Search

Autonomous driving poses numerous challenging problems, one of which is perceiving and understanding the environment. Since self-driving is safety critical and many actions taken during driving rely on the outcome of various perception algorithms (for instance all traffic participants and infrastructural objects in the vehicle's surroundings must reliably be recognized and localized), thus the perception might be considered as one of the most critical subsystems in an autonomous vehicle. Although the perception itself might further be decomposed into various sub-problems, such as object detection, lane detection, traffic sign detection, environment modeling, etc. In this paper the focus is on fusion models in general (giving support for multisensory data processing) and some related automotive applications such as object detection, traffic sign recognition, end-to-end driving models and an example of taking decisions in multi-criterial traffic situations that are complex for both human drivers and for the self-driving vehicles as well.

We demonstrate a working functional prototype of a cooperative perception system that maintains a real-time digital twin of the traffic environment, providing a more accurate and more reliable model than any of the participant subsystems—in this case, smart vehicles and infrastructure stations—would manage individually. The importance of such technology is that it can facilitate a spectrum of new derivative services, including cloud-assisted and cloud-controlled ADAS functions, dynamic map generation with analytics for traffic control and road infrastructure monitoring, a digital framework for operating vehicle testing grounds, logistics facilities, etc. In this paper, we constrain our discussion on the viability of the core concept and implement a system that provides a single service: the live visualization of our digital twin in a 3D simulation, which instantly and reliably matches the state of the real-world environment and showcases the advantages of real-time fusion of sensory data from various traffic participants. We envision this prototype system as part of a larger network of local information processing and integration nodes, i.e., the logically centralized digital twin is maintained in a physically distributed edge cloud.

The paper discusses the identification of the empirical white noise processes generated by deterministic numerical algorithms.The introduced fuzzy-random complementary approach can identify the inner hidden correlational patterns of the empirical white noise process if the process has a real hidden structure of this kind. We have shown how the characteristics of auto-correlated white noise processes change as the order of autocorrelation increases. Although in this paper we rely on random number generators to get approximate white noise processes, in our upcoming research we are planning to turn the focus on physical white noise processes in order to validate our hypothesis.

A spectacular measurement campaign was carried out on a real-world motorway stretch of Hungary with the participation of international industrial and academic partners. The measurement resulted in vehicle based and infrastructure based sensor data that will be extremely useful for future automotive R&D activities due to the available ground truth for static and dynamic content. The aim of the measurement campaign was twofold. On the one hand, road geometry was mapped with high precision in order to build Ultra High Definition (UHD) map of the test road. On the other hand, the vehicles—equipped with differential Global Navigation Satellite Systems (GNSS) for ground truth localization—carried out special test scenarios while collecting detailed data using different sensors. All of the test runs were recorded by both vehicles and infrastructure. The paper also showcases application examples to demonstrate the viability of the collected data having access to the ground truth labeling. This data set may support a large variety of solutions, for the test and validation of different kinds of approaches and techniques. As a complementary task, the available 5G network was monitored and tested under different radio conditions to investigate the latency results for different measurement scenarios. A part of the measured data has been shared openly, such that interested automotive and academic parties may use it for their own purposes.

The paper discusses the identification of the empirical, partially intelligible white noise processes generated by deterministic numerical algorithms. The introduced fuzzy‐random complemen...

Autonomous driving functions increasingly incorporate machine learning methods for perception, environment modeling and decision making. The ever-present danger of unintended behavior of neural networks has given cause for concern in safety-critical applications and has spurred research towards the establishment of certified properties. In our work we present a general approach for exploring guaranteed properties of neural networks through a specific use case. We first methodically specified several desired properties for an ideal traffic sign classifier. Then we applied a mixed integer linear programming verification method to certify (or conversely, falsify) that our pre-trained rectified linear unit (ReLU) activation network will satisfy given properties under all conditions. We established through relaxations of our initial specification that our model does in fact happen to guarantee certain (but not all) properties at a different threshold. We thus showed that it is possible to establish the degree to which non-trivial and humanly meaningful properties are inherently guaranteed by an arbitrary pixel space ReLU network. We believe this approach can be a helpful addition in comprehensively evaluating the reliability of a network via quantifying its degree of compliance to an ideal specification.

In real time evaluation systems the decision should be made in time to avoid the serious consequences. In the literature there are several techniques which aim to reduce the computational complexity of these kinds of systems. Among others the Higher Order Singular Value Decomposition (HOSVD) based reduction method is a useful tool for handling this problem. In the case when only non-exact reduction can be performed, the error calculation is also essential, because the reduction degree is based on the calculated error in these systems. In this paper the authors present the HOSVD reduction error calculation in hierarchical fuzzy systems using Mamdani-type inference and define a general formula which includes the propagated error from the previous levels of the hierarchy; in which the error bound, calculated by different ways, can be used and takes into account the case when not all the inputs contain a propagated error but only a few of them. Furthermore a greedy algorithm is presented for reduction optimization.

