摘要 :
Based on the optimal fusion criterion weighted by matrices in the linear minimum variance sense, an optimal information fusion steady- state Kalman filter is given for the discrete time- invariant linear stochastic control system ...
展开
Based on the optimal fusion criterion weighted by matrices in the linear minimum variance sense, an optimal information fusion steady- state Kalman filter is given for the discrete time- invariant linear stochastic control system measured by multiple sensors with coloured measurement noises, which is equivalent to an optimal information fusion steady- state Kalman predictor with a two- layer fusion structure for system with correlated noises. Furthermore, the steady- state optimal fusion predictor can be obtained only by fusing once after all local subsystems enter the steady- state predictions. The solution of steady- state prediction error cross- covariance matrix between any two subsystems can be obtained by iteration with an arbitratry initial value, whose convergence is proved. Applying it to a tracking system with three sensors shows its effectiveness.
收起
摘要 :
This paper proposes mechanisms to efficiently address critical tasks in the operation of cluster-based target tracking, namely: (1) measurement integration, (2) inclusion/exclusion in the cluster, and (3) cluster head rotation. Th...
展开
This paper proposes mechanisms to efficiently address critical tasks in the operation of cluster-based target tracking, namely: (1) measurement integration, (2) inclusion/exclusion in the cluster, and (3) cluster head rotation. They all employ distributed probabilistic tools designed to take into account wireless camera networks (WCNs) capabilities and constraints. They use efficient and distribution-friendly representations and metrics in which each node contributes to the computation in each mechanism without requiring any prior knowledge of the rest of the nodes. These mechanisms are integrated in two different distributed schemes so that they can be implemented in constant time regardless of the cluster size. Their experimental validation showed that the proposed mechanisms and schemes significantly reduce energy consumption (55 percent) and computational burden with respect to existing methods.
收起
摘要 :
A track-to-track fusion method to combine local estimates modeled with Gaussian mixture model is proposed for tracking a re-entry ballistic vehicle. An arbitrary power of a Gaussian mixture distribution is approximated with Gaussi...
展开
A track-to-track fusion method to combine local estimates modeled with Gaussian mixture model is proposed for tracking a re-entry ballistic vehicle. An arbitrary power of a Gaussian mixture distribution is approximated with Gaussian mixture model using first order expansion approximation, which leads to an analytical fusion equation for approximate Chernoff fusion. In the end, we verify the effectiveness of the proposed fusion algorithm with a series of Monte Carlo simulations. (C) 2016 Elsevier Masson SAS. All rights reserved.
收起
摘要 :
A great deal of attention is currently focused on multisensor data fusion. Multisensor data fusion combines data from multiple sensor systems to achieve improved performance and provide more inferences than could be achieved using...
展开
A great deal of attention is currently focused on multisensor data fusion. Multisensor data fusion combines data from multiple sensor systems to achieve improved performance and provide more inferences than could be achieved using a single sensor system. One of the most important aspects of it is track-to-track-association. This paper develops a fuzzy data fusion approach to solve the problem of track-to-track association and track fusion in distributed multisensor-multitarget multiple-attribute environments in overlapping coverage scenarios. The proposed approach uses the fuzzy clustering means algorithm to reduce the number of target tracks and associate duplicate tracks by determining the degree of membership for each target track. It uses current sensor data and the known sensor resolutions for track-to-track association, track fusion, and the selection of the most accurate sensor for tracking fused targets. Numerical results based on Monte Carlo simulations are presented. The results show that the proposed approach significantly reduces the computational complexity and achieves considerable performance improvement compared to Euclidean clustering. We also show that the performance of the proposed approach is reasonable close to the performance of the Bayesian minimum mean square error criterion.
收起
摘要 :
The tracking of objects using distributed multiple sensors is an important field of work in the application areas of autonomous robotics, military applications, and mobile systems. In this survey, we review a number of computation...
展开
The tracking of objects using distributed multiple sensors is an important field of work in the application areas of autonomous robotics, military applications, and mobile systems. In this survey, we review a number of computationally intelligent methods that are used for developing robust tracking schemes through sensor data fusion. The survey discusses the application of the various algorithms at different layers of the JDL model and highlights the weaknesses and strengths of the approaches in the context of different applications
收起
摘要 :
Occlusion and lack of visibility in crowded and cluttered scenes make it difficult to track individual people correctly and consistently, particularly in a single view. We present a multi-view approach to solving this problem. In ...
展开
Occlusion and lack of visibility in crowded and cluttered scenes make it difficult to track individual people correctly and consistently, particularly in a single view. We present a multi-view approach to solving this problem. In our approach we neither detect nor track objects from any single camera or camera pair; rather evidence is gathered from all the cameras into a synergistic framework and detection and tracking results are propagated back to each view. Unlike other multi-view approaches that require fully calibrated views our approach is purely image-based and uses only 2D constructs. To this end we develop a planar homographic occupancy constraint that fuses foreground likelihood information from multiple views, to resolve occlusions and localize people on a reference scene plane. For greater robustness this process is extended to multiple planes parallel to the reference plane in the framework of plane to plane homologies. Our fusion methodology also models scene clutter using the Schmieder and Weathersby clutter measure, which acts as a confidence prior, to assign higher fusion weight to views with lesser clutter. Detection and tracking are performed simultaneously by graph cuts segmentation of tracks in the space-time occupancy likelihood data. Experimental results with detailed qualitative and quantitative analysis, are demonstrated in challenging multi-view, crowded scenes.
收起
摘要 :
Local tracking in clutter initialises and updates true and false tracks. Local false track discrimination uses a track quality measure to confirm most of the true tracks, and to terminate most of the false tracks. Confirmed tracks...
