Discrete-continuous optimization for multi-target tracking

By Anton Andriyenko, Konrad Schindler, Stefan Roth. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

372 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4954559cfa985a89aa5a75aa40112da376091908

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Affinity Network for Multiple Object Tracking (2018, neutral): “2 37.0 13.9 19.9 32092.9 180183.8 3334.6 389.5 CompACT [95]+CMOT [19] 12.6 36.1 16.1 18.6 57885.9 167110.8 285.3 3.8 CompACT [95]+H2T [25] 12.4 35.7 14.8 19.4 51765.7 173899.8 852.2 3.0 RCNN [94]+DCT [96] 11.7 38.0 10.1 22.8 336561.2 210855.6 758.7 0.7 CompACT [95]+IHTLS [97] 11.1 36.8 13.8 19.9 539”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, methodology): “A different line of attack is to develop sophisticated motion models in order to better predict a tracked person’s location, most notably models that include interactions between nearby people [1, 10, 35, 44, 47, 56].”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “Early studies (Zamir et al., 2012; Andriyenko et al., 2012) use different object detection methods for evaluating MOT methods.”
Multi-target tracking by learning local-to-global trajectory models (2015, background): “As they consider more global information, these association Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/pr Pattern Recognition http://dx.doi.org/10.1016/j.patcog.2014.08.013 0031-3203/Crown Copyright & 2014 Published by Elsevier Ltd.”
Simple online and realtime tracking with a deep association metric (2017, neutral): “For example, ﬂow network formulations [1, 2, 3] and probabilistic graphical models [4, 5, 6, 7] have become popular frameworks of this type.”
Learning People Detectors for Tracking in Crowded Scenes (2013, methodology): “People detection is a key building block of most stateof-the-art people tracking methods [3, 22, 23].”
Object Detection from Video Tubelets with Convolutional Neural Networks (2016, background): “The large number of tracking-by-detection methods [1, 2, 3, 26] for multi-pedestrian tracking have shown that temporal information could be utilized to regularize the detection re-sults.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Therefore, Andriyenko et al. (2012) argue that a joint discrete and continuous formulation describes the tracking problem more naturally.”
Memory Based Online Learning of Deep Representations from Video Streams (2017, methodology): “iple Object Tracking algorithms typically adopt appearance and motion cues into an afﬁnity model to estimate and link detections to form tracklets which are afterwards combined into ﬁnal trajectories [27,28,29,30,31,32]. Most existing MOT methods are applied to pedestrian tracking and either use sim”
Video Instance Segmentation Tracking With a Modified VAE Architecture (2020, background): “Video object tracking [1, 4, 35, 54, 63, 65, 68] uses bounding boxes to identify the target objects and to estimate their positions in the subsequent frames.”
Deep Network Flow for Multi-object Tracking (2017, background): “While on-line methods only have access to the past and current observations, off-line (or batch) approaches [3, 9, 20, 1, 40, 54] also consider future frames or even the whole sequence at once.”
GMMCP tracker: Globally optimal Generalized Maximum Multi Clique problem for multiple object tracking (2015, methodology): “On the other two sequences which no tracking results are reported, we compare our method with competitive approaches which for we have access to their code including KSP [8], DCT [4], CMOT [5], IHTLS [13] and GMCP [27].”
Multiple object tracking: A literature review (2014, methodology): “Different MOT algorithms from previous works can now be thought as designing different approaches to solving the above MAP problem, either from a probabilistic inference perspective [6], [31], [32], [33], [34], [35], [36], [37] or a deterministic optimization perspective [16], [38], [39], [40], [41]”