A Linear Programming Approach for Multiple Object Tracking

By Hao Jiang, S. Fels, James J. Little. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

375 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/d8d6819004a6f384f06b902133463c50fe8cd8d3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, background): “Jiang et al. (2007) propose the use of Integer Linear Programming (ILP) (Schrijver 1998) to find a globally consistent solution, accounting for exclusion and occlusion between objects.”
Discrete-continuous optimization for multi-target tracking (2012, background): “One way to do this is to restrict the set of possible object locations, such as by requiring trajectories to exactly pass either through the individual detections [13], or through a set of pre-computed tracklets [26, 27].”
Seq-NMS for Video Object Detection (2016, methodology): “Other classes of methods tried to compute all of the object trajectories at once using linear programming [6, 2].”
Online Multi-Target Tracking Using Recurrent Neural Networks (2016, methodology): “Here, the problem is cast as a linear program and solved via relaxation [3, 18], shortest-path [14,16] or max-flow algorithms [4].”
Intelligent multi-camera video surveillance: A review (2013, background): “…with spatio-temporal reasoning (Alexander and Lucchesi , xxxx; Huang and Russell, 1997; Pasula et al., 1999; Veenman et al., 2001; Javed et al., 2003; Shafique and Shah, 2003; Morariu and Camps, 2006; Jiang et al., 2007; Song and Roy-Chowdhury, 2008; Hamid et al., 2010; Kuo et al., 2010).”
Learning to associate: HybridBoosted multi-target tracker for crowded scene (2009, methodology): “, Euclidean distance [2], single Gaussian distribution [6] and stump function for max speed [4]).”
On pairwise costs for network flow multi-object tracking (2014, background): “With the advances in object detection, “tracking-bydetection” have recently become a popular paradigm for object tracking [5, 8, 13, 17].”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, background): “, 2014), linear programs (Jiang et al., 2007), Hungarian algorithm (Bae and Yoon, 2014), general-”
Towards Real-Time Multi-Object Tracking (2019, background): “Data association thus can be solved by minimizing some fixed [15,26,44] or learned [19] cost, or by more complex optimization such as multi-cuts [35] and minimum cliques [43].”
Multi-target tracking by continuous energy minimization (2011, methodology): “In particular, continuous optimization also significantly improved the output of a state-of-the-art discrete tracker based on ILP [2].”
Tracking Without Bells and Whistles (2019, background): “The data association can then be formulated as maximum flow [4] or, equivalently, minimum cost problem with either fixed costs based on distance [26, 49, 66], including motion models [39], or learned costs [36].”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, background): “The data association can then be formulated as maximum flow [4] or, equivalently, minimum cost problem [28, 35, 45, 64], both efficiently solved to (near-)global optimality with LP, with a superior performance compared to frame-by-frame [29] or track-by-track [3] methods.”
Multi-target tracking by learning local-to-global trajectory models (2015, methodology): “For example, [24] used Viterbi algorithm to get optimal object sequences, [38,23,39] used the Hungarian algorithm to simultaneously optimize all trajectories, [22] used Quadratic Boolean Programming to couple the detection and estimation of trajectory hypotheses, [2] formulated multi-target tracking”
Multiple Object Tracking Using K-Shortest Paths Optimization (2011, critical): “However, Jiang et al. [4] require a priori knowledge of the number of objects to be tracked, which seriously limits its applicability in real life situations.”
Learning a Neural Solver for Multiple Object Tracking (2019, background): “The data association can then be formulated as maximum flow [8] or, equivalently, minimum cost problem with either fixed costs based on distance [29, 52, 73], including motion models [42], or learned costs [40].”
TrackFormer: Multi-Object Tracking with Transformers (2021, methodology): “Graphs have been used for track association and longterm re-identification by formulating the problem as a maximum flow (minimum cost) optimization [3] with distance based [20, 36, 62] or learned costs [24].”
Global data association for multi-object tracking using network flows (2008, background): “[7] builds a set of subgraphs for every object trajectory with edges between them representing the object interactions.”
Globally-optimal greedy algorithms for tracking a variable number of objects (2011, methodology): “Such graph-based algorithms include flow-networks [25], linear-programming formulations [14], and matching algorithms [15].”
Multiple object tracking: A literature review (2014, background): “Extend dynamic programming [125], linear programming [126], [127], [128], quadratic”