展开
Local tracking in clutter initialises and updates true and false tracks. Local false track discrimination uses a track quality measure to confirm most of the true tracks, and to terminate most of the false tracks. Confirmed tracks are transmitted for track-to-track fusion. The sets of tracks being considered for fusion may contain both true and false tracks. The authors assume that each track information also includes the track quality measure in the form of the probability of target existence information. This information is used for additional false track discrimination at the fusion centre. They also use this information to enhance the track-to-track association. They propose three different strategies for track fusion with the target existence information: the `single target', the `joint multitarget' and the `linear multitarget'.
收起
摘要 :
The paper proposes a method to detect failures in object tracking. Detection is done with the help of two types of errors, namely jump and stop errors. Jump errors occur when an abrupt change in object's motion is observed, wherea...
展开
The paper proposes a method to detect failures in object tracking. Detection is done with the help of two types of errors, namely jump and stop errors. Jump errors occur when an abrupt change in object's motion is observed, whereas stop errors occur when a moving object remains stationary for longer duration at any point. In our framework, moving objects are first tracked using well-known trackers and their trajectories are obtained. Discrepancies between trajectories are measured. We have shown that the proposed method can be reliable for detection of tracking failures. This can help to find error-free trajectories that are essential in various computer vision tasks. We have also shown that the tracking performance can be further improved while processing the output trajectories without much knowledge about the underlying tracking algorithms. The effect of tracking failure is investigated to identify erroneous trajectories. It has been observed that when a tracker fails, velocity profile of the moving object usually changes significantly. Based on this hypothesis, erroneous trajectories are detected and a set of error-free trajectories are marked and grouped. Two recently proposed tracking algorithms, namely real-time compressive tracker (CT) and real-time L1-tracker (L1APG), have been used to track the objects. We have tested our framework on five publicly available datasets containing more than 300 trajectories. Our experiments reveal that average classification rate of erroneous trajectories can be as high as 80.4% when objects are tracked using L1APG tracker. Accuracy can be as high as 81.2% when applied on trajectories obtained using CT tracker. Average accuracy of tracking increases significantly (19.2% with respect to L1APG tracker and 24.8% with respect to CT tracker) when the decision is taken using a fused framework.
收起
摘要 :
Tracking people and objects is a fundamental stage toward many video surveillance systems, for which various trackers have been specifically designed in the past decade. However, it comes to a consensus that there is not any speci...
展开
Tracking people and objects is a fundamental stage toward many video surveillance systems, for which various trackers have been specifically designed in the past decade. However, it comes to a consensus that there is not any specific tracker that works sufficiently well under all circumstances. Therefore, one potential solution is to deploy multiple trackers, with a tracker output fusion step to boost the overall performance. Subsequently, an intelligent fusion design, yet general and orthogonal to any specific tracker, plays a key role in successful tracking. In this paper, we propose a symbiotic tracker ensemble toward a unified tracking framework, which is based on only the output of each individual tracker, without knowing its specific mechanism. In our approach, all trackers run in parallel, without requiring any details for tracker running, which means that all trackers are treated as black boxes. The proposed symbiotic tracker ensemble framework aims at learning an optimal combination of these tracking results. Our method captures the relation among individual trackers robustly from two aspects. First, the consistency between two successive frames is calculated for each tracker. Then, the pair-wise correlation among different trackers is estimated in the new coming frame by a graph-propagation process. Experimental results on the Caremedia dataset and the Caviar dataset demonstrate the effectiveness of the proposed method, with comparisons to several state-of-the-art methods.
收起
摘要 :
Driver assistance systems have increasingly relied on more sensors for new functions. As advanced driver assistance system continue to improve towards automated driving, new methods are required for processing the data in an effic...
展开
Driver assistance systems have increasingly relied on more sensors for new functions. As advanced driver assistance system continue to improve towards automated driving, new methods are required for processing the data in an efficient and economical manner from the sensors for such complex systems. The detection of dynamic objects is one of the most important aspects required by advanced driver assistance systems and automated driving. In this thesis, an environment model approach for the detection of dynamic objects is presented in order to realize an effective method for sensor data fusion. A scalable high-level fusion architecture is developed for fusing object data from several sensors in a single system, where processing occurs in three levels: sensor, fusion and application. A complete and consistent object model which includes the object's dynamic state, existence probability and classification is defined as a sensor-independent and generic interface for sensor data fusion across all three processing levels. Novel algorithms are developed for object data association and fusion at the fusion-level of the architecture. An asynchronous sensor-to-global fusion strategy is applied in order to process sensor data immediately within the high-level fusion architecture, giving driver assistance systems the most up-to-date information about the vehicle's environment. Track-to-track fusion algorithms are uniquely applied for dynamic state fusion, where the information matrix fusion algorithm produces results comparable to a low-level central Kalman filter approach. The existence probability of an object is fused using a novel approach based on the Dempster-Shafer evidence theory, where the individual sensor's existence estimation performance is considered during the fusion process. A similar novel approach with the Dempster-Shafer evidence theory is also applied to the fusion of an object's classification. The developed high-level sensor data fusion architecture and its algorithms are evaluated using a prototype vehicle equipped with 12 sensors for surround environment perception. A thorough evaluation of the complete object model is performed on a closed test track using vehicles equipped with hardware for generating an accurate ground truth. Existence and classification performance is evaluated using labeled data sets from real traffic scenarios. The evaluation demonstrates the accuracy and effectiveness of the proposed sensor data fusion approach. The work presented in this thesis has additionally been extensively used in several research projects as the dynamic object detection platform for automated driving applications on highways in real traffic.
收起
原文获取