Arbitrary Objects Research Articles

Spatiotemporal Edges for Arbitrarily Moving Video Classification in Protected and Sensitive Scenes

Classification of arbitrary moving objects including vehicles and human beings in a real environment (such as protected and sensitive areas) is challenging due to arbitrary deformation and directions caused by shaky camera and wind. This work aims at adopting a spatiotemporal approach for classifying arbitrarily moving objects. The intuition to propose the approach is that the behavior of the arbitrary moving objects caused by wind and shaky camera is inconsistent and unstable, while, for static objects, the behavior is consistent and stable. The proposed method segments foreground objects from background using the frame difference between median frame and individual frame. This step outputs several different foreground information. The method finds static and dynamic edges by subtracting Canny of foreground information from the Canny edges of respective input frames. The ratio of the number of static and dynamic edges of each frame is considered as features. The features are normalized to avoid the problems of imbalanced feature size and irrelevant features. For classification, the work uses 10-fold cross-validation to choose the number of training and testing samples, and the random forest classifier is used for the final classification of frames with static objects and arbitrarily moving objects. For evaluating the proposed method, we construct our own dataset, which contains video of static and arbitrarily moving objects caused by shaky camera and wind. The results on the video dataset show that the proposed method achieves the state-of-the-art performance (76% classification rate) which is 14% better than the best existing method.

Non-interferometric key recording applied to a joint transform cryptosystem.

In this Letter, we propose an opto-digital cryptosystem based on the joint transform correlator architecture without the need for a reference beam, phase-shifting techniques, or an additional window in the input plane. In this system, only two intensity recordings are necessary: the intensity of the key Fourier transform, and the joint power spectrum between the key and an arbitrary object in contact with a random phase mask. Combining them with the knowledge of their respective input modules, we implement a modified Gerchberg-Saxton algorithm to recover the phase associated with the encryption key. The validity of our approach is demonstrated by computer simulations and experimental results.

A Generative Deep Learning Approach for Shape Recognition of Arbitrary Objects from Phaseless Acoustic Scattering Data

A generative deep learning approach for shape recognition of an arbitrary object from its acoustic scattering properties is proposed and demonstrated. The strategy exploits deep neural networks to learn the mapping between the latent space of a 2D acoustic object and the far‐field scattering amplitudes. A neural network is designed as an adversarial autoencoder and trained via unsupervised learning to determine the latent space of the acoustic object. Important structural features of the object are embedded in lower‐dimensional latent space which supports the modeling of a shape generator and accelerates the learning in the inverse design process. The proposed inverse design uses the variational inference approach with encoder‐ and decoder‐like architecture where the decoder is composed of two pretrained neural networks: the generator and the forward model. The data‐driven framework finds an accurate solution to the ill‐posed inverse scattering problem, where nonunique solution space is overcome by the multifrequency phaseless far‐field patterns. This inverse method is a powerful design tool that doesn't require complex analytical calculation and opens up new avenues for practical realization, automatic recognition of arbitrary‐shaped submarines or large fish, and other underwater applications.

Dynamic mosaic planning for a robotic bin-packing system based on picked part and target box monitoring

This paper describes the dynamic mosaic planning method developed in the context of the PICKPLACE European project. The dynamic planner has allowed the development of a robotic system capable of packing a wide variety of objects without having to adjust to each reference. The mosaic planning system consists of three modules: First, the picked item monitoring module monitors the grabbed item to find out how the robot has picked it. At the same time, the destination container is monitored online to obtain the actual status of the packaging. To this end, we present a novel heuristic algorithm that, based on the point cloud of the scene, estimates the empty volume inside the container as empty maximal spaces (EMS). Finally, we present the development of the dynamic IK-PAL mosaic planner that allows us to dynamically estimate the optimal packing pose considering both the status of the picked part and the estimated EMSs. The developed method has been successfully integrated in a real robotic picking and packing system and validated with 7 tests of increasing complexity. In these tests, we demonstrate the flexibility of the presented system in handling a wide range of objects in a real dynamic packaging environment. To our knowledge, this is the first time that a complete online picking and packing system is deployed in a real robotic scenario allowing to create mosaics with arbitrary objects and to consider the dynamics of a real robotic packing system.

