Exponential stability of general tracking algorithms

Tracking and adaptation algorithms are, from a formal point of view, nonlinear systems which depend on stochastic variables in a fairly complicated way. The analysis of such algorithms is thus quite complicated. A first step is to establish the exponential stability of these systems. This is of interest in its own right and a prerequisite for the practical use of the algorithm. It is also a necessary starting point to analyze the performance in terms of tracking and adaptation because that is how close the estimated parameters are to the time-varying true ones. In this paper we establish some general conditions for the exponential stability of a wide and common class of tracking algorithms. This includes least mean squares, recursive least squares, and Kalman filter based adaptation algorithms. We show how stability of an averaged (linear and deterministic) equation and stability of the actual algorithm are linked to each other under weak conditions on the involved stochastic processes. We also give explicit conditions for exponential stability of the most common algorithms. The tracking performance of the algorithms is studied in a companion paper     

Signal parameter tracking algorithms using hybrid recurrent networks

Several explicit algorithms for tracking the parameters of second order models have been derived by the authors based on information available from the system time trajectory. In this paper the problem is recast in terms of recurrent integral-hybrid networks used in a hierarchical formation for both the reduced order model and to estimate the derivatives for parameter tracking. We relax the constant parameter condition by assuming linear time variation, the additional information is extracted from the system output trajectory by obtaining higher time derivatives which result in explicit functions to track the parameters online.     

Recursive 4SID algorithms using gradient type subspace tracking

Sometimes we obtain some prior information about a system to be identified, e.g., the order, model structure etc. In this paper, we consider the case where the order of a MIMO system to be identified is a priori known. Recursive subspace state-space system identification algorithms presented here are based on the gradient type subspace tracking method used in the array signal processing. The algorithms enable us to estimate directly the subspace spanned by the column vectors of the extended observability matrix of the system to be identified without performing the singular value decomposition. Also, a new convergence proof of the gradient type subspace tracking is given in this paper. Under the condition of a step size between 0 and 1, we prove the convergence property of the recursive equation of the gradient type subspace tracking. A numerical example illustrates that our algorithm is more robust with respect to the choice of the initial values than the corresponding PAST one.     

Automated eye tracking system calibration using artificial neural networks

The electro-oculogram (EOG) continues to be widely used to record eye movements especially in clinical settings. However, an efficient and accurate means of converting these recordings into eye position is lacking. An artificial neural network (ANN) that maps two-dimensional (2D) eye movement recordings into 2D eye positions can enhance the utility of such recordings. Multi-layer perceptrons (MLPs) with non-linear activation functions and trained with back propagation proved to be capable of calibrating simulated EOG data to a mean accuracy of 0.33 degrees . Linear perceptrons (LPs) were only nearly half as accurate. For five subjects, the mean accuracy provided by the MLPs was 1.09 degrees of visual angle ( degrees ) for EOG data, and 0.98 degrees for an infrared eye tracker. MLPs enabled calibration of 2D saccadic EOG to an accuracy not significantly different from that obtained with the infrared tracker. Using initial weights trained on another person reduced MLP training time, reaching convergence in as little as 20 iterations.     

Detecting and tracking mesoscale precipitating objects using machine learning algorithms

Accurate identification of precipitating clouds is a challenging task. In the present work, Support Vector Machines (SVMs), Decision Trees (DT), and Random Forests (RD) algorithms were applied to extract and track mesoscale convective precipitating clouds from a series of 22 Geostationary Operational Environmental Satellite-13 meteorological image sub-scenes over the continental territory of Colombia. This study’s aims are twofold: (i) to establish whether the use of five meteorological spectral channels, rather than a single infrared (IR) channel, improves rainfall objects detection and (ii) to evaluate the potential of machine learning algorithms to locate precipitation clouds. Results show that while the SVM algorithm provides more accurate classification of rainfall cloud objects than the traditional IR brightness temperature threshold method, such improvement is not statistically significant. Accuracy assessment was performed using STEP (shape (S), theme (T), edge (E), and position (P)) object-based similarity matrix method, taking as reference precipitation satellite images from the Tropical Rainfall Measuring Mission. Best thematic and geometric accuracies were obtained applying the SVM algorithm.     

Improvement of tracking performance using prediction-based algorithms for a maneuvering target

This paper presents a study involving prediction of a complicated maneuvering target, with the aim of improving the tracking performance of a fire control system (FCS). In this study, we predict the position of a complicated maneuvering target 5 s in advance using the information up to the current time. Because of the large error caused by the complicated maneuvers and the long prediction time interval, the mechanical system of the fire control system will take a heavy load. In order to cope with this problem, several approaches to decreasing the prediction error have been proposed including the prediction algorithms based on the multiple model(MM) filter, interacting multiple model (IMM) filter, and variable dimension with input estimation (VDIE) filter. Finally, comparative simulation results are presented to verify the performance of the filters.     

