Multiple Instance Learning Tracker Research Articles

МЕТОДЫ РАСПОЗНАВАНИЯ ОБРАЗОВ В ВИДЕОПОТОКЕ

The article examines the problem of automatic object recognition using a video stream as a digital image. Algorithms for recognizing and tracking objects in the video stream are considered, methods used in video processing are analyzed, and the use of machine learning tools in working with video is described.The main approaches to solving the problem of recognizing moving objects in a video stream are investigated: the detection-based approach and the tracking-based approach. Arguments are made in favor of the tracking-based approach, and, in addition, modern methods of tracking objects in the video stream are considered. In particular, the algorhythms: Online Boosting Tracker - one of the first object tracking algorithms with high tracking accuracy, MIL Tracker (Multiple Instance Learning Tracker), which is a development of the idea of learning with a teacher and the Online Boosting algorithm and the KCF Tracker algorithm (Kernelized Correlation Filters Tracker) - a method that uses the mathematical properties of overlapping areas of positive examples.As a result, the advantages and disadvantages of the considered methods and algorithms for recognizing and tracking objects for various applications are highlighted.

Automated Goal Score Detection in Football Match Using Key Moments

Abstract Automated goal score detection in a football match is a comprehensive work and a challenging task as well. In this paper, we proposed a methodology for goal score detection using key moments of the match. Key moments in any sports are referred as actions that stimulate excitement or attraction of the audience. So, key moments can be identified using computer vision. Extracting one key moment involves many steps to happen at a time and it is necessary to integrate all the steps to identify it as a key moment. It is necessary to identify the goalpost region and track the ball to calculate the goal in football match. The proposed work analyses the various tracking algorithms and finalize MIL (Multiple Instance Learning) tracker technique to track the ball. So, the proposed work identifies the goal post region using sequence of image processing operations, tracks the ball using multiple instance learning tracker and confirms whether the goal has been occurred or not. The results of the proposed work have been shown.

Human motion tracking: A comparative study

In this paper, we aim to carry out a brief study of a new tracking system and the results of existing tracking systems including Compressive Tracking (CT), Fragment Tracker (FRAG), Multiple Instance Learning Tracker (MIL), and Tracking Learning Detection algorithm (TLD). For this purpose, we present the principles of those tracking systems. Then, we test them on several datasets that contain challenging attributions. Finally, we evaluate them qualitatively and quantitatively by two widely used criterions: the Average Center Error (ACE) and the Average Overlap Error (AOE). We conclude our paper by discussing the obtained results and the future works in this field.

Spatio-temporally weighted multiple instance learning for visual tracking

Due to the superiority in handling label ambiguity, multiple instance learning (MIL) has been introduced into adaptive tracking-by-detection methods to alleviate drift and yields promising tracking performance. However, the MIL tracker assumes that all samples in a positive bag contribute equally to the bag probability, which ignores the sample importance. To address this issue, in this paper we propose a spatio-temporally weighted MIL (STWMIL) tracker which integrates temporal weight into the update scheme for Haar-like features and spatial weight into the bag probability function. Spatial weight for the positive sample near the target location is larger than that far from the target location, which means the former contributes more to the positive bag probability. Based on spatial weight, a novel bag probability function is proposed using the weighted Noisy-OR model. Temporal weight for the recently-acquired images is larger than that for the earlier observations, which means less modelling power is expended on old observations. Based on temporal weight, a novel update scheme with changing but convergent learning rate is derived with strict mathematic proof. Extensive experiments performed on the OTB-2013, TC128 and UAV123 tracking benchmarks demonstrate that our proposed tracker achieves superior performance both qualitatively and quantitatively over several state-of-the-art trackers.

Robust visual tracking via online multiple instance learning with Fisher information

Most tracking-by-detection approaches train the classifier in an supervised manner in which the samples near the tracked object location are labeled positively while those far from the object location are negative. However, the inaccuracy of the tracker may cause incorrectly labeled training samples, which in turn degrade the classifier when updating it, thereby leading to drift problem. Recently, multiple instance learning (MIL) is introduced into visual tracking with demonstrated success of dealing with drift. In MIL tracker, the samples are put into bags, and the classifier is a linear combination of some weak classifiers which are greedily selected via maximizing the likelihood function of the bags. However, the weak classifiers selected by the likelihood function are less informative to tell target from complex background than those from some information criterion (e.g., Fisher information criterion). In this paper, we show that using the Fisher information criterion instead of the likelihood function in the MIL can yield a more robust and efficient result. An online boosting feature selection approach is proposed via optimizing the Fisher information criterion, which can yield more robust and efficient tracking performance. Experimental evaluations on challenging sequences demonstrate the superiority of our tracker to state-of-the-art trackers in terms of efficiency, accuracy and robustness.

Enhanced MIL tracker with distribution field‐based features and temporal fusion framework

A new tracker based on multiple instance learning (MIL) with distribution field (DF)-based features and a novel temporal fusion framework is presented. DF-based features make the representations less sensitive to the object's appearance variation. In addition, the tracker introduces a new temporal fusion framework based on the randomised policy, aiming at adding robustness against outliers during the tracking. Experimental results on challenging video sequences show the effectiveness of the proposed method.