The paper focuses on the problem of raw data fusion in neural networks based 3D object detection architectures. Here we consider the case of autonomous driving with data from camera and LiDAR sensors. Understanding the vehicle surroundings is a crucial task in autonomous driving since any subsequent action taken is strongly dependent on it. In this paper we present an alternative method of fusing camera image information with LiDAR poinclouds at a close to raw level of abstraction. Our results suggest that our approach improves the average precision of 3D bounding box detection of cyclists (and possibly other objects) in sparse point clouds compared to the baseline architecture without low-level fusion. The proposed approach has been evaluated on the KITTI dataset containing driving scenes with corresponding camera and LiDAR data. The long-term goal of our research is to develop a neural network architecture for environment perception that fuses multi-sensor data at the earliest stages possible, thus leveraging the full benefits of possible inter-sensor synergies.

This paper describes the relation of the higher order singular value decomposition (HOSVD) based canonical form to the Hilbert-Schmidt type integral operators. This connection between the canonical form of f(x) and the integral operators determined by function f(x) is important; on the one hand it gives a new aspect for the consideration of LPV models, and on the other hand it allows for the approximation of eigenfunctions and integral operators based on a numerical reconstruction of the canonical form.

Photo sharing websites have become extremely popular with GPS-enabled digital cameras and camera phones. Seeing autumn leaves, cherry blossoms, etc. is a traditional seasonal activity. Tremendous photos about leaves and blossoms have been uploaded. The goal of our paper is to detect and rank the most scenic leaves and blossoms viewing places based on social and image features. Methods for social interestingness, color percentage, edge rate, sharpness, ranking score have been provided. The proposed methods have been validated and verified by experimental results for maple leaves in Kyoto.

To reveal the influence of global warming on glaciers, highly accurate observations of glacier movement must continue every year. It is thought that there is a close relationship between glacier moving speed and global warming. Thus, there have been precise, detailed observations of the movement of the Perito Moreno glacier in Patagonia of the Argentine Republic over the past five years. The measurement method of using GPS and an optical measuring instrument is generally used to monitor glacier movement, but the measurement accuracy attained is not optimal because of the huge size of the glacier. The measurement system used for the Perito Moreno observations, however, could realize high accuracy measurement over long distance. The measurement system is based on the principle of stereo measurement using cameras. This paper describes the results of the Perito Moreno glacier observations of this year and considers the effectiveness of glacier observation using cameras.

A time series collected by thermal cameras yields many application possibilities for security monitoring applications. The character of features involved in thermal images is different compared to the images acquired by conventional capturing devices; many methods applicable for conventional image processing cannot directly be applied for thermal images. New methods are introduced in HOSVD based representation of thermal images, and in application of resolution enhancement and data compression. The retrieval process of thermal image databases and useful feature descriptors were analyzed, as well as the special semi-automatic fusion techniques of thermal image sequences.

With GPS-enabled digital cameras and camera phones photo sharing websites have become exceptionally popular recently. Traditional seasonal activities are to admire leaves and blossoms. Tremendous photos about them have been uploaded. The goal of our paper is to detect the most scenic leaves and blossoms viewing places from Flickr based on social and image features as well as to perform their time trend analysis based on statistical and control engineering methods. Firstly, methods for social interestingness, color percentage, edge rate, sharpness, ranking score have been proposed. Secondly, methods for time trend analysis based on chi square test of independence and subspace identification have been provided. The proposed methods have been validated and verified with experimental results for maple leaves in Kyoto.

High dynamic range of illumination may cause serious distortions and other problems in viewing and further processing of digital images. In this paper a new fuzzy based tone reproduction pre-processing algorithm is introduced which may help in developing hardly or nonviewable features and content of the images making easier the further processing of it.

In the paper the authors proposed a HOSVD based approach to enhance the reconstruction of inner structures based on projections from different angles which is strongly related to the well known Radon transform. It is shown that in case of less number of projections the HOSVD based approximation applied in the projection space can significantly enhance the output obtained by the inverse Radon transform.

Complexity reduction techniques should be used in those kinds of complex systems in which the evaluation time has a critical importance. Although the hierarchical clustered structure can reduce the number of the rules in contrast to the single-staged models, a further reduction technique is recommended to use in the subsystems to improve the evaluation time. A possible method among the several available ones is the widely used Higher Order Singular Value Decomposition (HOSVD), which is used to reduce the number of the rules in fuzzy logic-based systems. The authors studied this method and a novel pre-processing procedure was developed. This procedure can be used in HOSVD rule base reduction as an offline process to calculate the new membership function values belongs to crisp inputs. Due to offline processing the operation needs are reduced at all levels and all groups of the hierarchy where the reduction is performed separately. The novel method is based on the equidistant division of the input's domain, where the division is based on the accuracy of the input factor.

