Input Object Research Articles

Learning how objects function via co-analysis of interactions

We introduce a co-analysis method which learns a functionality model for an object category, e.g., strollers or backpacks. Like previous works on functionality, we analyze object-to-object interactions and intra-object properties and relations. Differently from previous works, our model goes beyond providing a functionality-oriented descriptor for a single object; it prototypes the functionality of a category of 3D objects by co-analyzing typical interactions involving objects from the category. Furthermore, our co-analysis localizes the studied properties to the specific locations, or surface patches, that support specific functionalities, and then integrates the patch-level properties into a category functionality model. Thus our model focuses on the how , via common interactions, and where , via patch localization, of functionality analysis. Given a collection of 3D objects belonging to the same category, with each object provided within a scene context, our co-analysis yields a set of proto-patches , each of which is a patch prototype supporting a specific type of interaction, e.g., stroller handle held by hand. The learned category functionality model is composed of proto-patches, along with their pairwise relations, which together summarize the functional properties of all the patches that appear in the input object category. With the learned functionality models for various object categories serving as a knowledge base, we are able to form a functional understanding of an individual 3D object, without a scene context. With patch localization in the model, functionality-aware modeling , e.g, functional object enhancement and the creation of functional object hybrids, is made possible.

OBJECT CLASSIFICATION VIA PLANAR ABSTRACTION

Abstract. We present a supervised machine learning approach for classification of objects from sampled point data. The main idea consists in first abstracting the input object into planar parts at several scales, then discriminate between the different classes of objects solely through features derived from these planar shapes. Abstracting into planar shapes provides a means to both reduce the computational complexity and improve robustness to defects inherent to the acquisition process. Measuring statistical properties and relationships between planar shapes offers invariance to scale and orientation. A random forest is then used for solving the multiclass classification problem. We demonstrate the potential of our approach on a set of indoor objects from the Princeton shape benchmark and on objects acquired from indoor scenes and compare the performance of our method with other point-based shape descriptors.

OBJECT CLASSIFICATION VIA PLANAR ABSTRACTION

We present a supervised machine learning approach for classification of objects from sampled point data. The main idea consists in first abstracting the input object into planar parts at several scales, then discriminate between the different classes of objects solely through features derived from these planar shapes. Abstracting into planar shapes provides a means to both reduce the computational complexity and improve robustness to defects inherent to the acquisition process. Measuring statistical properties and relationships between planar shapes offers invariance to scale and orientation. A random forest is then used for solving the multiclass classification problem. We demonstrate the potential of our approach on a set of indoor objects from the Princeton shape benchmark and on objects acquired from indoor scenes and compare the performance of our method with other point-based shape descriptors.

Performance assessment of thermal power plant load control system based on covariance index

This paper proposes a novel method of performance assessment for load control system of thermal power unit. Load control system is the most important multivariable control system. It is necessary to monitor and evaluate the performance of it. The performance evaluation index system based on covariance is defined, and the performance evaluation rules are given. In MATLAB, the double input and double output object model of the load control system is established, and the dynamic characteristics of the load control system are analyzed under the BF and TF mode. The simulation data, which is based on the parameters retuning, is used as the “benchmark data”, and the simulation data of different controllers are collected as “monitoring data”. For most of the time, the thermal power plant is under the coordinated control mode, and the principle and strategy of the two coordinated control are analyzed, and the engineering realization scheme is given. Operation data in different time periods of two different thermal power plants was acquisition and preprocessing respectively. The principle of selecting “benchmark data” is the minimum of pressure parameter. Two data segments were selected as “benchmark data”, performance assessment and analysis was carried on the data from other time periods. The results show that the validity and reliability of the method based on the evaluation index. In short, the data of the simulation and the load control system of power plant are used to demonstrate the effectiveness of the method.

A stochastic game net‐based model for effective decision‐making in smart environments

SummaryInternet of Things (IoT) in today's smart environments has many applications in gerontology, health care, transportation, and smart cities. Many challenges still exist in developing IoT‐based smart environments. Dynamic generation of action strategies based on multiple IoT object's input is one of the major challenges. In this paper, stochastic Petri nets and game theory are combined to create stochastic game nets (SGNs) for IoT‐based smart environment where each IoT device acts as a player with predefined place and action sets. Complete SGN will be created dynamically using individual sensor SGNs which will make IoT‐based smart environments highly interoperable and scalable. Proposed model is used to predict activities performed by two‐single person in their respective home with more than 70 sensors. Simulation results show suitability of proposed model in smart environments. Proposed model is tested for smart homes, but it can be used in any IoT‐based smart environment. Copyright © 2016 John Wiley & Sons, Ltd.

