This paper presents a novel stereo-based visual odometry approach that provides state-of-the-art results in real time, both indoors and outdoors. Our proposed method follows the procedure of computing optical flow and...
详细信息
ISBN:
(纸本)9781479930227
This paper presents a novel stereo-based visual odometry approach that provides state-of-the-art results in real time, both indoors and outdoors. Our proposed method follows the procedure of computing optical flow and stereo disparity to minimize the re-projection error of tracked feature points. However, instead of following the traditional approach of performing this task using only consecutive frames, we propose a novel and computationally inexpensive technique that uses the whole history of the tracked feature points to compute the motion of the camera. In our technique, which we call multi-frame feature integration, the features measured and tracked over all past frames are integrated into a single, improved estimate. An augmented feature set, composed of the improved estimates, is added to the optimization algorithm, improving the accuracy of the computed motion and reducing ego-motion drift. Experimental results show that the proposed approach reduces pose error by up to 65% with a negligible additional computational cost of 3.8%. Furthermore, our algorithm outperforms all other known methods on the KITTI Vision Benchmark data set.
Trust is an important aspect in human societies. It enables cooperation and provides means to estimate potential cooperation partners. Several works have addressed how the concept of trust can be transferred to comput...
详细信息
ISBN:
(纸本)9781479924813
Trust is an important aspect in human societies. It enables cooperation and provides means to estimate potential cooperation partners. Several works have addressed how the concept of trust can be transferred to computer systems. In this paper, we present an approach to calculate trust, including direct trust, confidence, and reputation, in a network consisting of agents with changing behavior. Our metrics are highly configurable for an adaption to a wide variety of systems and situations, especially Organic Computing Systems can benefit from trust by integrating it in their algorithms implementing self-organizational behavior. We evaluate the effect of direct trust and confidence together with reputation (DTCR) in comparison with using only direct trust (DT) or direct trust with confidence (DTC). Because these metrics can be configured with many parameters leading to an immense number of possible configurations we apply a heuristic optimization algorithm to find very good setups showing the highest benefits. For this evaluation, an abstract scenario is developed and applied;it consists of unreliable components from different classes of defined mean behavior. This general scenario could model many possible industrial settings out of which a few are introduced, too. Our evaluations show that reputation and direct trust are best used together with a fluent transition between them defined by the confidence. In all cases, reputation works as a corrective when direct trust information is not optimal and potentially misleading. This leads to very good results with very limited variance;particularly we show that a small number of interactions are sufficient to obtain the best results.
The performance of direct model predictive control (MPC) with reference tracking and long prediction horizons is evaluated, using the current control problem of a variable speed drive system with a voltage source inve...
详细信息
ISBN:
(纸本)9781479903368
The performance of direct model predictive control (MPC) with reference tracking and long prediction horizons is evaluated, using the current control problem of a variable speed drive system with a voltage source inverter as an illustrative example. A modified sphere decoding algorithm allows one to efficiently solve the optimization problem underlying MPC also for long horizons. For a horizon of five and a three-level inverter, for example, the computational burden is reduced by four orders of magnitude, compared to the standard exhaustive search approach. This work illustrates the performance gains that are achievable by using prediction horizons larger than one. Specifically, for long prediction horizons and a low switching frequency, the total harmonic distortion of the current is significantly lower than for space vector modulation, making direct MPC with long horizons an attractive and computationally viable control scheme.
The hardware identifiers of common wireless protocols can be exploited by adversaries for both tracking and physical device association. Rather than examining hardware identifiers in isolation, we observe that many mo...
详细信息
ISBN:
(纸本)9780769551241
The hardware identifiers of common wireless protocols can be exploited by adversaries for both tracking and physical device association. Rather than examining hardware identifiers in isolation, we observe that many modern devices are equipped with multiple wireless interfaces of different physical types, e. g. GSM and 802.11, suggesting that there exists utility in cross-protocol hardware identifier correlation. This research empirically examines the feasibility of such cross-protocol association, concentrating on correlating a GSM hardware identifier to that of the 802.11 hardware identifier on the same device. Our dataset includes 18 distinct mobile devices, with identifiers collected over time at disparate locations. We develop correlation techniques from the perspective of two adversaries: i) limited, able to observe identifiers only in time and space;and ii) a more advanced adversary with visibility into the data stream of each protocol. We first test correlation via temporal and spatial analysis using only basic signal collection, mimicking an RF collection with no decryption or data processing capability. Using a constrained optimization algorithm over temporal and spatial data to perform matching, we demonstrate increasing association accuracy over time, up to approximate to 80% in our experiments. Our second approach simulates the added capability to collect, decrypt, and reconstruct specific application protocol data, and parses the data of one protocol using search terms derived from the other. With the combined techniques, we achieve 100% accuracy and precision.
The past decade has witnessed a rapidly growing interest in decentralized algorithms for collective decision-making in cyber-physical networks. For a large variety of settings, control strategies are now known that ei...
详细信息
ISBN:
(纸本)9781479934096
The past decade has witnessed a rapidly growing interest in decentralized algorithms for collective decision-making in cyber-physical networks. For a large variety of settings, control strategies are now known that either minimize time complexity (i.e., convergence time) or optimize communication complexity (i.e., number and size of exchanged messages). Yet, little attention has beed paid to the problem of studying the inherent trade-off between time and communication complexity. Generally speaking, time-optimal algorithms are fast and robust, but require a large (and sometimes impractical) number of exchanged messages;in contrast, communication optimal algorithms minimize the amount of information routed through the network, but are slow and sensitive to link failures. In this paper we address this gap by focusing on a generalized version of the decentralized consensus problem (that includes voting and mediation) on undirected network topologies and in the presence of "infrequent" link failures. We present and rigorously analyze a tunable, semi-hierarchical algorithm, where the tuning parameter allows a graceful transition from time-optimal to communication-optimal performance (hence, allowing hybrid performance metrics), and determines the algorithm's robustness, measured as the time required to recover from a failure. An interesting feature of our algorithm is that it leads the decision-making agents to self-organize into a semi-hierarchical structure with variable-size clusters, among which information is flooded. Our results make use of a novel connection between the consensus problem and the theory of gamma synchronizers. Simulation experiments are presented and discussed.
