented by three main regional epic traditions, which makes it possible to take into account almost all the local features of the olonkho text. Results. The study revealed 12 lexical parallels in the figurative vocabulary presented in the Yakut and Buryat epic texts. These lexical parallels were divided into three thematic groups by the way of description. Thus, first group is figurative words describing the figure, second is the group of words describing facial expressions and face, and the last one is the words describing the shape of objects. A comparative analysis of the revealed lexical parallels showed that they have a emotionally expressive character that allows expressing the narrator’s attitude to the described object, have the same semantic meaning, the same ways of word formation and the general principle of word formation.

Part2Point: A Part-Oriented Point Cloud Reconstruction Framework.

Three-dimensional object modeling is necessary for developing virtual and augmented reality applications. Traditionally, application engineers must manually use art software to edit object shapes or exploit LIDAR to scan physical objects for constructing 3D models. This is very time-consuming and costly work. Fortunately, GPU recently provided a cost-effective solution for massive data computation. With GPU support, many studies have proposed 3D model generators based on different learning architectures, which can automatically convert 2D object pictures into 3D object models with good performance. However, as the demand for model resolution increases, the required computing time and memory space increase as significantly as the parameters of the learning architecture, which seriously degrades the efficiency of 3D model construction and the feasibility of resolution improvement. To resolve this problem, this paper proposes a part-oriented point cloud reconstruction framework called Part2Point. This framework segments the object's parts, reconstructs the point cloud for individual object parts, and combines the part point clouds into the complete object point cloud. Therefore, it can reduce the number of learning network parameters at the exact resolution, effectively minimizing the calculation time cost and the required memory space. Moreover, it can improve the resolution of the reconstructed point cloud so that the reconstructed model can present more details of object parts.

MFSNet: Enhancing Semantic Segmentation of Urban Scenes with a Multi-Scale Feature Shuffle Network

The complexity of urban scenes presents a challenge for semantic segmentation models. Existing models are constrained by factors such as the scale, color, and shape of urban objects, which limit their ability to achieve more accurate segmentation results. To address these limitations, this paper proposes a novel Multi-Scale Feature Shuffle NetWork (MFSNet), which is an improvement upon the existing Deeplabv3+ model. Specifically, MFSNet integrates a novel Pyramid Shuffle Module (PSM) to extract discriminative features and feature correlations, with the objective of improving the accuracy of classifying insignificant objects. Additionally, we propose an efficient feature aggregation module (EFAM) to effectively expand the receptive field and aggregate contextual information, which is integrated as a branch within the network architecture to mitigate the information loss resulting from downsampling operations. Moreover, in order to augment the precision of segmentation boundary delineation and object localization, we employ a progressive upsampling strategy for reinstating spatial information in the feature maps. The experimental results show that the proposed model achieves competitive performance, achieving 80.4% MIoU on the Pascal VOC 2012 dataset, 79.4% MIoU on the Cityscapes dataset, and 40.1% MIoU on the Coco-Stuff dataset.