In this paper we address the problem of tracking multiple speakers via the fusion of visual and auditory information. We propose to exploit the complementary nature of these two modalities in order to accurately estimate smooth trajectories of the tracked persons, to deal with the partial or total absence of one of the modalities over short periods of time, and to estimate the acoustic status -- either speaking or silent -- of each tracked person along time. We propose to cast the problem at hand into a generative audio-visual fusion (or association) model formulated as a latent-variable temporal graphical model. This may well be viewed as the problem of maximizing the posterior joint distribution of a set of continuous and discrete latent variables given the past and current observations, which is intractable. We propose a variational inference model which amounts to approximate the joint distribution with a factorized distribution. The solution takes the form of a closed-form expectation maximization procedure. We describe in detail the inference algorithm, we evaluate its performance and we compare it with several baseline methods. These experiments show that the proposed audio-visual tracker performs well in informal meetings involving a time-varying number of people.
The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage. Current popular trackers based on tracking-by-detection framework typically draw samples in the raw image as the inputs of deep convolution networks in the first stage, which usually results in high computational burden and low running speed. In this paper, we propose a new visual tracking method using sampling deep convolutional features to address this problem. Only one cropped image around the target object is input into the designed deep convolution network and the samples is sampled on the feature maps of the network by spatial bilinear resampling. In addition, a generative adversarial network is integrated into our network framework to augment positive samples and improve the tracking performance. Extensive experiments on benchmark datasets demonstrate that the proposed method achieves a comparable performance to state-of-the-art trackers and accelerates tracking-by-detection trackers based on raw-image samples effectively.
Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent. Until now, few attempts have been done although this task is much closer to designing practical tracking systems. In this work, we propose a novel long-term tracking framework based on deep regression and verification networks. The offline-trained regression model is designed using the object-aware feature fusion and region proposal networks to generate a series of candidates and estimate their similarity scores effectively. The verification network evaluates these candidates to output the optimal one as the tracked object with its classification score, which is online updated to adapt to the appearance variations based on newly reliable observations. The similarity and classification scores are combined to obtain a final confidence value, based on which our tracker can determine the absence of the target accurately and conduct image-wide re-detection to capture the target successfully when it reappears. Extensive experiments show that our tracker achieves the best performance on the VOT2018 long-term challenge and state-of-the-art results on the OxUvA long-term dataset.
We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.
Recently, Siamese networks have drawn great attention in visual tracking community because of their balanced accuracy and speed. However, features used in most Siamese tracking approaches can only discriminate foreground from the non-semantic backgrounds. The semantic backgrounds are always considered as distractors, which hinders the robustness of Siamese trackers. In this paper, we focus on learning distractor-aware Siamese networks for accurate and long-term tracking. To this end, features used in traditional Siamese trackers are analyzed at first. We observe that the imbalanced distribution of training data makes the learned features less discriminative. During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors. During inference, a novel distractor-aware module is designed to perform incremental learning, which can effectively transfer the general embedding to the current video domain. In addition, we extend the proposed approach for long-term tracking by introducing a simple yet effective local-to-global search region strategy. Extensive experiments on benchmarks show that our approach significantly outperforms the state-of-the-arts, yielding 9.6% relative gain in VOT2016 dataset and 35.9% relative gain in UAV20L dataset. The proposed tracker can perform at 160 FPS on short-term benchmarks and 110 FPS on long-term benchmarks.
Compute and memory demands of state-of-the-art deep learning methods are still a shortcoming that must be addressed to make them useful at IoT end-nodes. In particular, recent results depict a hopeful prospect for image processing using Convolutional Neural Netwoks, CNNs, but the gap between software and hardware implementations is already considerable for IoT and mobile edge computing applications due to their high power consumption. This proposal performs low-power and real time deep learning-based multiple object visual tracking implemented on an NVIDIA Jetson TX2 development kit. It includes a camera and wireless connection capability and it is battery powered for mobile and outdoor applications. A collection of representative sequences captured with the on-board camera, dETRUSC video dataset, is used to exemplify the performance of the proposed algorithm and to facilitate benchmarking. The results in terms of power consumption and frame rate demonstrate the feasibility of deep learning algorithms on embedded platforms although more effort to joint algorithm and hardware design of CNNs is needed.
With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major issues, i.e., spatial boundary effect and temporal filter degradation. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured spatial sparsity constraints to multi-channel filers. Consequently, the process of learning spatial filters can be approximated by the lasso regularisation. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimisation framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123 and VOT2018. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.