Benchmarking template-based tracking algorithms

For natural interaction with augmented reality (AR) applications, good tracking technology is key. But unlike dense stereo, optical flow or multi-view stereo, template-based tracking which is most commonly used for AR applications lacks benchmark datasets allowing a fair comparison between state-of-the-art algorithms. Until now, in order to evaluate objectively and quantitatively the performance and the robustness of template-based tracking algorithms, mainly synthetically generated image sequences were used. The evaluation is therefore often intrinsically biased. In this paper, we describe the process we carried out to perform the acquisition of real-scene image sequences with very precise and accurate ground truth poses using an industrial camera rigidly mounted on the end effector of a high-precision robotic measurement arm. For the acquisition, we considered most of the critical parameters that influence the tracking results such as: the texture richness and the texture repeatability of the objects to be tracked, the camera motion and speed, and the changes of the object scale in the images and variations of the lighting conditions over time. We designed an evaluation scheme for object detection and interframe tracking algorithms suited for AR and other computer vision applications and used the image sequences to apply this scheme to several state-of-the-art algorithms. The image sequences are freely available for testing, submitting and evaluating new template-based tracking algorithms, i.e. algorithms that detect or track a planar object in an image sequence given only one image of the object (called the template).     

Pedestrian detection and tracking using temporal differencing and HOG features

This article proposes a multiple human detection and tracking approach. A moving person identification technique is provided first. The video objects are detected using a novel temporal differencing based procedure and several mathematical morphology-based operations. Then, our technique determines what moving image objects represent pedestrian people, by testing several conditions related to human bodies and detecting the skin regions from the movie frames. A robust human tracking method using a Histogram of Oriented Gradient (HOG) based template matching process is then introduced in our paper. Some person detection and tracking experiments and method comparisons are also described.     

视觉跟踪算法综述

随着信息技术与智能科学的迅速发展,计算机视觉已经成为IT产业和高新技术领域的前沿.视觉跟踪是当前计算机视觉领域的热点问题之一.阐述了视觉跟踪算法的研究现状,包括视觉跟踪算法的种类,常用数学方法,研究了基于区域的跟踪算法、基于模型的跟踪算法、基于特征的跟踪算法、基于主动轮廓的跟踪算法、参数估计方法和无参密度估计方法,并探讨了视觉跟踪算法的未来研究方向.     

Evaluation of eye,head and trunk coordination during target tracking tasks

This study tested the feasibility of a method to synchronise and to evaluate eye, head and trunk movement patterns during target tracking tasks performed by 10 subjects. A projected central target was randomly repositioned at 40° and 70° of rotation to the left and right. Subjects were instructed to change gaze as quickly as possible. Head and trunk motion was measured using a motion analysis system, and eye movement was measured using an eye-tracker; all data were synchronised. For healthy subjects, the eye moved faster than the head, there was no trunk movement and the head moved more than the eye to reach further displaced targets. The method tested was feasible, and it could be used to evaluate eye, head and trunk movement patterns of subjects with injuries such as whiplash and concussions.

Practitioner Summary: Studies of eye, head and trunk movements using synchronised methods are needed. We tested the feasibility of a method to synchronise and evaluate eye, head and trunk movement patterns. The method tested was feasible, and it could be used to evaluate movement patterns of subjects with injuries such as whiplash.     

Global stability analysis of fuzzy path tracking using frequency response

This paper studies the stability of fuzzy path tracking of autonomous vehicles. This problem lies in the generation of the steering commands for a vehicle to follow a given path autonomously. In this control loop, both the plant and the fuzzy controller are nonlinear. Due to this nonlinearity, complex behavioral phenomena can occur, giving rise to the loss of global stability. The extension of conventional frequency response methods for the stability analysis of the nonlinear fuzzy path-tracking control loop is proposed. Simulation experiments show the validity of the proposed method in three different cases: stable origin and unstable limit cycle, delay-induced Hopf bifurcation, and delay-induced unstable limit cycle.     

Performance analysis of general tracking algorithms

A general family of tracking algorithms for linear regression models is studied. It includes the familiar least mean square gradient approach, recursive least squares, and Kalman filter based estimators. The exact expressions for the quality of the obtained estimates are complicated. Approximate, and easy-to-use, expressions for the covariance matrix of the parameter tracking error are developed. These are applicable over the whole time interval, including the transient, and the approximation error can be explicitly calculated     

目标跟踪算法的并行优化

目标跟踪是计算机视觉领域一个重要的研究方向,近年来学者提出了众多优秀的目标跟踪算法,但许多算法的低实时性制约了其在应用场景中的有效性。针对这些算法,提出了一个通用的跟踪模型,并针对此模型提出了一个可行的并行优化方案。之后使用SCM算法验证了所提出的并行优化方案。在四核CPU的环境下,并行后的SCM算法相比于未并行的算法取得了3.48倍的并行加速比,并且比原算法Matlab+C程序的运行速度快了约30倍,这说明了所提出的并行优化方案的有效性。     

