Learning Support Correlation Filters for Visual Tracking

Design and test of a robustness evaluation system for micro-vision tracking algorithms

Industrial applications of micro-vision tracking algorithms become increasingly prevalent. Unfortunately, out-of-focused-plane (OFP) disturbances negatively impact the in-focused-plane (IFP) tracking accuracy of the micro-vision. This paper proposes a robustness evaluation system for micro-vision tracking algorithms. The relationship between IFP accuracy degradation/improvement and OFP disturbances is quantified. First, a commercial spatial nanopositioning stage (com-SNPS) and an SNPS designed in the laboratory (lab-SNPS) were employed to build a robustness evaluation system. Two SNPSs were utilized to generate both IFP trajectories and specific OFP disturbances. Capacitive sensors were used to evaluate the IFP accuracy of micro-vision tracking algorithms. Second, traditional micro-vision tracking algorithms were selected. The combination of the constant-template matching method, constant-region-of-interest (constant-ROI) retrieval method, and constant-focused-plane focusing method acted as test examples. Third, robust micro-vision tracking algorithms were developed. The variable-template matching method, variable-ROI retrieval method, and variable-focused-plane focusing method were combined. Finally, the prototype of the proposed robustness evaluation system was tested. The focused plane was determined to be a benchmark for calculating OFP disturbances. The IFP accuracy of chosen algorithms under specific OFP excitation was measured. Test results demonstrate different IFP degradation or improvement characteristics of micro-vision algorithms. This paper contributes to developing a robust micro-vision tracking algorithm.

An rs-fMRI based neuroimaging marker for adult absence epilepsy

OBJECTIVE

Approximately 20-30 % of epilepsy patients exhibit negative findings on routine magnetic resonance imaging, and this condition is known as nonlesional epilepsy. Absence epilepsy (AE) is a prevalent form of nonlesional epilepsy. This study aimed to investigate the clinical diagnostic utility of regional homogeneity (ReHo) assessed through the support vector machine (SVM) approach for identifying AE.

METHODS

This research involved 102 healthy individuals and 93 AE patients. Resting-state functional magnetic resonance imaging was employed for data acquisition in all participants. ReHo analysis, coupled with SVM methodology, was utilized for data processing.

RESULTS

Compared to healthy control individuals, AE patients demonstrated significantly elevated ReHo values in the bilateral putamen, accompanied by decreased ReHo in the bilateral thalamus. SVM was used to differentiate patients with AE from healthy control individuals based on rs-fMRI data. A composite assessment of altered ReHo in the left putamen and left thalamus yielded the highest accuracy at 81.64 %, with a sensitivity of 95.41 % and a specificity of 69.23 %.

SIGNIFICANCE

According to the results, altered ReHo values in the bilateral putamen and thalamus could serve as neuroimaging markers for AE, offering objective guidance for its diagnosis.

Scale-Aware Tracking Method with Appearance Feature Filtering and Inter-Frame Continuity

Visual object tracking is a fundamental task in computer vision that requires estimating the position and scale of a target object in a video sequence. However, scale variation is a difficult challenge that affects the performance and robustness of many trackers, especially those based on the discriminative correlation filter (DCF). Existing scale estimation methods based on multi-scale features are computationally expensive and degrade the real-time performance of the DCF-based tracker, especially in scenarios with restricted computing power. In this paper, we propose a practical and efficient solution that can handle scale changes without using multi-scale features and can be combined with any DCF-based tracker as a plug-in module. We use color name (CN) features and a salient feature to reduce the target appearance model's dimensionality. We then estimate the target scale based on a Gaussian distribution model and introduce global and local scale consistency assumptions to restore the target's scale. We fuse the tracking results with the DCF-based tracker to obtain the new position and scale of the target. We evaluate our method on the benchmark dataset Temple Color 128 and compare it with some popular trackers. Our method achieves competitive accuracy and robustness while significantly reducing the computational cost.

DATaR: Depth Augmented Target Redetection using Kernelized Correlation Filter

Unlike deep learning which requires large training datasets, correlation filter-based trackers like Kernelized Correlation Filter (KCF) use implicit properties of tracked images (circulant structure) for training in real time. Despite their popularity in tracking applications, there exists significant drawbacks of the tracker in cases like occlusions and out-of-view scenarios. This paper attempts to address some of these drawbacks with a novel RGB-D Kernel Correlation tracker in target re-detection. Our target re-detection framework not only re-detects the target in challenging scenarios but also intelligently adapts to avoid any boundary issues. Our results are experimentally evaluated using (a) standard dataset and (b) real time using the Microsoft Kinect V2 sensor. We believe this work will set the basis for improvement in the effectiveness of kernel-based correlation filter trackers and will further the development of a more robust tracker.

Multi-Task Deep Dual Correlation Filters for Visual Tracking

Correlation filters combined with deep features have delivered impressive results in visual tracking task. However, existing approaches treat deep features produced by different network layers independently, limiting their representation power. To address this issue, this paper proposes a multi-task deep dual correlation filters (MDDCF) based method for robust visual tracking. First, a new multi-task learning scheme is designed to take full advantage of the multi-level features of deep networks, where target representation with individual features is regarded as a single task. As such, the interdependencies between different levels of features can be better explored. Second, we reformulate the objective function of the dual correlation filters and propose a new alternating optimization method, allowing joint training of the correlation filters and network parameters. Third, we design an effective object template update scheme which can well capture the target appearance variations. Extensive experimental evaluations on seven benchmark datasets show that the proposed MDDCF tracker performs favorably against state-ofthe-art methods.