Generating Ambiguous Figure-Ground Images.

Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.

Fragment-based Visual Tracking with Multiple Representations

We present a fragment-based tracking algorithm that considers appearance information characterized by a non-parametric distribution and spatial information described by a parametric representation. We segment an input object into several fragments based on the appearance similarity and spatial distribution. Spatial distribution and appearance are important for distinguishing different fragments. We employee such information for separating an object from its background: Appearance information is described by nonparametric representation such as kernels; spatial information is characterized by Gaussians with spatial distribution of fragments. We integrate appearance and spatial information for target localization in images. The overall motion is estimated by the mean shift algorithm. This motion can deviate from the true position in the overall motion estimation because of the mean-shift drifting. We refine the estimated position based on the foreground probabilities. The proposed tracker gives better target localization results and better foreground probability images. Our experimental results demonstrate that the integration of appearance and spatial information by combining parametric and non-parametric representation is effective for tracking targets in difficult sequences.

Processing Top-k Dominating Queries in Metric Spaces

Top - k dominating queries combine the natural idea of selecting the k best items with a comprehensive “goodness” criterion based on dominance. A point p 1 dominates p 2 if p 1 is as good as p 2 in all attributes and is strictly better in at least one. Existing works address the problem in settings where data objects are multidimensional points. However, there are domains where we only have access to the distance between two objects. In cases like these, attributes reflect distances from a set of input objects and are dynamically generated as the input objects change. Consequently, prior works from the literature cannot be applied, despite the fact that the dominance relation is still meaningful and valid. For this reason, in this work, we present the first study for processing top- k dominating queries over distance-based dynamic attribute vectors, defined over a metric space . We propose four progressive algorithms that utilize the properties of the underlying metric space to efficiently solve the problem and present an extensive, comparative evaluation on both synthetic and real-world datasets.

Hierarchical Object-Based Mapping of Riverscape Units and in-Stream Mesohabitats Using LiDAR and VHR Imagery

In this paper, we present a new, semi-automated methodology for mapping hydromorphological indicators of rivers at a regional scale using multisource remote sensing (RS) data. This novel approach is based on the integration of spectral and topographic information within a multilevel, geographic, object-based image analysis (GEOBIA). Different segmentation levels were generated based on the two sources of Remote Sensing (RS) data, namely very-high spatial resolution, near-infrared imagery (VHR) and high-resolution LiDAR topography. At each level, different input object features were tested with Machine Learning classifiers for mapping riverscape units and in-stream mesohabitats. The GEOBIA approach proved to be a powerful tool for analyzing the river system at different levels of detail and for coupling spectral and topographic datasets, allowing for the delineation of the natural fluvial corridor with its primary riverscape units (e.g., water channel, unvegetated sediment bars, riparian densely-vegetated units, etc.) and in-stream mesohabitats with a high level of accuracy, respectively of K = 0.91 and K = 0.83. This method is flexible and can be adapted to different sources of data, with the potential to be implemented at regional scales in the future. The analyzed dataset, composed of VHR imagery and LiDAR data, is nowadays increasingly available at larger scales, notably through European Member States. At the same time, this methodology provides a tool for monitoring and characterizing the hydromorphological status of river systems continuously along the entire channel network and coherently through time, opening novel and significant perspectives to river science and management, notably for planning and targeting actions.

Unsupervised method of word sense disambiguation for real time associated word identification in human-robot interaction

This paper presents a system architecture and algorithm for the disambiguation problem in human-robot interaction. Currently, when we have a communication with robot, there are ambiguity problems which lead to a misunderstanding. Conventional methods only identify ambiguity in limited ways and in few contexts due to the cost of doing so. The proposed method using real Hangul input object RHINO cloud identifies ambiguous words, phrases and sentences in many contexts and suggests appropriate alternatives. And by calculating the frequency of an ambiguous word, an associated word and the theme we can obtain the associated strength. The theme which has the biggest strength is the meaning of the ambiguous word. This process reflects the fluctuation of associated words' social cultures because it searches words in real time.

