Search

Statistical dependencies between information sources are rarely known, yet in practical distributed tracking schemes, they must be taken into account in order to prevent track divergences. Chernoff fusion is well-known and universally accepted method that can address the problem of track fusion when the statistical dependence between the fusing sources is unknown. In this paper we derive the exact Chernoff fusion equations for Bernoulli Gaussian max filters. These filters have been recently derived in the framework of possibility theory, as the analog of the Bernoulli Gaussian sum filters. The main motivation for the possibilistic approach is that it effectively deals with imprecise mathematical models (e.g. dynamics, measurements) used in tracking algorithms. The paper also demonstrates the proposed possibilistic fusion scheme in the absence of knowledge about statistical dependence.

This paper proposes an online visual multi-object tracking (MOT) algorithm that resolves object appearance-reappearance and occlusion. Our solution is based on the labeled random finite set (LRFS) filtering approach, which in principle, addresses disappearance, appearance, reappearance, and occlusion via a single Bayesian recursion. However, in practice, existing numerical approximations cause reappearing objects to be initialized as new tracks, especially after long periods of being undetected. In occlusion handling, the filter's efficacy is dictated by trade-offs between the sophistication of the occlusion model and computational demand. Our contribution is a novel modeling method that exploits object features to address reappearing objects whilst maintaining a linear complexity in the number of detections. Moreover, to improve the filter's occlusion handling, we propose a fuzzy detection model that takes into consideration the overlapping areas between tracks and their sizes. We also develop a fast version of the filter to further reduce the computational time. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.

Delafossite oxide CuAlO2 has engaged great attention as a promising p-type conducting oxide. In this work, high-quality CuAlO2 single crystals with a size of several millimeters (mm) are successfully achieved with a reactive crucible melting method. The crystals are characterized by X-ray diffraction, scanning electron microscopy with energy-dispersive spectroscopy, transport measurement, and magnetic susceptibility measurement. The grown single crystals are free of contamination from a copper oxide flux. This work provides a new approach to growing high-quality delafossite oxide CuAlO2 with a few mm size.

In this paper, we propose Global Context Convolutional Network (GCCN) for visual recognition. GCCN computes global features representing contextual information across image patches. These global contextual features are defined as local maxima pixels with high visual sharpness in each patch. These features are then concatenated and utilised to augment the convolutional features. The learnt feature vector is normalised using the global context features using Frobenius norm. This straightforward approach achieves high accuracy in compassion to the state-of-the-art methods with 94.6% and 95.41% on CIFAR-10 and STL-10 datasets, respectively. To explore potential impact of GCCN on other visual representation tasks, we implemented GCCN as a based model to few-shot image classification. We learn metric distances between the augmented feature vectors and their prototypes representations, similar to Prototypical and Matching Networks. GCCN outperforms state-of-the-art few-shot learning methods achieving 99.9%, 84.8% and 80.74% on Omniglot, MiniImageNet and CUB-200, respectively. GCCN has significantly improved on the accuracy of state-of-the-art prototypical and matching networks by up to 30% in different few-shot learning scenarios.

We propose a novel approach for visual representation learning called Signature-Graph Neural Networks (SGN). SGN learns latent global structures that augment the feature representation of Convolutional Neural Networks (CNN). SGN constructs unique undirected graphs for each image based on the CNN feature maps. The feature maps are partitioned into a set of equal and non-overlapping patches. The graph nodes are located on high-contrast sharp convolution features with the local maxima or minima in these patches. The node embeddings are aggregated through novel Signature-Graphs based on horizontal and vertical edge connections. The representation vectors are then computed based on the spectral Laplacian eigenvalues of the graphs. SGN outperforms existing methods of recent graph convolutional networks, generative adversarial networks, and auto-encoders with image classification accuracy of 99.65% on ASIRRA, 99.91% on MNIST, 98.55% on Fashion-MNIST, 96.18% on CIFAR-10, 84.71% on CIFAR-100, 94.36% on STL10, and 95.86% on SVHN datasets. We also introduce a novel implementation of the state-of-the-art multi-head attention (MHA) on top of the proposed SGN. Adding SGN to MHA improved the image classification accuracy from 86.92% to 94.36% on the STL10 dataset

Determining the trajectories of cells and their lineages or ancestries in live-cell experiments are fundamental to the understanding of how cells behave and divide. This paper proposes novel online algorithms for jointly tracking and resolving lineages of an unknown and time-varying number of cells from time-lapse video data. Our approach involves modeling the cell ensemble as a labeled random finite set with labels representing cell identities and lineages. A spawning model is developed to take into account cell lineages and changes in cell appearance prior to division. We then derive analytic filters to propagate multi-object distributions that contain information on the current cell ensemble including their lineages. We also develop numerical implementations of the resulting multi-object filters. Experiments using simulation, synthetic cell migration video, and real time-lapse sequence, are presented to demonstrate the capability of the solutions.

