Robust Tracking Algorithm Research Articles

PCIAS

Measuring Instantaneous Angular Speed (IAS) of rotating objects is ubiquitous in industry and our daily life. Engineers diagnose the operation condition of engines with IAS. Anemometers obtain instantaneous wind speed with the IAS of rotating cups. Traditional IAS measurement systems have their limitations in the aspects of installation, accuracy, and cost. In this paper, we propose PCIAS, a system that uses acoustic signals of a smartphone to measure IAS of rotating objects in a contactless manner. PCIAS covers a pretty large IAS measurement range (the numerical interval of IAS) from 10 Revolutions Per Minute (RPM) to 10000 RPM, which outperforms almost all existing Commercial-Off-The-Shelf (COTS) IAS meters. In PCIAS, we first choose an appropriate measurement range according to applications. We then use the smartphone to collect acoustic signals backscattered or generated by the object. Next, we extract acoustic features of the object to eliminate interferences from the environment. After that, we propose a robust tracking algorithm to estimate IAS by matching cycle time length of acoustic features adaptively. We build two testbeds to evaluate the accuracy and the robustness of our system in different IAS ranges. Our experiments show that PCIAS achieves a relative accuracy of more than 92% in the low IAS range, more than 94% in the middle IAS range, and more than 96% in the high IAS range. Finally, We exhibit two typical cases to demonstrate the practical use of our system.

A novel framework for robust long-term object tracking in real-time

In this paper, we study the problem of long-term object tracking, where the object may become fully occluded or leave/re-enter the camera view. In this setting, the drifting due to significant appearance change of the object and the recovery from tracking failure are two major issues. To address these two issues, we propose an intelligent framework to integrate a tracker and detector, wherein the tracker module is used to validate the output of the detector with online learning. The key insight of our work is the importance of how a tracker and detector are integrated, which has received little attention in the literature. Based on our proposed framework, a correlation filter-based tracker and a cascaded detector are utilized to implement a robust long-term tracking algorithm. Extensive experimental results show that the proposed framework performs better compared to specific choices of tracker/detector modules and to state-of-the-art tracking-and-detection methods. Additionally, we extend the proposed system with a centralized strategy to achieve cooperative tracking using multiple cameras in a laboratory setting.

Sea surface object tracking for USV with spatio-temporal context fusion

As an important component of unmanned surface vessel environment awareness, visual perception provides very important external information for intelligent control of USV. Accurate, robust and real-time sea surface object tracking algorithms can effectively improve the intelligence level of USV. Sea surface object tracking faces several unique challenges: the object scale changes greatly, the object perspective changes greatly, and the object jitters drastically. In order to solve the three difficulties encountered in the above sea object tracking task, this paper proposed an object tracking algorithm with spatio-temporal context fusion. This algorithm combines the image space context information of the multi-scale detection of deep network and the correlated filter tracking video time context information. It is a real-time, accurate and robust object tracking. Finally, using the image data of the USV in the actual operation scene in the East China Sea and South China Sea as the test set of the tracking algorithm, the effectiveness of the tracking algorithm is verified.

Fuzzy Logic-based Adaptive Extended Kalman Filter Algorithm for GNSS Receivers

<p class="p1">Designing robust carrier tracking algorithms that are operable in strident environmental conditions for global navigation satellite systems (GNSS) receivers is the discern task. Major contribution in weakening the GNSS signals are ionospheric scintillations. The effect of scintillation can be known by amplitude scintillation index <em>S</em>4 and phase scintillation index sf parameters. The proposed fuzzy logic based adaptive extended Kalman filter (AEKF) method helps in modelling the signal amplitude and phase dynamically by Auto-Regressive Exogenous (ARX) analysis using Sugeno fuzzy logic inference system. The algorithm gave good performance evaluation for synthetic Cornell scintillation monitor (CSM) data and real-time strong scintillated PRN 12 L1 C/A data on October 24<span class="s1"><sup>th</sup></span>, 2012 around 21:30 h, Brazil local time collected by GNSS software navigation receiver (GSNR’x). Fuzzy logic algorithm is implemented for selecting the ARX orders based on estimated amplitude and phase ionospheric scintillation observations. Fuzzy based AEKF algorithm has the capability to mitigate ionospheric scintillations under both geomagnetic quiet and disturbed conditions.</p>