Hybrid Approach for Privacy Enhancement in Data Mining Using Arbitrariness and Perturbation

Imagine numerous clients, each with personal data; individual inputs are severely corrupt, and a server only concerns the collective, statistically essential facets of this data. In several data mining methods, privacy has become highly critical. As a result, various privacy-preserving data analysis technologies have emerged. Hence, we use the randomization process to reconstruct composite data attributes accurately. Also, we use privacy measures to estimate how much deception is required to guarantee privacy. There are several viable privacy protections; however, determining which one is the best is still a work in progress. This paper discusses the difficulty of measuring privacy while also offering numerous random sampling procedures and statistical and categorized data results. Furthermore, this paper investigates the use of arbitrary nature with perturbations in privacy preservation. According to the research, arbitrary objects (most notably random matrices) have

Spatiotemporal Edges for Arbitrarily Moving Video Classification in Protected and Sensitive Scenes

Classification of arbitrary moving objects including vehicles and human beings in a real environment (such as protected and sensitive areas) is challenging due to arbitrary deformation and directions caused by shaky camera and wind. This work aims at adopting a spatio-temporal approach for classifying arbitrarily moving objects. The intuition to propose the approach is that the behavior of the arbitrary moving objects caused by wind and shaky camera are inconsistent and unstable while for static objects, the behavior is consistent and stable. The proposed method segments foreground objects from background using the frame difference between median frame and individual frame. This step outputs several different foreground information. The method finds static and dynamic edges by subtracting Canny of foreground information from the Canny edges of respective input frames. The ratio of the number of static and dynamic edges of each frame is considered as features. The features are normalized to avoid the problems of imbalanced feature size and irrelevant features. For classification, the work uses 10-fold cross-validation to choose the number of training and testing samples and the random forest classifier is used for the final classification of frames with static objects and arbitrary movement objects. For evaluating the proposed method, we construct our own dataset, which contains video of static and arbitrarily moving objects caused by shaky camera and wind. The results on the video dataset show that the proposed method achieves the state-of-the-art performance (76% classification rate) which is 14% better than the best existing method.

A symmetry - based algorithm to determine the presence of the internal structure heterogeneity of the of a biological object

This article proposes a two-level approach for solving the problems of electrical impedance tomography of biological objects, which consists in successively applying the methods of “rough” and “fine” reconstruction to the potentials measured on the surface of the object. To perform a “rough” reconstruction procedure, it is proposed to use a method for determining the presence of heterogeneity in the internal structure of a biological object based on the symmetry algorithm. Thus, consistent localization and identification of the boundaries of the heterogeneity of the internal structure of the biological object is carried out. It is shown that when analyzing data for an arbitrary biological object, the symmetry characteristic of the type of objects under study can be taken into account, and deviations from such a characteristic symmetry will indicate deviations from the norm in the structure of a biological object.

THz Systems Exploiting Photonics and Communications Technologies

Terahertz (THz) systems open up the possibility of new applications of electromagnetic waves. Enormous bandwidths up to several terahertz enable the development of powerful spectroscopy systems that can provide insights into the structure and material of objects with micrometer resolution. New high power and compact THz time-domain spectroscopy (TDS) systems will be presented. The wide bandwidth also enables high-resolution imaging under far-field conditions to analyze arbitrary objects from a distance. In addition, a near-field system-on-a-chip imaging system is presented that achieves a resolution of 10 μm. Additionally, the application of terahertz waves presents challenges due to the low transmit power of the sources, high attenuation in free space, and the high noise figures of the receivers. These challenges can be overcome by antennas with high gain. Since - depending on the application - spatial scanning or focusing in a time-varying direction is required, beam steering is an essential component of many THz systems. In terms of communications, terahertz carrier frequencies offer wide bandwidths, enabling correspondingly high data rates of 100 Gbit/s and more. As a result, the frequency bands between 250 GHz and 450 GHz have already been identified and/or allocated for communication services and are being discussed as a component of 6G mobile communications. Concepts and demonstrations for 6G terahertz mobile communications will be presented. The high bandwidth of terahertz waves can also be used for high-accuracy indoor localization.

