Bayesian Nonparametric Modeling for Predicting Dynamic Dependencies in Multiple Object Tracking

The paper considers the problem of tracking an unknown and time-varying number of unlabeled moving objects using multiple unordered measurements with unknown association to the objects. The proposed tracking approach integrates Bayesian nonparametric modeling with Markov chain Monte Carlo methods to estimate the parameters of each object when present in the tracking scene. In particular, we adopt the dependent Dirichlet process (DDP) to learn the multiple object state prior by exploiting inherent dynamic dependencies in the state transition using the dynamic clustering property of the DDP. Using the DDP to draw the mixing measures, Dirichlet process mixtures are used to learn and assign each measurement to its associated object identity. The Bayesian posterior to estimate the target trajectories is efficiently implemented using a Gibbs sampler inference scheme. A second tracking approach is proposed that replaces the DDP with the dependent Pitman–Yor process in order to allow for a higher flexibility in clustering. The improved tracking performance of the new approaches is demonstrated by comparison to the generalized labeled multi-Bernoulli filter.

PARAMETRIC SYNTHESIS OF A MOVING OBJECT STABILIZER

The problem of choosing the variable parameters of a stabilizer of an object which minimize an additive quadratic integral functional reflecting the complex of requirements for a closed stabilization system is considered. To solve the problem a combined method of parametric synthesis of the stabilizer, which is a sequential combination of the Sobol grid method and the Nelder-Mead method, is proposed. At the first stage of the method by applying the Sobolev grid method a working point of the closed system in the pace of its variable parameters is transferred into a neighborhood of the quality functional global minimum point. Then at the second stage the Nelder-Mead method is used to relocated the working point into a small neighborhood of the global minimum. The method proposed comprises a particular algorithm for choosing the weight coefficient of the additive quality functional as well as makes use of the stabilization object state vector main coordinates, which provide the most adequate description of its dynamic features. The properties of a mathematical model of controlled system with discontinuous stabilization process control are studied numerically. The analysis of the plots in the dynamical system state phase space indicates non-spiral approach of the system to its equilibrium state. The synthesized control is realized in the form of a sequence of switchovers.

Development of object state estimation method in intelligent decision support systems

A method of object state estimation in intelligent decision support systems (DSS) has been developed. The essence of the method is to ensure a high-quality analysis of the current state of the analyzed object. The key difference of the developed method is the use of an advanced genetic algorithm. The advanced genetic algorithm is used when constructing a fuzzy cognitive model and increases the efficiency of identifying factors and relationships between them by simultaneously finding a solution by several individuals. The objective and complete analysis is achieved using advanced fuzzy temporal models of the object state, taking into account the type of uncertainty and noise of initial data. The method also contains an improved procedure for processing initial data under a priori uncertainty, an improved procedure for training artificial neural networks and an improved procedure for topological analysis of the structure of fuzzy cognitive models. The essence of the training procedure is the training of synaptic weights of the artificial neural network, the type and parameters of the membership function, as well as the architecture of individual elements and the architecture of the artificial neural network as a whole. The method increases the efficiency of data processing at the level of 11–15 % using additional advanced procedures. The proposed method can be used in DSS of automated control systems (artillery units, special-purpose geographic information systems). It can also be used in DSS for aviation and air defense ACS, as well as in DSS for logistics ACS of the Armed Forces

Target State Classification by Attention-Based Branch Expansion Network

The intelligent laboratory is an important carrier for the development of the manufacturing industry. In order to meet the technical state requirements of the laboratory and control the particle redundancy, the wearing state of personnel and the technical state of objects are very important observation indicators in the digital laboratory. We collect human and object state datasets, which present the state classification challenge of the staff and experimental tools. Humans and objects are especially important for scene understanding, especially those existing in scenarios that have an impact on the current task. Based on the characteristics of the above datasets—small inter-class distance and large intra-class distance—an attention-based branch expansion network (ABE) is proposed to distinguish confounding features. In order to achieve the best recognition effect by considering the network’s depth and width, we firstly carry out a multi-dimensional reorganization of the existing network structure to explore the influence of depth and width on feature expression by comparing four networks with different depths and widths. We apply channel and spatial attention to refine the features extracted by the four networks, which learn "what" and "where", respectively, to focus. We find the best results lie in the parallel residual connection of the dual attention applied in stacked block mode. We conduct extensive ablation analysis, gain consistent improvements in classification performance on various datasets, demonstrate the effectiveness of the dual-attention-based branch expansion network, and show a wide range of applicability. It achieves comparable performance with the state of the art (SOTA) on the common dataset Trashnet, with an accuracy of 94.53%.

