Robust Object Tracking by Hierarchical Association of Detection Responses

By Chang Huang, Bo Wu, Ramkant Nevatia. European Conference on Computer Vision, 2008

565 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/ce4331e3728100af129d849da6a954149946e816

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

In Safety, Risk, Reliability and Quality

Citations in the corpus

Multiple Object Tracking Using K-Shortest Paths Optimization (2011, unknown): “Huang et al. [22] explore the hierarchical version of the same concept, while Li et al. [23] use a variant of AdaBoost to automatically learn the best criterion for linking low-level tracks together.”
Multi-target tracking by learning local-to-global trajectory models (2015, methodology): “Please cite this article as: S. Zhang, et al., Multi-target tracking by learning local-to-global trajectory models, Pattern Recognition (2014), http://dx.doi.org/10.1016/j.patcog.2014.08.013i approaches can do better to overcome errors by detections and association.”
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor (2015, unknown): “(e.g. A1 = {d1, d10, d23}) during the time of presence; i.e. (V T1 ,DT1 )→ A.”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, background): “…approaches, which link detection responses to trajectories by global optimization based on position, size, and appearance similarity [1], [3], [18], [26], [30], [36], [48], the combination of object detectors and particle filtering results in algorithms that are more suitable for…”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “However, unlike [48, 24], we do not require any human supervision.”
Multiple object tracking: A literature review (2014, methodology): “Then either a greedy bipartite assignment algorithm [32], [111], [123] or the optimal Hungarian algorithm [31], [39], [58], [66], [124] are employed to determine the matching between nodes in the two sets.”
Recent advances and trends in visual tracking: A review (2011, background): “Huang et al. [103] presented a detection-based three-level hierarchical association approach to robustly track multiple objects in crowded environments.”
Subgraph decomposition for multi-target tracking (2015, background): “For example, it is common to first group single-frame hypotheses into tracklets spanning several adjacent frames, and then combine them into complete tracks [12, 19, 24, 11, 22, 23, 2].”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, background): “In recent years, tracking has been successfully extended to scenarios with multiple objects [48, 35, 23, 69].”
Social LSTM: Human Trajectory Prediction in Crowded Spaces (2016, background): “Other approaches like [27, 19, 42, 36] showed the use of scene semantics to predict goals and paths for human navigation.”
The Way They Move: Tracking Multiple Targets with Similar Appearance (2013, methodology): “This is a fair assumption for tracklets that are close to each other in time and akin to assume that appearance will stay similar over-time and change slowly in appearance-based target tracking [7, 12, 19].”
Stable multi-target tracking in real-time surveillance video (2011, methodology): “The most recent work [10, 19] further specialises the approach for visual tracking by using not only object detections but also motion estimations or tracklets by applying a standard tracking algorithm for a short period of time after each detection.”
Reliable cell tracking by global data association (2011, background): “[8] first generate reliable tracklets that are fragments of tracks formed by conservative grouping of detection”
Multiobject tracking as maximum weight independent set (2011, methodology): “, ground plane, camera calibration, or entry/exit zones, used in [13, 10].”
Robust tracking-by-detection using a detector confidence particle filter (2009, methodology): “Several recent multi-object tracking-by-detection algorithms address the resulting data association problem by optimizing detection assignments over a larger temporal window [1, 3, 12, 16, 21].”