Coherent Image Animation Using Spatial-Temporal Correspondence

Recent studies have shown remarkable success in deep generative models for image animation of an arbitrary object. However, previous methods synthesize the animated results in a frame-by-frame manner, which is prone to producing flickering and temporally-inconsistent results. In this paper, we propose a novel self-supervised framework leveraging temporal information for image animation. Our framework processes a video clip directly instead of processing each frame independently. To achieve coherence in the animated video, we design a spatial-temporal correspondence network~(STCN) to maintain the consistency of the keypoints. Specifically, the STCN takes full advantage of temporal information to propagate the keypoints between adjacent frames, and it can be trained with a consistency of keypoints during the forward and backward process. Meanwhile, we apply 3D-CNN-based generator and discriminator in our framework to ensure coherence in the final output video. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method.

MidNet: An Anchor-and-Angle-Free Detector for Oriented Ship Detection in Aerial Images

Ship detection in aerial images remains an active yet challenging task due to its arbitrary object orientation and various aspect ratios from the bird’s-eye perspective. Most existing oriented objection detection methods rely on angular prediction or predefined anchor boxes, making these methods highly sensitive to unstable angular regression and excessive hyper-parameter setting. To address these issues, we replace the angular-based object encoding with an anchor-and-angle-free paradigm, and propose a novel detector deploying a center and four midpoints for encoding each oriented object, namely MidNet. Moreover, MidNet designs a novel symmetrical deformable convolution for enhanceing the features of midpoints, then the center and midpoints for an identical ship are adaptively matched by predicting corresponding centripetal shift and matching radius. Finally, a concise analytical geometry algorithm is proposed to calculate the ship orientation and refine the keypoints step-wisely for building precise oriented bounding boxes. On two public ship detection datasets, HRSC2016 and FGSD2021, MidNet outperforms the state-of-the-art detectors by achieving APs of 90.52% and 86.50%.

Application of the principle of information objects description formalization for the design of information protection systems

The development of information independence of the State requires the introduction of the latest technologies for analyzing, storing, processing, and transmitting information. The focus of this work is improving information security systems with limited access, in particular the development of new methods of designing such systems, which are characterized by minimal influence of the subject-designer on the design process. The object of the study is the methodology and means of designing systems for restricting and controlling physical access, as well as access to information at objects of information activity and information and telecommunication systems of Ukraine. To exclude the influence of the subject of the designer, it is necessary to improve the design process itself. In this paper, the possibility of creating an automatic design system based on the representation of protection objects in the form of objects of a common structure has been mathematically proved. Such a structure combines both telecommunication objects and objects of information activity. Changes in the legislative, regulatory, and technical bases of information protection necessary for the implementation of the proposed system have been determined, in particular, granting the State Communications Committee of Ukraine new powers that ensure the balance of interests of the customer of protection systems and executors. The possibility of formalizing the representation of data on arbitrary objects of protection is shown. This representation makes it possible to create open library semantic databases with incomplete data on the object of protection. A theoretical base has been built that makes it possible to determine the correspondence between the set of threats to the information security of the object and the unambiguous corresponding list of countermeasures. At the same time, information protection projects are distinguished by evolution and uniformity of choice of a set of means of protection to any threats to objects of arbitrary complexity

Meta-heuristic optimization of control structure and design for MMC-HVdc applications