Improved appearance updating method in multiple instance learning tracking

Multiple instance learning (MIL) tracker becomes recently very popular because of their great success in complex scenes. Dynamically reflecting the appearance changes of the tracked object, the appearance updating plays an important role on tracking. In the original MIL tracker, the appearance model is assumed to obey normal distribution and its updating rule consists of a simple linearly weighted sum of the original and the current target distributions in the current frame. However, this updating method is not proved theoretically. In this work, the authors deduce a novel appearance updating method by estimating the mean and the variance of the sum of two normal distributions being merged in maximum likelihood estimation. The method can be naturally extended to multivariable distributions, useful to track colour object. Experimental results on some benchmark video sequences show that the method achieve higher precision and reliability than the three state-of-art trackers.

Visual Tracking Based on Particle Filter and Weighted Multiple Instance Learning

Visual tracking is one of fundamental tasks in the field of computer vision. In recent years, detection algorithms have been more and more interested in the use of discriminative classifiers for tracking system. Template drift is the major shortcoming of the detection algorithms because of the online self-learning mechanism of the visual tracker. Multiple Instance Learning (MIL) method has been applied to target tracking, which can alleviate the drift to some extent. However, the MIL tracker cannot discriminatively consider the importance of sample and instance in its learning procedure. Particle filter is employed to make the use of the learned classifier and to help generating a better representative set of training samples for the online learning. In this paper, we present a tracking method built by particle filter and weighted MIL tracker, which integrates the sample and instance importance into an efficient online learning procedure when the classifier is being trained. At the end, the experimental results on various videos verify that the proposed method has a satisfaction performance in real-time object tracking.

Robust Object Tracking Via Active Feature Selection

Adaptive tracking by detection has been widely studied with promising results. The key idea of such trackers is how to train an online discriminative classifier, which can well separate an object from its local background. The classifier is incrementally updated using positive and negative samples extracted from the current frame around the detected object location. However, if the detection is less accurate, the samples are likely to be less accurately extracted, thereby leading to visual drift. Recently, the multiple instance learning (MIL) based tracker has been proposed to solve these problems to some degree. It puts samples into the positive and negative bags, and then selects some features with an online boosting method via maximizing the bag likelihood function. Finally, the selected features are combined for classification. However, in MIL tracker the features are selected by a likelihood function, which can be less informative to tell the target from complex background. Motivated by the active learning method, in this paper we propose an active feature selection approach that is able to select more informative features than the MIL tracker by using the Fisher information criterion to measure the uncertainty of the classification model. More specifically, we propose an online boosting feature selection approach via optimizing the Fisher information criterion, which can yield more robust and efficient real-time object tracking performance. Experimental evaluations on challenging sequences demonstrate the efficiency, accuracy, and robustness of the proposed tracker in comparison with state-of-the-art trackers.

Real-Time Object Tracking Via Online Discriminative Feature Selection

Most tracking-by-detection algorithms train discriminative classifiers to separate target objects from their surrounding background. In this setting, noisy samples are likely to be included when they are not properly sampled, thereby causing visual drift. The multiple instance learning (MIL) paradigm has been recently applied to alleviate this problem. However, important prior information of instance labels and the most correct positive instance (i.e., the tracking result in the current frame) can be exploited using a novel formulation much simpler than an MIL approach. In this paper, we show that integrating such prior information into a supervised learning algorithm can handle visual drift more effectively and efficiently than the existing MIL tracker. We present an online discriminative feature selection algorithm that optimizes the objective function in the steepest ascent direction with respect to the positive samples while in the steepest descent direction with respect to the negative ones. Therefore, the trained classifier directly couples its score with the importance of samples, leading to a more robust and efficient tracker. Numerous experimental evaluations with state-of-the-art algorithms on challenging sequences demonstrate the merits of the proposed algorithm.

Real-time visual tracking via online weighted multiple instance learning

Adaptive tracking-by-detection methods have been widely studied with promising results. These methods first train a classifier in an online manner. Then, a sliding window is used to extract some samples from the local regions surrounding the former object location at the new frame. The classifier is then applied to these samples where the location of sample with maximum classifier score is the new object location. However, such classifier may be inaccurate when the training samples are imprecise which causes drift. Multiple instance learning (MIL) method is recently introduced into the tracking task, which can alleviate drift to some extent. However, the MIL tracker may detect the positive sample that is less important because it does not discriminatively consider the sample importance in its learning procedure. In this paper, we present a novel online weighted MIL (WMIL) tracker. The WMIL tracker integrates the sample importance into an efficient online learning procedure by assuming the most important sample (i.e., the tracking result in current frame) is known when training the classifier. A new bag probability function combining the weighted instance probability is proposed via which the sample importance is considered. Then, an efficient online approach is proposed to approximately maximize the bag likelihood function, leading to a more robust and much faster tracker. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm to state-of-the-art tracking algorithms.