Multiple hypothesis tracking (MHT) is generally accepted as the preferred method for solving the data association problem in modern multiple target tracking (MTT) systems. This paper summarizes the motivations for MHT, the basic principles behind MHT and the alternative implementations in common use. It discusses the manner in which the multiple data association hypotheses formed by MHT can be combined with multiple filter models, such as used by the interacting multiple model (IMM) method. An overview of the studies that show the advantages of MHT over the conventional single hypothesis approach is given. Important current applications and areas of future research and development for MHT are discussed.

/pdf/multiple-hypothesis-tracking-for-multiple-target-tracking-3fzibddaoe.pdf

Multiple hypothesis tracking for multiple target tracking

Tracking in a cluttered environment with probabilistic data association

The objective of this paper is to survey and put in perspective the existing methods of tracking in multitarget environment. In such an environment the origin of the measurements can be uncertain: they could have come from the target(s) of interest or clutter or false alarms or be due to the background. This compact and unified presentation of the state-of-art in multitarget tracking was motivated by the recent surge of interest in this problem. It is also hoped to be useful in view of the need to adapt and modify existing techniques before using them for specific problems. Particular attention is paid to the assumptions underlying each algorithm and its applicability to various situations.

Tracking methods in a multitarget environment

When tracking targets in dense environments, sensor reports originating from sources other than the target being tracked (i.e., from clutter, thermal false alarms, other targets) are occasionally incorrectly used in track updating. As a result tracking performance degrades, and the error covariance matrix calculated on-line by the usual types of tracking filters becomes extremely unreliable for estimating actual accuracies. This paper makes three contributions in this area. First, a new tracking filter is developed that incorporates, in an a posteriori statistical fashion, all data available from sensor reports located in the vicinity of the track, and that provides both optimal performance and reliable estimates of this performance when operating in dense environments. The optimality of and the performance equations for this filter are verified by analytical and simulation results. Second, several computationally efficient classes of suboptimal tracking filters based on the optimal filter developed in this paper and on an optimal filter of another class that appeared previously in the literature are developed. Third, using an extensive Monte Carlo simulation, the various optimal and suboptimal filters as well as the Kalman filter are compared, with regard to the differences between the on-line calculated and experimental covariances of each filter, and with regard to relative accuracies, computational requirements, and numbers of divergences or lost tracks each produces.

Derivation and evaluation of improved tracking filter for use in dense multitarget environments

This report contains a review of visual tracking in monocular video sequences. For the purpose of this review, the majority of the visual trackers in the literature are divided into three tracking categories: discrete feature trackers, contour trackers, and region-based trackers. This categorization was performed based on the features used and the algorithms employed by the various visual trackers. The first class of trackers represents targets as discrete features (e.g. points, sets of points, lines) and performs data association using a distance metric that accommodates the particular feature. Contour trackers provide precise outlines of the target boundaries, meaning that they must not only uncover the position of the target, but its shape as well. Contour trackers often make use of gradient edge information during the tracking process. Region trackers represent the target with area-based descriptors that define its support and attempt to locate the image region in the current frame that best matches an object template. Trackers that are not in agreement with the abovementioned categorization, including those that combine methods from the three defined classes, are also considered in this review. In addition to categorizing and describing the various visual trackers in the literature, this review also provides a commentary on the current state of the field as well as a comparative analysis of the various approaches. The paper concludes with an outline of open problems in visual tracking.

/pdf/a-review-of-visual-tracking-1jjlitka1e.pdf

A Review of Visual Tracking

This paper develops a new optimal tracking filter that accounts for and minimizes the effects of correlation uncertainties in surveillance systems. This filter reduces to the Kalman filter in the limiting case of no correlation errors and infinite gate sizes, and provides substantially improved performance in environments wherein correlation uncertainties cannot be ignored.

John Stein

Papers

An optimal tracking filter for processing sensor data of imprecisely determined origin in surveillance systems