This contribution applies meta-heuristic optimization algorithms for the optimization of controller implementations for modular multilevel converters in HVdc applications. The proposed toolbox allows optimization of parameters and structure of the controllers with arbitrary user-defined objective functions related to macroscopic as well as microscopic stability properties of the converter itself as well as within the overall system. Different meta-heuristic algorithms are compared with respect to calculation efficiency and achieved optimized values. • Interface between meta-heuristic algorithms and an arbitrary MMC control model. • Optimization of controller implementations w.r.t. time and frequency domain issues. • Evaluation of the performance of the introduced optimization framework. • Classification of the suitability of 18 algorithms for the given problem. • Validation of time domain as well as frequency domain objective functions.

Space Noncooperative Object Active Tracking With Deep Reinforcement Learning

Actively tracking an arbitrary space noncooperative object relied on visual sensor remains a challenging problem. In this article, we provide an open-source benchmark for space noncooperative object visual tracking including simulated environment, evaluation toolkit, and a position-based visual servoing (PBVS) baseline algorithm, which can facilitate the research in this topic especially for those methods based on deep reinforcement learning. We also present an end-to-end active visual tracker based on deep Q-learning, named as DRLAVT, which learns approximately optimal policy merely took color or RGBD images as input. To the best of authors knowledge, it is the first intelligent agent used for active visual tracking in aerospace domain. The experiment results show that our DRLAVT achieves an excellent robustness and real-time performance compared with the PBVS baseline, benefitted from the design of complex neural network and efficient reward function. In addition, the multiple targets training adopted in this article effectively guarantees the transferability of DRLAVT by forcing the agent to learn optimal control policy with respect to motion patterns of the target.

Light-induced vacuum micromotors based on an antimony telluride microplate

Manipulating motion of microobjects with light is indispensable in various technologies. On solid interfaces, its realizations, however, are hampered by surface friction. To resolve this difficulty, light-induced elastic waves have been recently proposed to drive microobjects against friction. Despite its expected applicability for arbitrary optical-absorptive objects, the new principle has only been tested with microsized gold plates. Herein, we validate this principle using a new material and report directional and continuous movements of a two-dimensional topological insulator (Sb2Te3) plate on an untreated microfiber surface driven by nanosecond laser pulses. The motion performance of the Sb2Te3 plate is characterized by a scanning electron microscope. We observe that the motion velocity can be controlled by tuning the average power of laser pulses. Further, by intentionally increasing the pulse repetition rate and exploiting the low thermal conductivity of Sb2Te3, we examine the thermal effects on actuation and reveal the motion instability induced by formations of microbumps on Sb2Te3 surfaces due to the Marangoni effects. Moreover, as the formed microbumps are heated to viscoelasticity states, liquid-like motion featuring asymmetry in contact angles is observed and characterized, which expands the scope of light-induced actuation of microobjects.

MVGrasp: Real-time multi-view 3D object grasping in highly cluttered environments

Nowadays robots play an increasingly important role in our daily life. In human-centered environments, robots often encounter piles of objects, packed items, or isolated objects. Therefore, a robot must be able to grasp and manipulate different objects in various situations to help humans with daily tasks. In this paper, we propose a multi-view deep learning approach to handle robust object grasping in human-centric domains. In particular, our approach takes a point cloud of an arbitrary object as an input, and then, generates orthographic views of the given object. The obtained views are finally used to estimate pixel-wise grasp synthesis for each object. We train the model end-to-end using a synthetic object grasp dataset and test it on both simulation and real-world data without any further fine-tuning. To evaluate the performance of the proposed approach, we performed extensive sets of experiments in four everyday scenarios, including isolated objects, packed items, pile of objects, and highly cluttered scenes. Experimental results show that our approach performed very well in all simulation and real-robot scenarios. More specifically, the proposed approach outperforms previous state-of-the-art approaches and achieves a success rate of >90% in all simulated and real scenarios, except for the pile of objects which is 82%. Additionally, our method demonstrated reliable closed-loop grasping of novel objects in a variety of scene configurations. The video of our experiments can be found here: https://youtu.be/c-4lzjbF7fY.