We propose an uncertainty-aware service approach to provide drone-based delivery services called Drone-as-a-Service (DaaS) effectively. Specifically, we propose a service model of DaaS based on the dynamic spatiotemporal features of drones and their in-flight contexts. The proposed DaaS service approach consists of three components: scheduling, route-planning, and composition. First, we develop a DaaS scheduling model to generate DaaS itineraries through a Skyway network. Second, we propose an uncertainty-aware DaaS route-planning algorithm that selects the optimal Skyways under weather uncertainties. Third, we develop two DaaS composition techniques to select an optimal DaaS composition at each station of the planned route. A spatiotemporal DaaS composer first selects the optimal DaaSs based on their spatiotemporal availability and drone capabilities. A predictive DaaS composer then utilises the outcome of the first composer to enable fast and accurate DaaS composition using several Machine Learning classification methods. We train the classifiers using a new set of spatiotemporal features which are in addition to other DaaS QoS properties. Our experiments results show the effectiveness and efficiency of the proposed approach., Comment: 20 pages, 20 figures, Accepted for publication at IEEE Transactions on Services Computing

We propose flexgrid2vec, a novel approach for image representation learning. Existing visual representation methods suffer from several issues, including the need for highly intensive computation, the risk of losing in-depth structural information and the specificity of the method to certain shapes or objects. flexgrid2vec converts an image to a low-dimensional feature vector. We represent each image with a graph of flexible, unique node locations and edge distances. flexgrid2vec is a multi-channel GCN that learns features of the most representative image patches. We have investigated both spectral and non-spectral implementations of the GCN node-embedding. Specifically, we have implemented flexgrid2vec based on different node-aggregation methods, such as vector summation, concatenation and normalisation with eigenvector centrality. We compare the performance of flexgrid2vec with a set of state-of-the-art visual representation learning models on binary and multi-class image classification tasks. Although we utilise imbalanced, low-size and low-resolution datasets, flexgrid2vec shows stable and outstanding results against well-known base classifiers. flexgrid2vec achieves 96.23% on CIFAR-10, 83.05% on CIFAR-100, 94.50% on STL-10, 98.8% on ASIRRA and 89.69% on the COCO dataset., Comment: 13 pages

We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered backgrounds. The complex motion of drones, i.e., multiple degrees of freedom in three-dimensional space, causes high uncertainty. The uncertainty problem leads to inaccurate location predictions and fuzziness in scale estimations. DroTrack solves such issues by discovering the dependency between object representation and motion geometry. We implement an effective object segmentation based on Fuzzy C Means (FCM). We incorporate the spatial information into the membership function to cluster the most discriminative segments. We then enhance the object segmentation by using a pre-trained Convolution Neural Network (CNN) model. DroTrack also leverages the geometrical angular motion to estimate a reliable object scale. We discuss the experimental results and performance evaluation using two datasets of 51,462 drone-captured frames. The combination of the FCM segmentation and the angular scaling increased DroTrack precision by up to $9\%$ and decreased the centre location error by $162$ pixels on average. DroTrack outperforms all the high-speed trackers and achieves comparable results in comparison to deep learning trackers. DroTrack offers high frame rates up to 1000 frame per second (fps) with the best location precision, more than a set of state-of-the-art real-time trackers., Comment: 10 pages, 12 figures, FUZZ-IEEE 2020

This paper proposes an online multi-camera multi-object tracker that only requires monocular detector training, independent of the multi-camera configurations, allowing seamless extension/deletion of cameras without retraining effort. The proposed algorithm has a linear complexity in the total number of detections across the cameras, and hence scales gracefully with the number of cameras. It operates in the 3D world frame, and provides 3D trajectory estimates of the objects. The key innovation is a high fidelity yet tractable 3D occlusion model, amenable to optimal Bayesian multi-view multi-object filtering, which seamlessly integrates, into a single Bayesian recursion, the sub-tasks of track management, state estimation, clutter rejection, and occlusion/misdetection handling. The proposed algorithm is evaluated on the latest WILDTRACKS dataset, and demonstrated to work in very crowded scenes on a new dataset., Comment: 18 pages, 11 figures, TPAMI