The evolution of traditional power grids into smart grids is becoming a crucial challenge in recent years. Resources we mostly depend upon, such as oil and coal, are not going to last forever. Even renewable energies,...
详细信息
ISBN:
(纸本)9781467351942;9781467351928
The evolution of traditional power grids into smart grids is becoming a crucial challenge in recent years. Resources we mostly depend upon, such as oil and coal, are not going to last forever. Even renewable energies, always considered part of the solution, are not integrated enough to significantly contribute to the normal daily production. The concept of a new grid, designed to constantly monitor demand/supply of the system and able to send energy only where and when it is actually needed, has to be developed in order to overcome all the lacks and waste that affect the current systems. However, the transformation process needed to achieve this future vision is slow, difficult and several issues must be solved. In this paper, we use the model of our regional power grid to test how it works and to spot any potential weaknesses. We perform some complex network analysis on the entire grid in order to classify it and calculate betweenness on single nodes to spot the hubs. Using an optimization algorithm we also analyse the grid behaviour under harsh conditions and the influence of renewables in our system.
We use time-of-flight information in an iterative optimization algorithm to recover reflectance properties of a three-dimensional scene hidden behind a diffuser. We demonstrate reconstruction of wide-field images with...
详细信息
ISBN:
(纸本)9781557529732
We use time-of-flight information in an iterative optimization algorithm to recover reflectance properties of a three-dimensional scene hidden behind a diffuser. We demonstrate reconstruction of wide-field images without relying on diffuser correlation properties. (C) 2013 Optical Society of America
Degradation is an inevitable course of any manufacturing tool, machine or system. The degradation of the health state of manufacturing tools results in some sort of an ineludible maintenance action which could be both...
详细信息
ISBN:
(纸本)9780791855461
Degradation is an inevitable course of any manufacturing tool, machine or system. The degradation of the health state of manufacturing tools results in some sort of an ineludible maintenance action which could be both costly and occurring during critical production time. In many manufacturing systems, a fleet of identical machines are assigned different tasks (or products) towards satisfying production requirements. We re-introduce the maintenance-optimal resource allocation planning scheme [1] (presented in MSEC2012) and focus on the solution of the generated mathematical model. The planning scheme, denoted as Degradation Based Optimal Swapping (DBOS), incorporates the optimal implementation of swapping scheduled tasks (or products) and allocating maintenance actions throughout a finite time horizon. The objective is to minimize projected maintenance costs and/or utilize the manufacturing productivity towards prescribed logistics and/or production goals. A DBOS-specific branch-and-bound-based optimization algorithm is developed to address the complexity in the generated model. Numerical results will demonstrate the effectiveness of the algorithm in comparison to standard optimization algorithms. DBOS planning scheme coupled with the proposed algorithm succeeds in establishing substantial savings in the simulated case studies which amount up to 70% of the estimated maintenance costs in comparison to the scenario where fixed scheduling is applied.
The prediction of landslide displacement is essential for carrying out to improve the disaster warning system and reduce casualties and property losses. This study applies a novel neural network technique, extreme lea...
详细信息
ISBN:
(纸本)9781467363433
The prediction of landslide displacement is essential for carrying out to improve the disaster warning system and reduce casualties and property losses. This study applies a novel neural network technique, extreme learning machine (ELM) with kernel function, to landslide displacement prediction problem. However, the generalization performance of ELM with kernel function depends closely on the kernel types and the kernel parameters. In this paper, we use a convex combination of Gaussian kernel function and polynomial kernel function in ELM, which may use these two types of kernel functions' advantages. In order to avoid blindness and inaccuracy in parameter selection, a novel hybrid optimization algorithm based on the combination of Particle Swarm optimization (PSO) and Gravitational Search Algorithm (GSA) is used to optimize the regularization parameter C, the Gaussian kernel parameter gamma, the polynomial kernel parameter q and the mixing weight coefficient eta. The performance of our model is verified through two case studies in Baishuihe landslide and Yuhuangge landslide.
In multi-label image annotations, because each image is associated to multiple categories, the semantic terms (label classes) are not mutually exclusive. Previous research showed that such label correlations can large...
详细信息
ISBN:
(纸本)9781479928392
In multi-label image annotations, because each image is associated to multiple categories, the semantic terms (label classes) are not mutually exclusive. Previous research showed that such label correlations can largely boost the annotation accuracy. However, all existing methods only directly apply the label correlation matrix to enhance the label inference and assignment without further learning the structural information among classes. In this paper, we model the label correlations using the relational graph, and propose a novel graph structured sparse learning model to incorporate the topological constraints of relation graph in multi-label classifications. As a result, our new method will capture and utilize the hidden class structures in relational graph to improve the annotation results. In proposed objective, a large number of structured sparsity-inducing norms are utilized, thus the optimization becomes difficult. To solve this problem, we derive an efficient optimization algorithm with proved convergence. We perform extensive experiments on six multi-label image annotation benchmark data sets. In all empirical results, our new method shows better annotation results than the state-of-the-art approaches.
暂无评论