Environmental Objects for Authoring Procedural Scenes

AbstractWe propose a novel approach for authoring large scenes with automatic enhancement of objects to create geometric decoration details such as snow cover, icicles, fallen leaves, grass tufts or even trash. We introduce environmental objects that extend an input object geometry with a set of procedural effects that defines how the object reacts to the environment, and by a set of scalar fields that defines the influence of the object over of the environment. The user controls the scene by modifying environmental variables, such as temperature or humidity fields. The scene definition is hierarchical: objects can be grouped and their behaviours can be set at each level of the hierarchy. Our per object definition allows us to optimize and accelerate the effects computation, which also enables us to generate large scenes with many geometric details at a very high level of detail. In our implementation, a complex urban scene of 10 000 m2, represented with details of less than 1 cm, can be locally modified and entirely regenerated in a few seconds.

Enhancing the Structural Performance of Additively Manufactured Objects Through Build Orientation Optimization

Additively manufactured objects often exhibit directional dependencies in their structure due to the layered nature of the printing process. While this dependency has a significant impact on the object's functional performance, the problem of finding the best build orientation to maximize structural robustness remains largely unsolved. We introduce an optimization algorithm that addresses this issue by identifying the build orientation that maximizes the factor of safety (FS) of an input object under prescribed loading and boundary configurations. First, we conduct a minimal number of physical experiments to characterize the anisotropic material properties. Next, we use a surrogate-based optimization method to determine the build orientation that maximizes the minimum factor safety. The surrogate-based optimization starts with a small number of finite element (FE) solutions corresponding to different build orientations. The initial solutions are progressively improved with the addition of new solutions until the optimum orientation is computed. We demonstrate our method with physical experiments on various test models from different categories. We evaluate the advantages and limitations of our method by comparing the failure characteristics of parts printed in different orientations.

Clustering and maximum likelihood search for efficient statistical classification with medium-sized databases

This paper addresses the problem of insufficient performance of statistical classification with the medium-sized database (thousands of classes). Each object is represented as a sequence of independent segments. Each segment is defined as a random sample of independent features with the distribution of multivariate exponential type. To increase the speed of the optimal Kullback–Leibler minimum information discrimination principle, we apply the clustering of the training set and an approximate nearest neighbor search of the input object in a set of cluster medoids. By using the asymptotic properties of the Kullback–Leibler divergence, we propose the maximal likelihood search procedure. In this method the medoid to check is selected from the cluster with the maximal joint density (likelihood) of the distances to the previously checked medoids. Experimental results in image recognition with artificially generated dataset and Essex facial database prove that the proposed approach is much more effective, than an exhaustive search and the known approximate nearest neighbor methods from FLANN and NonMetricSpace libraries.

Structured Volume Decomposition via Generalized Sweeping.

In this paper, we introduce a volumetric partitioning strategy based on a generalized sweeping framework to seamlessly partition the volume of an input triangle mesh into a collection of deformed cuboids. This is achieved by a user-designed volumetric harmonic function that guides the decomposition of the input volume into a sequence of two-manifold level sets. A skeletal structure whose corners correspond to corner vertices of a 2D parameterization is extracted for each level set. Corners are placed so that the skeletal structure aligns with features of the input object. Then, a skeletal surface is constructed by matching the skeletal structures of adjacent level sets. The surface sheets of this skeletal surface partition the input volume into the deformed cuboids. The collection of cuboids does not exhibit T-junctions, significantly simplifying the hexahedral mesh generation process, and in particular, it simplifies fitting trivariate B-splines to the deformed cuboids. Intersections of the surface sheets of the skeletal surface correspond to the singular edges of the generated hex-meshes. We apply our technique to a variety of 3D objects and demonstrate the benefit of the structure decomposition in data fitting.

An improved star test for implicit polynomial objects

For a given point set, a particular point is called a star if it can see all the boundary points of the set. The star test determines whether a candidate point is a star for a given set. It is a key component of some topology computing algorithms such as Connected components via Interval Analysis (CIA), Homotopy type via Interval Analysis (HIA), etc. Those algorithms decompose the input object using axis-aligned boxes, so that each box is either not intersecting or intersecting with the object and in this later case its center is a star point of the intersection. Graphs or simplicial complexes describing the topology of the objects can be obtained by connecting these star points following different rules. The star test is performed for simple primitive geometric objects, because complex objects can be constructed using Constructive Solid Geometry (CSG), and the star property is preserved via union and intersection. In this paper, we improve the method to perform the test for implicit objects. For a primitive set defined by an implicit polynomial equation, the polynomial is made homogeneous with the introduction of an auxiliary variable, thus the degree of the star condition is reduced. A linear programming optimization is introduced to further improve the performance. Several examples are given to show the experimental results of our method.