Most of the existing tracking methods based on CNN(convolutional neural networks) are too slow for real-time application despite the excellent tracking precision compared with the traditional ones. In this paper, a fast dynamic visual tracking algorithm combining CNN based MDNet(Multi-Domain Network) and RoIAlign was developed. The major problem of MDNet also lies in the time efficiency. Considering the computational complexity of MDNet is mainly caused by the large amount of convolution operations and fine-tuning of the network during tracking, a RoIPool layer which could conduct the convolution over the whole image instead of each RoI is added to accelerate the convolution and a new strategy of fine-tuning the fully-connected layers is used to accelerate the update. With RoIPool employed, the computation speed has been increased but the tracking precision has dropped simultaneously. RoIPool could lose some positioning precision because it can not handle locations represented by floating numbers. So RoIAlign, instead of RoIPool, which can process floating numbers of locations by bilinear interpolation has been added to the network. The results show the target localization precision has been improved and it hardly increases the computational cost. These strategies can accelerate the processing and make it 7x faster than MDNet with very low impact on precision and it can run at around 7 fps. The proposed algorithm has been evaluated on two benchmarks: OTB100 and VOT2016, on which high precision and speed have been obtained. The influence of the network structure and training data are also discussed with experiments.
We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels. The inference consists of identifying trajectories of all pedestrian actors, individual activities, pairwise interactions, and collective activities, given the observed pedestrian detections. Our method uses a graphical model to represent and solve the joint tracking and recognition problems via multi-stages: (1) activity-aware tracking, (2) joint interaction recognition and occlusion recovery, and (3) collective activity recognition. We solve the where and when problem with visual tracking, as well as the who and what problem with recognition. High-order correlations among the visible and occluded individuals, pairwise interactions, groups, and activities are then solved using a hypergraph formulation within the Bayesian framework. Experiments on several benchmarks show the advantages of our approach over state-of-art methods.
Deep convolutional neural networks (CNNs) have dominated many computer vision domains because of their great power to extract good features automatically. However, many deep CNNs-based computer vison tasks suffer from lack of training data while there are millions of parameters in the deep models. Obviously, these two biphase violation facts will result in parameter redundancy of many poorly designed deep CNNs. Therefore, we look deep into the existing CNNs and find that the redundancy of network parameters comes from the correlation between features in different channels within a convolutional layer. To solve this problem, we propose the stochastic channel decorrelation (SCD) block which, in every iteration, randomly selects multiple pairs of channels within a convolutional layer and calculates their normalized cross correlation (NCC). Then a squared max-margin loss is proposed as the objective of SCD to suppress correlation and keep diversity between channels explicitly. The proposed SCD is very flexible and can be applied to any current existing CNN models simply. Based on the SCD and the Fully-Convolutional Siamese Networks, we proposed a visual tracking algorithm to verify the effectiveness of SCD.
Correlation filter (CF) based trackers have aroused increasing attentions in visual tracking field due to the superior performance on several datasets while maintaining high running speed. For each frame, an ideal filter is trained in order to discriminate the target from its surrounding background. Considering that the target always undergoes external and internal interference during tracking procedure, the trained filter should take consideration of not only the external distractions but also the target appearance variation synchronously. To this end, we present a State-aware Anti-drift Tracker (SAT) in this paper, which jointly model the discrimination and reliability information in filter learning. Specifically, global context patches are incorporated into filter training stage to better distinguish the target from backgrounds. Meanwhile, a color-based reliable mask is learned to encourage the filter to focus on more reliable regions suitable for tracking. We show that the proposed optimization problem could be efficiently solved using Alternative Direction Method of Multipliers and fully carried out in Fourier domain. Extensive experiments are conducted on OTB-100 datasets to compare the SAT tracker (both hand-crafted feature and CNN feature) with other relevant state-of-the-art methods. Both quantitative and qualitative evaluations further demonstrate the effectiveness and robustness of the proposed work.
We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a reference frame. Quantitative and qualitative experiments suggest that this task causes the model to automatically learn to track visual regions. Although the model is trained without any ground-truth labels, our method learns to track well enough to outperform the latest methods based on optical flow. Moreover, our results suggest that failures to track are correlated with failures to colorize, indicating that advancing video colorization may further improve self-supervised visual tracking.
Model update lies at the heart of object tracking. Generally, model update is formulated as an online learning problem where a target model is learned over the online training set. Our key innovation is to \emph{formulate the model update problem in the meta-learning framework and learn the online learning algorithm itself using large numbers of offline videos}, i.e., \emph{learning to update}. The learned updater takes as input the online training set and outputs an updated target model. As a first attempt, we design the learned updater based on recurrent neural networks (RNNs) and demonstrate its application in a template-based tracker and a correlation filter-based tracker. Our learned updater consistently improves the base trackers and runs faster than realtime on GPU while requiring small memory footprint during testing. Experiments on standard benchmarks demonstrate that our learned updater outperforms commonly used update baselines including the efficient exponential moving average (EMA)-based update and the well-designed stochastic gradient descent (SGD)-based update. Equipped with our learned updater, the template-based tracker achieves state-of-the-art performance among realtime trackers on GPU.
