A Linear Programming Approach for Multiple Object Tracking

Jiang, Hao; Fels, Sidney; Little, James J.

doi:10.1109/cvpr.2007.383180

Cited by 292 publications

(227 citation statements)

References 4 publications

Supporting

Mentioning

227

Contrasting

Order By: Relevance

“…Many approaches assume manual initialization of tracks and/or a fixed, known number of objects [14]. However, for many real-world tracking problems, such information is not available.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Globally-optimal greedy algorithms for tracking a variable number of objects

2011

View full text Add to dashboard Cite

We analyze the computational problem of multi-object tracking in video sequences. We formulate the problem using a cost function that requires estimating the number of tracks, as well as their birth and death states. We show that the global solution can be obtained with a greedy algorithm that sequentially instantiates tracks using shortest path computations on a flow network. Greedy algorithms allow one to embed pre-processing steps, such as nonmax suppression, within the tracking algorithm. Furthermore, we give a near-optimal algorithm based on dynamic programming which runs in time linear in the number of objects and linear in the sequence length. Our algorithms are fast, simple, and scalable, allowing us to process dense input data. This results in state-of-the-art performance.

show abstract

“…Many approaches assume manual initialization of tracks and/or a fixed, known number of objects [14]. However, for many real-world tracking problems, such information is not available.…”

Section: Related Workmentioning

confidence: 99%

“…Our contribution is grounded in a novel analysis of an integer linear program (ILP) formulation of multi-object tracking [14,25,3,17,2,18]. Our work most closely follows the min-cost flow algorithm of [25].…”

Section: Introductionmentioning

confidence: 99%

Globally-optimal greedy algorithms for tracking a variable number of objects

2011

View full text Add to dashboard Cite

show abstract

“…The multiple object tracking problem is defined as a linear constrained optimization flow problem and Linear Programming (LP) is commonly used to find the global optimum. The idea was first used for people tracking in [18], although this method needs to know a priori the number of targets to track, which limits its application in real tracking situations. In [9], the scene is divided into identical cells, each represented by a node in the constructed graph.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

Leal-Taixé

Pons-Moll

Rosenhahn

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Multiple people tracking consists in detecting the subjects at each frame and matching these detections to obtain full trajectories. In semi-crowded environments, pedestrians often occlude each other, making tracking a challenging task. Tracking methods mostly work with the assumption that each pedestrian moves independently unaware of the objects or the other pedestrians around it. In the real world though, it is clear that when walking in a crowd, pedestrians try to avoid collisions, keep a close distance to a group of friends or avoid static obstacles in the scene. In this paper, we present an approach which includes the interaction between pedestrians in two ways: first, including social and grouping behavior as a physical model within the tracking system, and second, using a global optimization scheme which takes into account all trajectories and all frames to solve the data association problem . Results are presented on three challenging publicly available datasets, showing our method outperforms state-of-the-art tracking systems. We also make a thorough analysis of the effect of the parameters of the proposed tracker as well as its robustness against noise, outliers and missing data.

show abstract

“…They rely on Conditional Random Fields [17,27], belief Propagation [29,9], Dynamic or Linear Programming [3,10]. Among the latter, some operate on graphs whose nodes can either be all the spatial locations of potential people presence [26,11,5,1], only those where a detector has fired [25,15], or short temporal sequences of consecutive detections that are very likely to correspond to the same person [21,30,23,4].…”

Section: Related Workmentioning

confidence: 99%

“…This can be done recursively [6,19], using dynamic programming [26,11,23], or using Linear Programming [25,15,5].…”

Section: Introductionmentioning

confidence: 99%

Tracking Interacting Objects Optimally Using Integer Programming

Wang

Türetken

Fleuret

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously and expressing the fact that one object can appear or disappear at locations where another is in terms of linear flow constraints. We demonstrate the power of our approach on scenes involving cars and pedestrians, bags being carried and dropped by people, and balls being passed from one player to the next in a basketball game. In particular, we show that by estimating jointly and globally the trajectories of different types of objects, the presence of the ones which were not initially detected based solely on image evidence can be inferred from the detections of the others.

show abstract

A Linear Programming Approach for Multiple Object Tracking

Cited by 292 publications

References 4 publications

Globally-optimal greedy algorithms for tracking a variable number of objects

Globally-optimal greedy algorithms for tracking a variable number of objects

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

Tracking Interacting Objects Optimally Using Integer Programming

Contact Info

Product

Resources

About