A Visual Tracker Offering More Solutions

Most trackers focus solely on robustness and accuracy. Visual tracking, however, is a long-term problem with a high time limitation. A tracker that is robust, accurate, with long-term sustainability and real-time processing, is of high research value and practical significance. In this paper, we comprehensively consider these requirements in order to propose a new, state-of-the-art tracker with an excellent performance. EfficientNet-B0 is adopted for the first time via neural architecture search technology as the backbone network for the tracking task. This improves the network feature extraction ability and significantly reduces the number of parameters required for the tracker backbone network. In addition, maximal Distance Intersection-over-Union is set as the target estimation method, enhancing network stability and increasing the offline training convergence rate. Channel and spatial dual attention mechanisms are employed in the target classification module to improve the discrimination of the trackers. Furthermore, the conjugate gradient optimization strategy increases the speed of the online learning target classification module. A two-stage search method combined with a screening module is proposed to enable the tracker to cope with sudden target movement and reappearance following a brief disappearance. Our proposed method has an obvious speed advantage compared with pure global searching and achieves an optimal performance on OTB2015, VOT2016, VOT2018-LT, UAV-123 and LaSOT while running at over 50 FPS.

Reliable Multi-kernel Subtask Graph Correlation Tracker

Many astonishing correlation filter trackers pay limited concentration on the tracking reliability and locating accuracy. To solve the issues, we propose a reliable and accurate cross correlation particle filter tracker via graph regularized multi-kernel multi-subtask learning. Specifically, multiple non-linear kernels are assigned to multi-channel features with reliable feature selection. Each kernel space corresponds to one type of reliable and discriminative features. Then, we define the trace of each target subregion with one feature as a single view, and their multi-view cooperations and interdependencies are exploited to jointly learn multi-kernel subtask cross correlation particle filters, and make them complement and boost each other. The learned filters consist of two complementary parts: weighted combination of base kernels and reliable integration of base filters. The former is associated to feature reliability with importance map, and the weighted information reflects different tracking contribution to accurate location. The second part is to find the reliable target subtasks via the response map, to exclude the distractive subtasks or backgrounds. Besides, the proposed tracker constructs the Laplacian graph regularization via cross similarity of different subtasks, which not only exploits the intrinsic structure among subtasks, and preserves their spatial layout structure, but also maintains the temporal-spatial consistency of subtasks. Comprehensive experiments on five datasets demonstrate its remarkable and competitive performance against state-of-the-art methods.

Robust long-term object tracking with adaptive scale and rotation estimation

In this article, a robust long-term object tracking algorithm is proposed. It can tackle the challenges of scale and rotation changes during the long-term object tracking for security robots. Firstly, a robust scale and rotation estimation method is proposed to deal with scale changes and rotation motion of the object. It is based on the Fourier–Mellin transform and the kernelized correlation filter. The object’s scale and rotation can be estimated in the continuous space, and the kernelized correlation filter is used to improve the estimation accuracy and robustness. Then a weighted object searching method based on the histogram and the variance is introduced to handle the problem that trackers may fail in the long-term object tracking (due to semi-occlusion or full occlusion). When the tracked object is lost, the object can be relocated in the whole image using the searching method, so the tracker can be recovered from failures. Moreover, two other kernelized correlation filters are learned to estimate the object’s translation and the confidence of tracking results, respectively. The estimated confidence is more accurate and robust using the dedicatedly designed kernelized correlation filter, which is employed to activate the weighted object searching module, and helps to determine whether the searching windows contain objects. We compare the proposed algorithm with state-of-the-art tracking algorithms on the online object tracking benchmark. The experimental results validate the effectiveness and superiority of our tracking algorithm.

Low-Rank Multi-Channel Features for Robust Visual Object Tracking

Kernel correlation filters (KCF) demonstrate significant potential in visual object tracking by employing robust descriptors. Proper selection of color and texture features can provide robustness against appearance variations. However, the use of multiple descriptors would lead to a considerable feature dimension. In this paper, we propose a novel low-rank descriptor, that provides better precision and success rate in comparison to state-of-the-art trackers. We accomplished this by concatenating the magnitude component of the Overlapped Multi-oriented Tri-scale Local Binary Pattern (OMTLBP), Robustness-Driven Hybrid Descriptor (RDHD), Histogram of Oriented Gradients (HoG), and Color Naming (CN) features. We reduced the rank of our proposed multi-channel feature to diminish the computational complexity. We formulated the Support Vector Machine (SVM) model by utilizing the circulant matrix of our proposed feature vector in the kernel correlation filter. The use of discrete Fourier transform in the iterative learning of SVM reduced the computational complexity of our proposed visual tracking algorithm. Extensive experimental results on Visual Tracker Benchmark dataset show better accuracy in comparison to other state-of-the-art trackers.

Robust Individual-Cell/Object Tracking via PCANet Deep Network in Biomedicine and Computer Vision

Tracking individual-cell/object over time is important in understanding drug treatment effects on cancer cells and video surveillance. A fundamental problem of individual-cell/object tracking is to simultaneously address the cell/object appearance variations caused by intrinsic and extrinsic factors. In this paper, inspired by the architecture of deep learning, we propose a robust feature learning method for constructing discriminative appearance models without large-scale pretraining. Specifically, in the initial frames, an unsupervised method is firstly used to learn the abstract feature of a target by exploiting both classic principal component analysis (PCA) algorithms with recent deep learning representation architectures. We use learned PCA eigenvectors as filters and develop a novel algorithm to represent a target by composing of a PCA-based filter bank layer, a nonlinear layer, and a patch-based pooling layer, respectively. Then, based on the feature representation, a neural network with one hidden layer is trained in a supervised mode to construct a discriminative appearance model. Finally, to alleviate the tracker drifting problem, a sample update scheme is carefully designed to keep track of the most representative and diverse samples during tracking. We test the proposed tracking method on two standard individual cell/object tracking benchmarks to show our tracker's state-of-the-art performance.