Real-time siamese multiple object tracker with enhanced proposals

Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with the number of targets or produce features with limited semantic information. To solve the aforementioned problems and allow the tracking of dozens of arbitrary objects in real-time, we propose SiamMOTION. SiamMOTION includes a novel proposal engine that produces quality features through an attention mechanism and a region-of-interest extractor fed by an inertia module and powered by a feature pyramid network. Finally, the extracted tensors enter a comparison head that efficiently matches pairs of exemplars and search areas, generating quality predictions via a pairwise depthwise region proposal network and a multi-object penalization module. SiamMOTION has been validated on five public benchmarks, achieving leading performance against current state-of-the-art trackers. Code available at: https://www.github.com/lorenzovaquero/SiamMOTION

Trace expressions and associated limits for nonequilibrium Casimir torque

We exploit fluctuational electrodynamics to present trace expressions for the torque experienced by arbitrary objects in a passive, non-absorbing, rotationally invariant background environment. Specializing to a single object, this formalism, together with recently developed techniques for calculating bounds via Lagrange duality, is then used to derive limits on the maximum Casimir torque that a single object with an isotropic electric susceptibility can experience when out of equilibrium with its surrounding environment. The maximum torque achievable at any wavelength is shown to scale in proportion to body volumes in both subwavelength (quasistatics) and macroscopic (ray optics) settings, and come within an order of magnitude of achievable torques on topology optimized bodies. Finally, we discuss how to extend the formalism to multiple bodies, deriving expressions for the torque experienced by two subwavelength particles in proximity to one another.

DA$^{2}$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping

In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects. The dataset contains about 9M pairs of parallel-jaw grasps, generated from more than 6000 objects and each labeled with various grasp dexterity measures. In addition, we propose an end-to-end dual-arm grasp evaluation model trained on the rendered scenes from this dataset. We utilize the evaluation model as our baseline to show the value of this novel and nontrivial dataset by both online analysis and real robot experiments. All data and related code will be open-sourced at https://sites.google.com/view/da2dataset.

Novel Numerical Basis Sets for Electromagnetic Field Expansion in Arbitrary Inhomogeneous Objects.

We investigated how to construct low-order subspace basis sets to accurately represent electromagnetic fields generated within inhomogeneous arbitrary objects by radio-frequency sources external to a Huygen's surface. The basis generation relies on the singular value decomposition of Green's functions integro-differential operators which makes it feasible to derive a reduced-order yet stable model. We present a detailed study of the theoretical and numerical requisites for generating such basis, and show how it can be used to calculate performance limits in magnetic resonance imaging applications. Finally, we propose a novel numerical framework for the computation of characteristic modes of arbitrary inhomogeneous objects. We validated accuracy and convergence properties of the numerical basis against a complete analytical basis in the case of a uniform spherical object. We showed that the discretization of the Huygens's surface has a minimal effect on the accuracy of the calculations, which mainly depended on the electromagnetic solver resolution and order of approximation.

A Brief Discourse on Hausdorff Dimension and Self-similarity

One often distinguishes between a line and a plane by saying that the former is one-dimensional while the latter is two-dimensional. But, what does it mean for an object to have d dimensions? Can we define a consistent notion of dimension rigorously for arbitrary objects, say a snowflake, perhaps? And must the dimension always be integer-valued? After highlighting some crucial problems that one encounters while defining a sensible notion of dimension for a certain class of objects, we attempt to answer the above questions by exploring the concept of Hausdorff dimension—a remarkable method of assigning dimension to subsets of arbitrary metric spaces. In order to properly formulate the definition and properties of the Hausdorff dimension, we review the critical measure-theoretic terminology beforehand. Finally, we discuss the notion of self-similarity and show how it often defies our quotidian intuition that dimension must always be integer-valued.