Correlation Tracking via Self-Adaptive Fusion of Multiple Features

Correlation filter (CF) based tracking algorithms have shown excellent performance in comparison to most state-of-the-art algorithms on the object tracking benchmark (OTB). Nonetheless, most CF based tracking algorithms only consider limited single channel feature, and the tracking model always updated from frame-by-frame. It will generate some erroneous information when the target objects undergo sophisticated scenario changes, such as background clutter, occlusion, out-of-view, and so forth. Long-term accumulation of erroneous model updating will cause tracking drift. In order to address problems that are mentioned above, in this paper, we propose a robust multi-scale correlation filter tracking algorithm via self-adaptive fusion of multiple features. First, we fuse powerful multiple features including histogram of oriented gradients (HOG), color name (CN), and histogram of local intensities (HI) in the response layer. The weights assigned according to the proportion of response scores that are generated by each feature, which achieve self-adaptive fusion of multiple features for preferable feature representation. In the meantime the efficient model update strategy is proposed, which is performed by exploiting a pre-defined response threshold as discriminative condition for updating tracking model. In addition, we introduce an accurate multi-scale estimation method integrate with the model update strategy, which further improves the scale variation adaptability. Both qualitative and quantitative evaluations on challenging video sequences demonstrate that the proposed tracker performs superiorly against the state-of-the-art CF based methods.

Robust Visual Tracking with Discrimination Dictionary Learning

It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to represent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary atoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries can learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates. Additionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with l1 constraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art tracking algorithms.

Robust tracking via weighted online extreme learning machine

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative solution to the problem of linear equations. Therefore, ELM offers the satisfying classification performance and fast training time than other discriminative models in tracking. However, the original ELM method often suffers from the problem of the imbalanced classification distribution, which is caused by few target objects, leading to under-fitting and more background samples leading to over-fitting. Worse still, it reduces the robustness of tracking under special conditions including occlusion, illumination, etc. To address above problems, in this paper, we present a robust tracking algorithm. First, we introduce the local weight matrix that is the dynamic creation from the data distribution at the current frame in the original ELM so as to balance between the empirical and structure risk, and fully learn the target object to enhance the classification performance. Second, we improve it to the incremental learning method ensuring tracking real-time and efficient. Finally, the forgetting factor is used to strengthen the robustness for changing of the classification distribution with time. Meanwhile, we propose a novel optimized method to obtain the optimal sample as the target object, which avoids tracking drift resulting from noisy samples. Therefore, our tracking method can fully learn both of the target object and background information to enhance the tracking performance, and it is evaluated in 20 challenge image sequences with different attributes including illumination, occlusion, deformation, etc., which achieves better performance than several state-of-the-art methods in terms of effectiveness and robustness.

Robust lane tracking algorithm for forward target detection of automated driving vehicles

Detection of a primary forward target is one of the most important factors in a longitudinal control system of automated driving vehicles. If there is no special event such as a lane change, a lane detected by a vision sensor can be deemed as a predicted driving path of the ego vehicle. Based on this, it is possible to determine the state of the primary forward target vehicle accurately using the detected lanes. However, malfunction of vision sensors can induce unrecognized and misrecognized lane detection problems on account of internal/external environment factors. Furthermore, if a detection point is getting farther from the subject vehicle, the detection accuracy is getting lower because of inaccuracy of lane model parameters. To solve these problems, a novel method of lane tracking has been investigated. First, an integrated sensor module that combines a virtual sensor and a vision sensor has been developed. The virtual sensor is combined kinematic and dynamic vehicle model to be used in the full-speed range. Second, a lane estimator to improve lane detection accuracy at a long distance has been developed. The lane width in the public road can be assumed to be constant in the same road type. Based on this assumption, the clothoid parameters can be restored and consequently improve the lane detection accuracy. The performance of the proposed algorithm was verified by actual vehicle tests on public roads with manual driving and on proving ground with an automated driving system. The proposed algorithm has been compared with a conventional method which is based on in-vehicle yaw rate sensor. The test results have shown significant improvement of lane tracking performance over the conventional method.