The representation of data plays significant role in many applications, as for instance when performing data compression, feature extraction or enhancement, etc. In this paper we briefly mention some well known data representation forms and propose a new domain based on the so called higher order singular value decomposition (HOSVD) and wavelet transformation. It will be shown how the data can be processed by manipulating its components in this domain. Furthermore, the properties of the components as well as the applicability of the proposed approach in the field of image processing and system identification will be shown.

The paper describes an approach for data representation and processing in the so called HOSVD-DCT based domain which combines the higher order singular value decomposition (HOSVD) with the discrete cosine transformation (DCT). The key idea is to express the multivariate function by an orthonormal set of one variable specific functions and perform DCT on those components which are less significant from the application point of view in order to ensure finer grained processing. It is advantageous also in case of system identification, where the behaviour of the system can be approximated by blending locally identified models. In this case the proposed method can efficiently be applied.

The paper deals with the theoretical background of the higher order singular value decomposition (HOSVD) based canonical form of functions. Furthermore in special case it describes the relation between the canonical form and the Hilbert-Schmidt type integral operators. The described techniques have a variety of applications, e.g. image processing, system identification, data compression, filtering, etc. As an example of application from the field of intelligent systems, a tensor-product based concept is introduced useful for approximating the behavior of a strongly non-linear system by locally tuned neural network models. The proposed approach may be a useful tool for solving many kind of black-box like identification problems. The weights in the corresponding layers of the input local models are jointly expressed in tensor-product form such a way ensuring the efficient approximation. Similar concept has been used by the authors for approximating the system matrix of linear parameter varying systems in state space representation. We hope that the proposed concept could be an efficient compromised modeling view using both the analytical and heuristic approaches.

The spread of Web 2.0 has caused user-generated content explosion. Users can tag resources in order to describe and organize them. Tag clouds are visually depicted tags in order to facilitate browsing among numerous tags and resources. The goal of our paper is to improve tag clouds with vocabulary refinement and enhanced reference counts. Namely, three novel algorithms have been proposed to correct spelling and clerical errors, contract tags, and improve reference counts. The provided algorithms have been validated and verified on real-world tag clouds of a thesis portal.

Data compression and enhancement represent an important consideration in many application areas. The transmission bandwidth and storage capacity are often crucial factors. The efficiency of the processing of data in numerous cases strongly depends on the form of data representation. In the present paper a method, based on the so called higher order singular value decomposition and tensor-product transformation, is introduced for multidimensional scaling and compression of thermal images sequences. The proposed approach operates with smooth functions forming an orthonormal basis. Because of the smoothness property of these orthonormal components, the method can advantageously be utilized for the efficient compression of thermal image sequences.

Anytime systems represent a subfamily of the realtime ones. They provide continuous operation even in cases when the circumstances are changing, e.g temporary shortage of time, changing computational power, etc. As the available computation time decreases, the accuracy of the computation becomes negatively affected. Iterative algorithms support this kind of computation. Unfortunately the construction of iterative algorithms is complex and their usability is limited. In this paper a novel method for anytime systems with modular architecture is introduced. The main aim of the proposed algorithm is to extend the applicability of anytime systems. The effectiveness of the algorithm is demonstrated on a categorization problem.

The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.

In this paper we present a method for constructing a control model of loading systems based on higher order singular decomposition (HOSVD) of a tensor. Modern logistics need control systems that are able to develop and improve the material and information flow by automating the control processes. We propose the application of linear parameter varying (LPV) structure by which non-linear systems can be controlled on the basis of linear control theories. Describing the system, modeling logistic processes require many uncertain input parameters. Using the proposed method the complexity of the model can be kept on a lower level.

Process chains are a common modeling paradigm for analysis and optimization of logistic processes, and are intensively used in many practical applications. The ProC/B toolset is a collection of software tools for modeling, analysis, validation and optimization of process chains. The ProC/B models can be translated into queueing networks or Petri nets, which can be solved by effective techniques and algorithms to evaluate performance metrics. The base queueing model with Mean-Value Analysis evaluation algorithm, and their adaptations for modeling thread pool and queue limit have been verified and validated for multi-tier software systems. The goal of our work is to adapt these models and algorithms for process chains to model parallel processes and queue limit.