Robust visual tracking for long video sequences is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor, as this descriptor is robust to problems such as pixel-pixel misalignment, pose and illumination changes, that commonly occur in visual tracking. We model the changes in the template using a generative process. We introduce a new dynamical model for the template update using a random walk on the Riemannian manifold where the covariance descriptors lie in. This is done using log-transformed space of the manifold to free the constraints imposed inherently by positive semidefinite matrices. Modeling template variations and poses kinetics together in the state space enables us to jointly quantify the uncertainties relating to the kinematic states and the template in a principled way. Finally, the sequential inference of the posterior distribution of the kinematic states and the template is done using a particle filter. Our results shows that this principled approach can be robust to changes in illumination, poses and spatial affine transformation. In the experiments, our method outperformed the current state-of-the-art algorithm - the incremental Principal Component Analysis method, particularly when a target underwent fast poses changes and also maintained a comparable performance in stable target tracking cases.
Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications. Here we propose to use the feature learning pipeline for visual tracking. Tracking is implemented using tracking-by-detection and the resulted framework is very simple yet effective. First, online dictionary learning is used to build a dictionary, which captures the appearance changes of the tracking target as well as the background changes. Given a test image window, we extract local image patches from it and each local patch is encoded with respect to the dictionary. The encoded features are then pooled over a spatial pyramid to form an aggregated feature vector. Finally, a simple linear classifier is trained on these features. Our experiments show that the proposed powerful---albeit simple---tracker, outperforms all the state-of-the-art tracking methods that we have tested. Moreover, we evaluate the performance of different dictionary learning and feature encoding methods in the proposed tracking framework, and analyse the impact of each component in the tracking scenario. We also demonstrate the flexibility of feature learning by plugging it into Hare et al.'s tracking method. The outcome is, to our knowledge, the best tracker ever reported, which facilitates the advantages of both feature learning and structured output prediction.
In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context based on a Bayesian framework, which models the statistical correlation between the low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is posed by computing a confidence map, and obtaining the best target location by maximizing an object location likelihood function. The Fast Fourier Transform is adopted for fast learning and detection in this work. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.
The problem of robust extraction of visual odometry from a sequence of images obtained by an eye in hand camera configuration is addressed. A novel approach toward solving planar template based tracking is proposed which performs a non-linear image alignment for successful retrieval of camera transformations. In order to obtain global optimum a bio-metaheuristic is used for optimization of similarity among the planar regions. The proposed method is validated on image sequences with real as well as synthetic transformations and found to be resilient to intensity variations. A comparative analysis of the various similarity measures as well as various state-of-art methods reveal that the algorithm succeeds in tracking the planar regions robustly and has good potential to be used in real applications.
Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost. StructBoost supports nonlinear structured learning by combining a set of weak structured learners. As SSVM generalizes SVM, our StructBoost generalizes standard boosting approaches such as AdaBoost, or LPBoost to structured learning. The resulting optimization problem of StructBoost is more challenging than SSVM in the sense that it may involve exponentially many variables and constraints. In contrast, for SSVM one usually has an exponential number of constraints and a cutting-plane method is used. In order to efficiently solve StructBoost, we formulate an equivalent $ 1 $-slack formulation and solve it using a combination of cutting planes and column generation. We show the versatility and usefulness of StructBoost on a range of problems such as optimizing the tree loss for hierarchical multi-class classification, optimizing the Pascal overlap criterion for robust visual tracking and learning conditional random field parameters for image segmentation.
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.
Object tracking is a long standing problem in vision. While great efforts have been spent to improve tracking performance, a simple yet reliable prior knowledge is left unexploited: the target object in tracking must be an object other than non-object. The recently proposed and popularized objectness measure provides a natural way to model such prior in visual tracking. Thus motivated, in this paper we propose to adapt objectness for visual object tracking. Instead of directly applying an existing objectness measure that is generic and handles various objects and environments, we adapt it to be compatible to the specific tracking sequence and object. More specifically, we use the newly proposed BING objectness as the base, and then train an object-adaptive objectness for each tracking task. The training is implemented by using an adaptive support vector machine that integrates information from the specific tracking target into the BING measure. We emphasize that the benefit of the proposed adaptive objectness, named ADOBING, is generic. To show this, we combine ADOBING with seven top performed trackers in recent evaluations. We run the ADOBING-enhanced trackers with their base trackers on two popular benchmarks, the CVPR2013 benchmark (50 sequences) and the Princeton Tracking Benchmark (100 sequences). On both benchmarks, our methods not only consistently improve the base trackers, but also achieve the best known performances. Noting that the way we integrate objectness in visual tracking is generic and straightforward, we expect even more improvement by using tracker-specific objectness.