Robust tracking-by-detection using a detector confidence particle filter

By Michael D. Breitenstein, Fabian Reichlin, Bastian Leibe, Esther Koller-Meier, Luc Van Gool. IEEE International Conference on Computer Vision, 2009

669 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/17d65b2f276bc3b92f4a92567becc4fe41ffcb69

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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust Visual Tracking and Vehicle Classification via Sparse Representation (2011, background): “Tracking can also be combined with either detection [1], [5], [44] or recognition [15], [28], [29], [36], [39], [47].”
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].”
3D Traffic Scene Understanding From Movable Platforms (2014, neutral): “Conclusions are drawn in Section 6.”
Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures (2012, methodology): “These methods might be placed into a few broad categories: those that aim to distinguish the foreground regions of images from the background [33, 12, 65, 39], segment images into distinct regions to perform localization [35, 23, 56], track an object over a sequence of images (after its position has”
Robust tracking using local sparse appearance model and K-selection (2011, methodology): “Discriminative methods formulate tracking as a classification problem [3] [4] [6] [11].”
D Traffic Scene Understanding from Movable Platforms (2013, background): “For a long time, dynamic objects have been considered either in isolation [5], [26], [27], [52] or using simple motion [9], [23], [42], [47], [63] or social interaction [15], [62] models.”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, background): “In contrast to our previous work [5], [6], we increase the robustness of the tracker by detecting reappearing persons that temporally left the scene.”
Joint Probabilistic Data Association Revisited (2015, methodology): “To manage a scenario with multiple objects, typically a greedy or local assignment process is used to resolve data association [8].”
Stable multi-target tracking in real-time surveillance video (2011, background): “The first group covers feed-forward systems which use only current and past observations to estimate the current state [7, 1, 2].”
Recent advances and trends in visual tracking: A review (2011, methodology): “In Breitenstein et al. [98], proposed a multi-person tracking-by-detection algorithm with a cascade detection conﬁdence threshold mechanism, which aims at avoiding the errors introduced by the online learning classiﬁer.”
Learning a Neural Solver for Multiple Object Tracking (2019, background): “Data association can be done on a frame-by-frame basis for online applications [10, 20, 51] or track-by-track [7].”
Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings (2010, neutral): “This thus means some latency as opposed to typical online trackers [15, 18, 19].”
Part-based multiple-person tracking with partial occlusion handling (2012, methodology): “In every frame, the detections are associated with existing trajectories by a greedy bipartite assignment algorithm [17] which has also been used in [4, 21].”
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs (2012, neutral): “Quantitative results are provided in Table 2 [11,20].”
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking (2020, methodology): “One is that most methods are based on the tracking-by-detection paradigm [1], which is plausible but suboptimal due to the infeasibility of global (end-to-end) optimization.”
Deep Affinity Network for Multiple Object Tracking (2018, methodology): “Most motion modeling techniques [20], [29], [30] use linear motion models under constant velocity assumption [20].”
Tracking-Learning-Detection (2012, methodology): “Such techniques have been applied to tracking of faces in lowframe-rate video [52], multiple hockey players [53], or pedestrians [54], [55].”