The main contribution of the paper is to propose a novel system for real-time measurement of the inside of crashed and non-crashed car cabins. The proposed system consists of a multi-camera system and a probe equipped with a camera and line laser module, both designed to enable the fast and easy acquisition of the car cabin from its inside. The main tasks of the development were first of all the accurate estimation of the location of the handheld probe, as well as its orientation in real-time by guaranteeing its almost free motion and rotation inside the cabin. Furthermore, the calibration of the system, the estimation of target's 3D coordinates — based on laser stripe projection and processing corresponding camera images — and finally the point-cloud processing can also be considered as main tasks to be performed. In the course of the development of these methods the main restriction was to keep the complexity as low as possible in order to guarantee the real-time functionality.

According to the current processor trend, the cores of the processors are increasing, which ensures much higher computational capacity in multithreaded environments. Schedulers are prepared for multi processor environment, but scheduling algorithms are still based on the single processor scheduling approach. In this paper the reasons of changing the current scheduling approaches and them explanations will be discussed. The main aim of this analysis is to give support by the development of new qualitative scheduling approaches.

This paper addresses the issues to establish performance models and evaluation methodologies applying the identified queue limit performance factors. The computational complexity of the novel algorithms is provided. It is demonstrated that the proposed models and algorithms can be used for performance prediction of web-based software systems in ASP.NET environment. The validity of the novel models and algorithms as well as the correctness of the performance prediction is proven with performance measurements. It is shown that the error of the suggested models and algorithms is less than the error of the original model and algorithm. These methods facilitate more efficient performance prediction of web-based software systems.

The paper discusses formulas and interpretations of the fine structure constant (FSC) and the Number Archetype 137 taking into account of our earlier results and the concept of the “undetached observer” of Pauli. A new “controlling-.observing equation” is proposed for the reinterpretation of FSC and other Number Archetypes on the basis of Hermeneutics found in W. Pauli and C. G. Jung “Correspondence”.

In most of nowadays intelligent systems (robots, vehicles, etc.) the sensing based on image processing represents an essential part. In order to be able to use these systems effectively even if the lighting conditions are not ideal, e.g. dark objects, very bright areas in the scene, etc., multiple exposure based image reproduction algorithms are highly welcome. The main aim of the paper is to introduce a novel method enabling to merge multiple exposure images and obtain a corresponding High Dynamic Range Image.

The main aim of the paper is to introduce a new representation domain advantageously usable also in the field of image processing. In this case the image is represented by polylinear functions on HOSVD basis. The paper gives an overview, how these functions can be reconstructed and how they can be applied in case of image processing. Comparing to other domains, using the proposed domain the image can be expressed by a reduced number of components (polylinear functions) by maintaining its quality. The efficiency of this representation form is demonstrated by performing an image resolution enhancement trough this new domain by maintaining its quality significantly.

Nowadays many applications require for their processing knowledge about the shapes of objects. In a lot of cases, the shapes to be acquired can have the kind of segments for which measurement is difficult, because of the occlusion problem. Shapes with such properties can be observed on crashed car bodies for example, where the deformation can be of complex shapes. In this paper a new measurement system is introduced, the aim of which is to accurately acquire the deformed parts of a car body and obtain useful information supporting car deformation analysis.

The main aim of this paper is to introduce a method for approximating surfaces given by a set of discrete points with possible additional parameters. The method uses the higher order singular value decomposition based on canonical form of two-variable TP (tensor product) functions. Except of approximation abilities of this principle, the paper focuses on the compression properties of the method, as well. The method is able to achieve high compression rate in the input data by keeping the error at remarkable lower level.

High dynamic range of illumination may cause serious distortions and other problems in viewing and further processing of digital images. In this paper a new tone reproduction preprocessing algorithm is introduced which may help in developing hardly or non-viewable features and content of the images. The method is based on the synthetization of multiple exposure images from which the dense part, i.e. regions having the maximum level of detail are included in the output image. The resulted high quality HDR image makes easier the information extraction and effectively supports the further processing of the image.

Car body deformation modeling plays a very important role in crash accident analyses, as well as in safe car body design. The determination of the energy absorbed by the deformation and the corresponding Energy Equivalent Speed can be of key importance, however their precise determination is a very difficult task. Although, using the results of crash tests, intelligent and soft methods offer an automatic way to model the crash process itself, as well as to determine the absorbed energy, the before-crash speed of the car, etc. In this paper a modeling technique and an intelligent expert system are introduced which together are able to follow the deformation process of car bodies in car crashes and to analyze the strength of the different parts without any human intervention thus significantly can contribute to the improvement of the modeling, (automatic) design, and safety Of car bodies.

Corner detection plays an important role in computer vision as well as in 3D reconstruction of a scene. With the help of the corners we can determine the most characteristic points of an object and so reconstruct them. Corners are useful in case of pattern recognition, as well. In this paper a new corner detection scheme is introduced which is based on fuzzy reasoning and applies a special local structure matrix. ©2004 IEEE.