Development of a method of structural-parametric assessment of the object state

A method of structural and parametric assessment of the object state has been developed. The essence of the method is to provide an analysis of the current state of the object under analysis. The key difference of the developed method is the use of advanced procedures for processing undefined initial data, selection, crossover, mutation, formation of the initial population, advanced procedure for training artificial neural networks and rounding coordinates. The use of the method of structural-parametric assessment of the object state allows increasing the efficiency of object state assessment. An objective and complete analysis is achieved using an advanced algorithm of evolution strategies. The essence of the training procedure is the training of synaptic weights of the artificial neural network, the type and parameters of the membership function, the architecture of individual elements and the architecture of the artificial neural network as a whole. An example of using the proposed method in assessing the operational situation of the troops (forces) grouping is given. The developed method is 30–35 % more efficient in terms of the fitness of the obtained solution compared to the conventional algorithm of evolution strategies. Also, the proposed method is 20–25 % better than the modified algorithms of evolution strategies due to the use of additional improved procedures according to the criterion of fitness of the obtained solution. The proposed method can be used in decision support systems of automated control systems (artillery units, special-purpose geographic information systems). It can also be used in DSS for aviation and air defense ACS, DSS for logistics ACS of the Armed Forces of Ukraine

Independent storage of real-world object features is visual rather than verbal in nature

Previous work has shown that semantically meaningful properties of visually presented real-world objects, such as their color, their state/configuration of their parts/pose, or the features that differentiate them from other exemplars of the same category category, are stored with a high degree of independence in long-term memory (e.g., are frequently swapped or misbound across objects). But is this feature independence due to the visual representation of the objects, or because of verbal encoding? Semantically meaningful features can also be labeled by distinct words, which can be recombined to produce independent descriptions of real-world object features. Here, we directly test how much of the pattern of feature independence arises from visual vs. verbal encoding. In two experiments, during the study phase we orthogonally varied the match or mismatch of state (e.g., open/closed) and color information between images of objects and their verbal descriptions (Experiment 1) or between images of two exemplars from the same category (Experiment 2). At test, observers had to choose a previously presented image or description in a 4-AFC task. Whereas in Experiment 1 we found quite a small effect of visual-verbal mismatch on memory for images, the effect of mismatch between exemplars in Experiment 2 was dramatic: memory for a feature was reasonably good when it matched between exemplars, but dropped to chance otherwise. Importantly, this effect was observed both for color and object state independently. We conclude that independent, feature-based storage of objects in long-term memory is provided primarily by visual representations with possible minor influences of verbal encoding.

A Differentiable Extended Kalman Filter for Object Tracking Under Sliding Regime

Tactile sensing represents a valuable source of information in robotics for perception of the state of objects and their properties. Modern soft tactile sensors allow perceiving orthogonal forces and, in some cases, relative motions along the surface of the object. Detecting and measuring this kind of lateral motion is fundamental to react to possibly uncontrolled slipping and sliding of the object being manipulated. Object slip detection and prediction have been extensively studied in the robotic community leading to solutions with good accuracy and suitable for closed-loop grip stabilization. However, algorithms for object perception, such as in-hand object pose estimation and tracking algorithms, often assume no relative motion between the object and the hand and rarely consider the problem of tracking the pose of the object subjected to slipping and sliding motions. In this work, we propose a differentiable Extended Kalman filter that can be trained to track the position and the velocity of an object under translational sliding regime from tactile observations alone. Experiments with several objects, carried out on the iCub humanoid robot platform, show that the proposed approach allows achieving an average position tracking error in the order of 0.6 cm, and that the provided estimate of the object state can be used to take control decisions using tactile feedback alone. A video of the experiments is available as Supplementary Material.

Digitalization of historic buildings using modern technologies and tools

The aim of the paper is to present some experiences of using modern technologies to historical buildings digitalization. The emphasis is placed on the possibilities of spatial data collecting, as well as on subsequent 3D modelling. The paper describes the proposed survey techniques which are based on the Terrestrial Laser Scanning and photogrammetry. The authors obtained the point cloud by using the laser scanner Faro Focus 3D and dedicated software to combine scans (target based and cloud to cloud methods). The paper also provides an introduction to issues related to a method of building structure modelling based on a pointcloud. The authors proposed some computer software tools that could improve work with a point cloud and the modelling process. The resulting 3D model could be both a source of information about historical building and a sufficient base to create computational model with spatial finite elements. The subject of the case study is the St. Hubert Chapel located in Rzeszów (Poland) and built in the middle of the 18th century under the patronage of the Lubomirski family. This rococo chapel is one of the most valuable architectural monuments in the region. Historical Building Information Model (HBIM) could be helpful in analysis, visualisations and conservation practice of this precious monument. Diagnosing the current object state and assessing its technical condition could be the purpose of creating a computational FEM model.

Development of estimation and forecasting method in intelligent decision support systems

The method of estimation and forecasting in intelligent decision support systems was developed. The essence of the method is the analysis of the current state of the object and short-term forecasting of the object state. Objective and complete analysis is achieved by using improved fuzzy temporal models of the object state and an improved procedure for processing the original data under uncertainty. Also, the possibility of objective and complete analysis is achieved through an improved procedure for forecasting the object state and an improved procedure for learning evolving artificial neural networks. The concepts of fuzzy cognitive model are related by subsets of influence fuzzy degrees, arranged in chronological order, taking into account the time lags of the corresponding components of the multidimensional time series. The method is based on fuzzy temporal models and evolving artificial neural networks. The peculiarity of the method is the possibility of taking into account the type of a priori uncertainty about the object state (full awareness of the object state, partial awareness of the object state and complete uncertainty about the object state). The possibility to clarify information about the object state is achieved using an advanced training procedure. It consists in training the synaptic weights of the artificial neural network, the type and parameters of the membership function, as well as the architecture of individual elements and the architecture of the artificial neural network as a whole. The object state forecasting procedure allows conducting multidimensional analysis, consideration, and indirect influence of all components of a multidimensional time series with their different time shifts relative to each other under uncertainty. The method provides an increase in data processing efficiency at the level of 15–25% using additional advanced procedures.