Robust Offset-Free Speed Tracking Controller of Permanent Magnet Synchronous Generator for Wind Power Generation Applications

This article presents a robust speed tracking algorithm for a permanent magnet synchronous generator utilized for wind power generation systems, considering the machine parameter and load uncertainties. There are two major contributions: (a) a disturbance observer is designed to exponentially estimate disturbances from the model-plant mismatches and severe load torque variations, and (b) it is included in a nonlinear cascade-type proportional speed tracking controller to establish the performance recovery and offset-free properties without the use of tracking error integrators. A simulation result numerically verifies the effectiveness of the proposed technique, where the PowerSIM software emulates a wind power generation system.

Robust Magnetic Tracking of Subsea Cable by AUV in the Presence of Sensor Noise and Ocean Currents

To inspect subsea cables, an autonomous underwater vehicle (AUV) with two triaxial magnetometers is usually assigned to track the cable route. In this paper, a novel two-layer framework synthesizing antinoise cable localization and robust tracking algorithm is proposed to guide an AUV to track subsea cables in the presence of sensor noise and ocean currents. First, an analytic formulation for the cable localization using two magnetometers is derived, and then a dedicated magnetic line-of-sight (LOS) guidance is built based on the horizontal offset between the AUV and the cable. Second, a novel antinoise method by estimating the horizontal offset is integrated into the LOS guidance law to reduce the negative effects of magnetic noise in the kinematic layer. Subsequently, in the dynamic layer, a simplified yet robust feedback controller with reduced implementation complexity is designed to track the desired guidance profiles, such that the AUV is able to track subsea cables in the presence of sensor noise and ocean currents. In addition, the capability of dynamic control laws accounting for ocean currents is analyzed in the amplitude–frequency domain. Finally, numerical studies illustrate the antinoise and robust performance of the proposed two-layer framework for subsea cable tracking.

Visual object tracking via the local soft cosine similarity

In this paper, we propose a robust visual tracking algorithm based on soft similarity under the Bayesian framework. Firstly, we propose a Local Soft Similarity based on Soft Cosine Measure (L3SCM) that measures the soft similarity between two vectors of features in Vector Space Model (VSM) by taking into account dependencies between these features. Secondly, we model the motion model component of the proposed tracker by using the Bayesian framework, then we apply the L3SCM measure into the observation model component to measure the local similarities between the template of the tracked target and the sampled candidates in incoming frame of a given image sequence. Finally, we integrate a simple scheme to update the target template throughout the tracking process in order to improve the robustness of the proposed tracker. Experimental results on several challenging image sequences illustrate that the proposed method performs better against several state-of-the-art trackers.

Robust visual tracking based on deep convolutional neural networks and kernelized correlation filters

Object tracking is still a challenging problem in computer vision, as it entails learning an effective model to account for appearance changes caused by occlusion, out of view, plane rotation, scale change, and background clutter. This paper proposes a robust visual tracking algorithm called deep convolutional neural network (DCNNCT) to simultaneously address these challenges. The proposed DCNNCT algorithm utilizes a DCNN to extract the image feature of a tracked target, and the full range of information regarding each convolutional layer is used to express the image feature. Subsequently, the kernelized correlation filters (CF) in each convolutional layer are adaptively learned, the correlation response maps of that are combined to estimate the location of the tracked target. To avoid the case of tracking failure, an online random ferns classifier is employed to redetect the tracked target, and a dual-threshold scheme is used to obtain the final target location by comparing the tracking result with the detection result. Finally, the change in scale of the target is determined by building scale pyramids and training a CF. Extensive experiments demonstrate that the proposed algorithm is effective at tracking, especially when evaluated using an index called the overlap rate. The DCNNCT algorithm is also highly competitive in terms of robustness with respect to state-of-the-art trackers in various challenging scenarios.