Программная реализация модуля "Создание и ведение баз данных" информационной системы проектирования технологического процесса лесозаготовок

the article examines the structural model of building information system and general laws of its functioning. The model is defined as a tuple models Fит = < F, Fxy, Fyw > whose elements form the steps performed sequentially IT(F-model of formation of multiple requests, Fxy-convert the input object in the model output, Fyw is a model of multiple output documents)

Performance tuning and sparse traversal technique for a cell‐based fetch length algorithm on a GPU

SummaryFor determining distances (fetch lengths) from points to polygons in a two‐dimensional Euclidean plane, cell‐based algorithms provide a simple and effective solution. They divide the input area into a grid of cells that cover the area. The objects are stored into the appropriate cells, and the resulting structure is used for solving the problem. When the input objects are distributed unevenly or the cell size is small, most of the cells may be empty. The representation is then called sparse. In the method proposed in this work, each cell contains information about its distance to the nonempty cells. It is then possible to skip over several empty cells at a time without memory accesses. A cell‐based fetch length algorithm is implemented on a graphics processing unit (GPU). Because control flow divergence reduces its performance, several methods to reduce the divergence are studied. While many of the explicit attempts turn out to be unsuccessful, sorting of the input data and sparse traversal are observed to greatly improve performance: compared with the initial GPU implementation, up to 45‐fold speedup is reached. The speed improvement is greatest when the map is very sparse and the points are given in a random order. Copyright © 2015 John Wiley & Sons, Ltd.

Iterative phase retrieval algorithms. I: optimization.

Two modified Gerchberg-Saxton (GS) iterative phase retrieval algorithms are proposed. The first we refer to as the spatial phase perturbation GS algorithm (SPP GSA). The second is a combined GS hybrid input-output algorithm (GS/HIOA). In this paper (Part I), it is demonstrated that the SPP GS and GS/HIO algorithms are both much better at avoiding stagnation during phase retrieval, allowing them to successfully locate superior solutions compared with either the GS or the HIO algorithms. The performances of the SPP GS and GS/HIO algorithms are also compared. Then, the error reduction (ER) algorithm is combined with the HIO algorithm (ER/HIOA) to retrieve the input object image and the phase, given only some knowledge of its extent and the amplitude in the Fourier domain. In Part II, the algorithms developed here are applied to carry out known plaintext and ciphertext attacks on amplitude encoding and phase encoding double random phase encryption systems. Significantly, ER/HIOA is then used to carry out a ciphertext-only attack on AE DRPE systems.

Phase imaging using spiral-phase diversity

We demonstrate that the two-dimensional quadrature transform property of a spiral-phase filter may be utilized for addressing the noninterferometric iterative phase imaging problem. Two intensity measurements for an unknown input object are performed in the back focal (Fourier transform) plane of a lens with and without a spiral-phase mask in the lens aperture. It is shown that the two intensity measurements along with the aperture support constraint can be used for estimating the phase of an unknown input object with an iterative algorithm. Numerical simulations are presented for comparison of the new spiral-phase diversity technique and the more standard defocus-diversity method. Experimental results for the spiral-phase diversity are also shown to illustrate the effectiveness of this approach for imaging of amplitude/phase objects.

Single- vs. multiple-instance classification

In multiple-instance (MI) classification, each input object or event is represented by a set of instances, named a bag, and it is the bag that carries a label. MI learning is used in different applications where data is formed in terms of such bags and where individual instances in a bag do not have a label. We review MI classification from the point of view of label information carried in the instances in a bag, that is, their sufficiency for classification. Our aim is to contrast MI with the standard approach of single-instance (SI) classification to determine when casting a problem in the MI framework is preferable. We compare instance-level classification, combination by noisy-or, and bag-level classification, using the support vector machine as the base classifier. We define a set of synthetic MI tasks at different complexities to benchmark different MI approaches. Our experiments on these and two real-world bioinformatics applications on gene expression and text categorization indicate that depending on the situation, a different decision mechanism, at the instance- or bag-level, may be appropriate. If the instances in a bag provide complementary information, a bag-level MI approach is useful; but sometimes the bag information carries no useful information at all and an instance-level SI classifier works equally well, or better.