Continuous Energy Minimization for Multitarget Tracking

By Anton Milan, Stefan Roth, Konrad Schindler. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

583 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ea971778c6bab3a968e8dc731f7e2db06b5666f1

How researchers see this paper

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

In Economics and Econometrics

Citations in the corpus

Online Multi-Object Tracking with Dual Matching Attention Networks (2018, background): “Numerous approaches [37,39,58,47,45,51,48] use detections from past and future frames for batch processing.”
Opening up Open World Tracking (2021, background): “Early effort focused on developing strong data association techniques [11,39,41,50,63,65] and hand-crafting appearance [23, 49, 52] and motion cues [15, 38].”
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking (2015, methodology): “CEM [36] formulates the problem in terms of a high-dimensional continuous energy.”
Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priors (2021, methodology): “Our energy formulation shares some similarities with the energy function utilized by Milan et al. (2014) for multiple object tracking, which also included a data ﬁt term, pairwise interaction terms between tracked objects as well as unary potentials encoding physical motion constraints (analogous…”
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, background): “[31] formulate multi-object tracking as minimization of a continuous energy and focus on designing the energy function.”
Multi-scale object candidates for generic object tracking in street scenes (2016, methodology): “We compare to two state-of-the-art tracking-by-detection methods [2], [5], for which we obtained tracking results from the authors.”
Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning (2014, methodology): “Thus, the global association is very crucial in this approach, and many methods [2, 6, 21] for global association have been proposed.”
MOT20: A benchmark for multi object tracking in crowded scenes (2020, methodology): “Following a recent trend [1], [9], [15], we employ two sets of measures that have established themselves in the literature: The CLEAR metrics proposed by Stiefelhagen et al .”
GSM: Graph Similarity Model for Multi-Object Tracking (2020, background): “Most meth-ods assumed that the objects move smoothly in the image space and designed different motion models to capture the dynamic behaviour of individual objects such as linear motion model [Milan et al. , 2013; Breitenstein et al. , 2009] and nonlinear motion model [Yang and Nevatia, 2012].”
VirtualWorlds as Proxy for Multi-object Tracking Analysis (2016, methodology): “eep Learning Baselines for MOT Thanks to the recent progress on object detection, association-based tracking-by-detection in monocular video streams is particularly successful and widely used for MOT [29,30,31,32,33,34,35,36,37,38] (see [39] for a recent review). These methods consist in building tr”
Joint Probabilistic Data Association Revisited (2015, methodology): “Within computer vision, applications of multi-target tracking are exemplified by the tasks of surveillance of a crowd of pedestrians [5, 25, 28, 29, 33, 44], and of tracking dense cellular and sub-cellular structures in biological sequences [11, 35] (Fig.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Milan et al. (2014) extend the continuous energy function of Andriyenko & Schindler (2011) to take into account physical constraints such as target dynamics, mutual exclusion, and track persistence.”
MOT16: A Benchmark for Multi-Object Tracking (2016, methodology): “The easiest sequence for tracking (S2L1) consisted of a scene with few pedestrians, and for that sequence state-of-the-art methods perform extremely well with accuracies of over 90% given a good set of initial detections [23], [33], [47].”
Learning to rank in person re-identification with metric ensembles (2015, background): “Future works include learning mid-level features [21] for person re-id, incorporating depth from a single monocular image [23], integrating person re-id with person detector [29, 30] and improving multiple target tracking of [26] with the proposed approach.”
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks (2021, background): “On the other hand, batch methods [46]–[51] need to have access to global information (i.”
Multiple Hypothesis Tracking Revisited (2015, unknown): “2 CEM [29] 19.”
Online Multi-Target Tracking Using Recurrent Neural Networks (2016, background): “Conversely, more complex cost functions have been considered in (Leibe, Schindler, and Van Gool 2007; Milan, Roth, and Schindler 2014), but without any theoretical bounds on optimality.”
Quasi-Dense Similarity Learning for Multiple Object Tracking (2020, methodology): “To remedy this problem, some methods introduce motion estimation [7, 30] or displacement regression [10, 35, 54] to ensure accurate distance estimation.”