Robust video tracking algorithm: a multi‐feature fusion approach

This study proposes a novel robust video tracking algorithm consists of target detection, multi-feature fusion, and extended Camshift. Firstly, a novel target detection method that integrates Canny edge operator, three-frame difference, and improved Gaussian mixture model (IGMM)-based background modelling is provided to detect targets. The IGMM-based background modelling divides video frames into meshes to avoid pixel-wise processing. In addition, the output of the target detection is utilised to initialise the IGMM and to accelerate the convergence of iterations. Secondly, low-dimensional regional covariance matrices are introduced to describe video targets by fusing multiple features like pixel location, colour index, rotation and scale invariant features as well as uniform local binary patterns, and directional derivatives. Thirdly, an extended Camshift based on adaptive kernel bandwidth and robust H∞ state estimation is proposed to predict the states of fast moving targets and to reduce the mean shift iterations. Finally, the effectiveness of the proposed tracking algorithm is demonstrated via experiments.

Adaptive Feedback Linearization Based NeuroFuzzy Maximum Power Point Tracking for a Photovoltaic System

In the current smart grid scenario, the evolution of a proficient and robust maximum power point tracking (MPPT) algorithm for a PV subsystem has become imperative due to the fluctuating meteorological conditions. In this paper, an adaptive feedback linearization-based NeuroFuzzy MPPT (AFBLNF-MPPT) algorithm for a photovoltaic (PV) subsystem in a grid-integrated hybrid renewable energy system (HRES) is proposed. The performance of the stated (AFBLNF-MPPT) control strategy is approved through a comprehensive grid-tied HRES test-bed established in MATLAB/Simulink. It outperforms the incremental conductance (IC) based adaptive indirect NeuroFuzzy (IC-AIndir-NF) control scheme, IC-based adaptive direct NeuroFuzzy (IC-ADir-NF) control system, IC-based adaptive proportional-integral-derivative (IC-AdapPID) control scheme, and conventional IC algorithm for a PV subsystem in both transient as well as steady-state modes for varying temperature and irradiance profiles. The comparative analyses were carried out on the basis of performance indexes and efficiency of MPPT.

Research on Intelligent Recognition System for Traffic Violation

This paper focuses on the intelligent recognition system of traffic violation on the basis of analyzing urban complex monitoring environment. For the realization that the system integrates the forensics of violation with license plate recognition in all day time, this paper proposes a set of efficient and robust vehicle detection and tracking algorithms. Vehicle detection was realized by the visual features of the license plate and color characteristic of the taillight to detect edge differential motion between image frames. In vehicle tracking, the extraction of large-scale fast stable points by Lucas-Kanade Pyramid method and predictions for tracking taillight based on Kalman method are proposed to realize long-distance stable tracking vehicles in whole day time. The practical applications show the system has excellent performance.

Two-Layer IMM Tracker with Variable Structure for Curvilinear Maneuvering Targets

It is of great importance to develop a robust and fast tracking algorithm for curvilinear maneuvering targets in tracking system. To target this issue, a novel two-layer interacting multiple model (IMM) tracker with variable structure is proposed, in which a nested inner layer IMM and an out layer IMM are executed in loops to boost the tracking performance. The purpose of inner layer IMM, which consists of constant angular velocity model and constant angular acceleration model, is to predict possible turn rate of the moving target. And the goal of outer layer IMM, which is based on curvilinear model with time-varying mode-set that consists of three adaptive turn rates, is to boot robust tracking performance in the presence of measuring noise and target maneuvering. Additionally, the state space in curvilinear model is extended from two-dimension to three-dimension which include position, velocity and acceleration variables. Experimental results over a flight scenario showed that for the specific tracking problem of maneuvering targets, the proposed two-layer IMM tracker with variable structure outperforms the state-of-the-art tracking algorithms significantly.