类孪生网络目标跟踪算法综述

目前,在视觉目标跟踪任务中的主流方法是基于模版匹配的跟踪器,这些方法在目标的分类和边界框的回归上具有很强的鲁棒性,主要可以分为判别相关滤波跟踪器和孪生网络跟踪器,这两种方法都有一个类孪生网络的框架。以孪生网络跟踪器为例,该方法通过模版和搜索区域之间的相关操作确定目标的位置,取得了顶尖的性能表现。近年来,Transformer在计算机视觉领域的发展十分迅速,结合了Transformer的类孪生网络跟踪器在速度和精度方面都远超传统的跟踪方法。文章简要概括了判别相关滤波跟踪器、孪生网络跟踪器的发展,以及Transformer在目标跟踪任务中的应用。     

眨眼检测与眼睛跟踪

提出一种在视频人脸图像序列中,进行眼睛检测,跟踪和睁、闭状态判别的方法。通过眨眼检测,对眼睛进行定位;使用针对性强的内眼角提取算子,确定内眼角精确位置;利用内眼角特征来动态跟踪眼睛;睁眼模板在线生成和更新,通过当前眼睛区域和睁眼模板的相关分析来判别睁、闭眼状态。实验结果表明,算法在50场/s的处理速度下,内眼角点定位准确率达到98%以上,眨眼检测正确率为97.5%。     

Human eye sclera detection and tracking using a modified time-adaptive self-organizing map

This paper investigates the use of time-adaptive self-organizing map (TASOM)-based active contour models (ACMs) for detecting the boundaries of the human eye sclera and tracking its movements in a sequence of images. The task begins with extracting the head boundary based on a skin-color model. Then the eye strip is located with an acceptable accuracy using a morphological method. Eye features such as the iris center or eye corners are detected through the iris edge information. TASOM-based ACM is used to extract the inner boundary of the eye. Finally, by tracking the changes in the neighborhood characteristics of the eye-boundary estimating neurons, the eyes are tracked effectively. The original TASOM algorithm is found to have some weaknesses in this application. These include formation of undesired twists in the neuron chain and holes in the boundary, lengthy chain of neurons, and low speed of the algorithm. These weaknesses are overcome by introducing a new method for finding the winning neuron, a new definition for unused neurons, and a new method of feature selection and application to the network. Experimental results show a very good performance for the proposed method in general and a better performance than that of the gradient vector field (GVF) snake-based method.     

PeepList: Adapting ex-post interaction with pervasive display content using eye tracking

Short intensive interactions with unfamiliar pervasive displays coerce users to perform cognitive operations with uncertainty and risk of not being able to access the information of relevance later. We developed a new way of interaction with pervasive displays by harnessing the eye tracking technology to extract information that is most likely relevant to the user. These extracted bits of important information are presented to the user and sorted according to their estimated importance—in the PeepList. The users can interact with the PeepList without explicit commands and they can access the customized PeepList ex-post in order to review information previously consumed from the pervasive display.We carried out a user study involving 16 participants to evaluate the contribution of PeepList to efficient pervasive display interaction. The tests revealed that the PeepList system is unobtrusive, accurate, and in particular it reduces the interaction times by 40% when complex tasks were presented to the participants. A feasible user model can be built in under 30 seconds in 50% of all interactions, and in one minute, a majority of all interactions (70%) lead to a useful user model. Experimental results show that eye tracking is a valuable real-time implicit source of information about what the user is searching for on a pervasive display and that it can be used for real-time user interface adaptation. This considerably improves the efficiency of obtaining and retaining required data.     

A strong tracking nonlinear robust filter for eye tracking

Non-intrusive methods for eye tracking are important for many applications of vision-based human computer interaction. However, due to the high nonlinearity of eye motion, how to ensure the robustness of external interference and accuracy of eye tracking pose the primary obstacle to the integration of eye movements into today’s interfaces. In this paper, we present a strong tracking unscented Kalman filter (ST-UKF) algorithm, aiming to overcome the difficulty in nonlinear eye tracking. In the proposed ST-UKF, the Suboptimal fading factor of strong tracking filtering is introduced to improve robustness and accuracy of eye tracking. Compared with the related Kalman filter for eye tracking, the proposed ST-UKF has potential advantages in robustness and tracking accuracy. The last experimental results show the validity of our method for eye tracking under realistic conditions.     

How programmers read regular code: a controlled experiment using eye tracking

Regular code, which includes repetitions of the same basic pattern, has been shown to have an effect on code comprehension: a regular function can be just as easy to comprehend as a non-regular one with the same functionality, despite being significantly longer and including more control constructs. It has been speculated that this effect is due to leveraging the understanding of the first instances to ease the understanding of repeated instances of the pattern. To verify and quantify this effect, we use eye tracking to measure the time and effort spent reading and understanding regular code. The experimental subjects were 18 students and 2 faculty members. The results are that time and effort invested in the initial code segments are indeed much larger than those spent on the later ones, and the decay in effort can be modeled by an exponential model. This shows that syntactic code complexity metrics (such as LOC and MCC) need to be made context-sensitive, e.g. by giving reduced weight to repeated segments according to their place in the sequence. However, it is not the case that repeated code segments are actually read more and more quickly. Rather, initial code segments receive more focus and are looked at more times, while later ones may be only skimmed. Further, a few recurring reading patterns have been identified, which together indicate that in general code reading is far from being purely linear, and exhibits significant variability across experimental subjects.