Toward an Optimal Solution for Multitarget Tracking

ICTACT Journal on Image and Video Processing, 2017

2008

Multi-frame data association involves finding the most probable correspondences between target tracks and measurements (collected over multiple time instances) as well as handling the common tracking problems such as, track initiations and terminations, occlusions, and noisy detections. The problem is known to be NP-Hard for more than two frames. A rank constrained continuous formulation of the problem is presented that can be efficiently solved using nonlinear optimization methods. It is shown that the global and local extrema of the continuous problem respectively coincide with the maximum and the maximal solutions of the discrete counterpart. A scanning window based tracking algorithm is developed using the formulation that performs well under noisy conditions with frequent occlusions and multiple track initiations and terminations. The above claims are supported by experiments and quantitative evaluations using both synthetic and real data under different operating conditions. 1 978-1-4244-2243-2/08/$25.00 ©2008 IEEE

1995

SUMMARY Various combinatorial optimization techniques are currently available. Most of these techniques have not been thourougly tested on realistic problems. The EUCLID (EUropean Cooperation for the Long term In Defence) CALMA (Combinatorial Algorithms for Military Applications) RTP (Research and Technology Project) 6.4 project has the main objective to investigate the relevance of various existing algorithmic optimization techniques to the actual solution of complex combinatorial problems arising in military applications.

In tracking-by-detection paradigm for multi-target tracking, target association is modeled as an optimization problem that is usually solved through network flow formulation. In this paper, we proposed combinatorial optimization formulation and used a bipartite graph matching for associating the targets in the consecutive frames. Usually, the target of interest is represented in a bounding box and track the whole box as a single entity. However, in the case of humans, the body goes through complex articulation and occlusion that severely deteriorate the tracking performance. To partially tackle the problem of occlusion, we argue that tracking the rigid body organ could lead to better tracking performance compared to the whole body tracking. Based on this assumption, we generated the target hypothesis of only the spatial locations of person’s heads in every frame. After the localization of head location, a constant velocity motion model is used for the temporal evolution of the targe...

Computers & Operations Research, 2003

In this work we present a linear programming (LP) based approach for solving the data association problem (DAP) in multiple target tracking. It is well-known that the DAP can be formulated as an integer program. We present a compact formulation of the DAP. To solve practical instances of the DAP we propose an algorithm that uses an iterated K-scan sliding window technique. In each iteration we solve the LP relaxation of an integer program and next apply a greedy rounding procedure. Computational experiments indicate that the quality of the solutions found is quite satisfactory.

This work addresses the problem of tracking multiple moving targets by recursively estimating the joint multitarget probability density (JMPD). Estimation of the JMPD is done in a Bayesian framework and provides a method for tracking multiple targets which allows nonlinear target motion and measurement to state coupling as well as non-Gaussian target state densities. The JMPD technique simultaneously estimates both the target states and the number of targets in the surveillance region based on the set of measurements made. We give an implementation of the JMPD method based on particle filtering techniques and provide an adaptive sampling scheme which explicitly models the multitarget nature of the problem. We show that this implementation of the JMPD technique provides a natural way to track a collection of targets, is computationally tractable, and performs well under difficult conditions such as target crossing, convoy movement, and low measurement signal-to-noise ratio (SNR).

Public reporting burden for this collection of infonation is eastinated to average 1 hour per response. induding ft time for reiewrig it data needed and corrpleting and remiewing this collection of infoinatjion. Send cominents regarding this burden eatirate or any other this burden to Depalnient of Defense, Washilgtoni HedquatersSAces, Directoratefor Infformation Operations md R"oits (07044 4302. Respondent should be avar that notwithstanditg any other prousion of law, no peron shall be subject to any penalty for faili ., mu i a uc leaton of infornation if it does not display a currently valid OMB control nunber. PLEASE DO NOT RETURN YOUR FORM 70 THE ABOVE ADDRESS.

CVPR 2012

The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image observations to the appropriate target; (ii) the naturally continuous problem of trajectory estimation, i.e. recovering the trajectories of all targets. To go beyond simple greedy solutions for data association, recent approaches often perform multi-target tracking using discrete optimization. This has the disadvantage that trajectories need to be pre-computed or represented discretely, thus limiting accuracy. In this paper we instead formulate multi-target tracking as a discretecontinuous optimization problem that handles each aspect in its natural domain and allows leveraging powerful methods for multi-model fitting. Data association is performed using discrete optimization with label costs, yielding near optimality. Trajectory estimation is posed as a continuous fitting problem with a simple closed-form solution, which is used in turn to update the label costs. We demonstrate the accuracy and robustness of our approach with state-of-theart performance on several standard datasets.

2013

Performance comparison of the two approaches for the first scenario.. 5.2 Performance comparison of the two approaches for the second scenario. 5.3 Solutions to the SS, RA, and DF problems for the first scenario.. .. 5.4 Solutions to the SS, RA, and DF problems for the second scenario.. 6.1 Estimated vs the actual trajectories of the targets obtained using different algorithms for (a), (d), (g), (j) easy, (b), (e), (h), (k) medium, and (c), (f), (i), (l) hard problems.

Proceedings of the 5th international conference on Computer systems and technologies - CompSysTech '04, 2004

In this paper the effectiveness of two Data Association algorithms for Multiple Target Tracking (MTT) based on Global Nearest Neighbor approach are compared. As the time for assignment problem solution increases nonlinearly depending on the problem size, it is useful to divide the whole scenario on small groups of targets called clusters. For each cluster the assignment problem is solved by using Munkres algorithm. Results reveal that the computational time especially for large scenarios decreases significantly when clustering is used.