Improved Super-Resolution Ultrasound Microvessel Imaging With Spatiotemporal Nonlocal Means Filtering and Bipartite Graph-Based Microbubble Tracking

Super-resolution ultrasound microvessel imaging with contrast microbubbles has recently been proposed by multiple studies, demonstrating outstanding resolution with high potential for clinical applications. This paper aims at addressing the potential noise issue in in vivo human super-resolution imaging with ultrafast plane-wave imaging. The rich spatiotemporal information provided by ultrafast imaging presents features that allow microbubble signals to be separated from background noise. In addition, the high-frame-rate recording of microbubble data enables the implementation of robust tracking algorithms commonly used in particle tracking velocimetry. In this paper, we applied the nonlocal means (NLM) denoising filter on the spatiotemporal domain of the microbubble data to preserve the microbubble tracks caused by microbubble movement and suppress random background noise. We then implemented a bipartite graph-based pairing method with the use of persistence control to further improve the microbubble signal quality and microbubble tracking fidelity. In an in vivo rabbit kidney perfusion study, the NLM filter showed effective noise rejection and substantially improved microbubble localization. The bipartite graph pairing and persistence control demonstrated further noise reduction, improved microvessel delineation, and a more consistent microvessel blood flow speed measurement. With the proposed methods and freehand scanning on a free-breathing rabbit, a single microvessel cross-sectional profile with full-width at half-maximum of could be imaged at approximately 2-cm depth (ultrasound transmit center frequency = 8 MHz, theoretical spatial resolution ). Cortical microvessels that are apart can also be clearly separated. These results suggest that the proposed methods have good potential in facilitating robust in vivo clinical super-resolution microvessel imaging.

Robust adaptive trajectory tracking control of underactuated surface vessel in fields of marine practice

To enhance the control system robustness of an underactuated surface vessel with model uncertainties and environmental disturbances, a robust adaptive trajectory tracking algorithm based on proportional integral (PI) sliding mode control and the backstepping technique is proposed. In this algorithm, a continuous adaptive term is constructed to reduce the chattering magenta phenomenon of the system due to the sliding mode surface, and the backstepping technique is employed to force the ship position and the orientation on the desired values. In addition, we have proved the Lyapunov stability of the closed-loop system under the discontinuous environment disturbances or the thruster discontinuity. Finally, numerical simulations are performed to demonstrate the effectiveness of this novel methodology.

3-D Tracking for Augmented Reality Using Combined Region and Dense Cues in Endoscopic Surgery.

An augmented reality (AR) technique has recently gained its popularity in minimally invasive surgery. Tracking is a crucial step to achieve precise AR. Besides optical tracking in traditional medical AR, visual tracking attracts a lot of attention due to its generality. Moreover, when the target organ's 3-D model can be obtained from preoperative images and under the model rigidity assumption, tracking is then converted into a problem of computing the six-degree-of-freedom pose of the 3-D model. In this paper, we introduce a robust tracking algorithm in our endoscopic AR system, where we combine the benefits of both region and dense cues in a unified framework. Each kind of cues alone may not be adequate for tracking in endoscopic surgery. However, they have complementary characteristics, with region cues being more robust to motion blur and fast motion, and dense cues being more accurate when motion is not large. We also propose an appearance model adaption method and an occlusion processing method to effectively handle occlusions. Experiments on both synthetic dataset and simulated surgical environment show the effectiveness and robustness of our proposed method. This work presents a novel tracking strategy in medical AR applications.

Visual tracking using global sparse coding and local convolutional features

Visual tracking is a challenging task in many computer vision applications due to factors such as occlusion, scale variations, background clutter, and so on. In this paper, we present a robust tracking algorithm by representing the target at two levels: global and local levels. Accordingly, the tracking algorithm is composed of two parts: global and local parts. The global part is a discriminative model which separates the foreground object from the background based on holistic features. In the local part, we explore the target's local representation by a set of filters convolving the target region at each position. Then, the global part and local part are integrated into a collaborative model to construct the final tracker. Experiments on the tracking benchmark dataset with 50 challenging videos demonstrate the robustness and effectiveness of the proposed algorithm, outperforming several state-of-the-art models.