In online multi-target tracking, modeling of appearance and geometric similarities between pedestrians visual scenes is of great importance. The higher dimension of inherent information in the appearance model compared to the geometric model is problematic in many ways. However, due to the recent success of deep-learning-based methods, handling of high-dimensional appearance information becomes feasible. Among many deep neural networks, Siamese network with triplet loss has been widely adopted as an effective appearance feature extractor. Since the Siamese network can extract the features of each input independently, one can update and maintain target-specific features. However, it is not suitable for multi-target settings that require comparison with other inputs. To address this issue, we propose a novel track appearance model based on the joint-inference network. The proposed method enables a comparison of two inputs to be used for adaptive appearance modeling and contributes to the disambiguation of target-observation matching and to the consolidation of identity consistency. Diverse experimental results support the effectiveness of our method. Our work was recognized as the 3rd-best tracker in BMTT MOTChallenge 2019, held at CVPR2019. The code is available at https://github.com/yyc9268/Deep-TAMA., Comment: Accepted in Information Sciences, Elsevier. 3rd Prize on 4th BMTT MOTChallenge Workshop held in CVPR2019

We consider the subleading contributions of the hadronic vacuum polarization, involving the $\pi^0\gamma^*\gamma^*$ transition form factor, to the muon anomalous magnetic moment $g-2$. Various models for the form factor, based on hadronic ansatzes and holographic principles, are considered: They are the Wess-Zumino-Witten, vector meson dominance, lowest meson dominance (one and two vector resonances) models, and AdS/QCD. The model parameters are determined by fitting the experimental data for the $e^+ e^- \rightarrow \pi^0 \gamma$ total cross section. We report numerical results of the corrections to the muon $g-2$ that the resulting values of two vector resonances model are of order-of-magntitude smaller than the one obtained from the dispersion relation., Comment: published version, 15 pages, 6 figures, 2 tables

The clockwork mechanism for gravity introduces a tower of massive graviton modes, "clockwork gravitons," with a very compressed mass spectrum, whose interaction strengths are much stronger than that of massless gravitons. In this work, we compute the lowest order contributions of the clockwork gravitons to the anomalous magnetic moment, $g-2$, of muon in the context of extra dimensional model with a five dimensional Planck mass, $M_5$. We find that the total contributions are rather insensitive to the detailed model parameters, and determined mostly by the value of $M_5$. In order to account for the current muon $g-2$ anomaly, $M_5$ should be around $0.2~{\rm TeV}$, and the size of the extra dimension has to be quite large, $l_5 \gtrsim 10^{-7}\,$m. For $M_5\gtrsim1~{\rm TeV}$, the clockwork graviton contributions are too small to explain the current muon $g-2$ anomaly. We also compare the clockwork graviton contributions with other extra dimension models such as Randall-Sundrum models or large extra dimension models. We find that the leading contributions in the small curvature limit are universal, but the cutoff-independent subleading contributions vary for different background geometries and the clockwork geometry gives the smallest subleading contributions., Comment: 14 pages, 4 figures: v3 minor corrections, to appear in PRD

This paper proposes an on-line multiple object tracking algorithm that can operate in unknown background. In a majority of multiple object tracking applications, model parameters for background processes such as clutter and detection are unknown and vary with time, hence the ability of the algorithm to adaptively learn the these parameters is essential in practice. In this work, we detail how the Generalized Labeled Multi Bernouli (GLMB) filter a tractable and provably Bayes optimal multi-object tracker can be tailored to learn clutter and detection parameters on the fly while tracking. Provided that these background model parameters do not fluctuate rapidly compared to the data rate, the proposed algorithm can adapt to the unknown background yielding better tracking performance., Comment: 12 pages, 10 figures

In multi-object tracking applications, model parameter tuning is a prerequisite for reliable performance. In particular, it is difficult to know statistics of false measurements due to various sensing conditions and changes in the field of views. In this paper we are interested in designing a multi-object tracking algorithm that handles unknown false measurement rate. Recently proposed robust multi-Bernoulli filter is employed for clutter estimation while generalized labeled multi-Bernoulli filter is considered for target tracking. Performance evaluation with real videos demonstrates the effectiveness of the tracking algorithm for real-world scenarios., Comment: 6 pages, 5 figures, 2 tables