Part-based multiple-person tracking with partial occlusion handling

By Guang Shu, Afshin Dehghan, Omar Oreifej, Emily M. Hand, Mubarak Shah. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

370 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/084352b63e98d3b3310521fb3bda8cb4a77a0254

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism (2017, background): “Most works [21, 49, 41, 23, 45] aim at utilizing better detectors for handling partial occlusion.”
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs (2012, methodology): “This is a data association problem for which we can use any available data association method, such as bipartite matching[5,4].”
Features for Multi-target Multi-camera Tracking and Re-identification (2018, background): “Formulations with polynomial time solutions consider evidence along paths of time-consecutive edges [8, 16, 31, 37, 38, 39, 55, 75, 78] and some build on bipartite matching [12, 14, 20, 26, 42, 62, 71].”
Multi-class Open Set Recognition Using Probability of Inclusion (2014, methodology): “For multi-class recognition problems in computer vision, posterior probabilities are widely used to make decisions in applications such as pedestrian classification and orientation estimation [18], image retrieval [15], attribute fusion [42], part-based human tracking [47], large-scale multi-class o”
In defense of color-based model-free tracking (2015, background): “pedestrian tracking [11, 36, 37, 40]), it is often desirable to build a generic tracker which can readily be used for arbitrary object classes.”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, methodology): “Inspired by their result, we argue that the bottleneck of existing tracking methods is the used representations with their corresponding similarity scores.”
Deep Affinity Network for Multiple Object Tracking (2018, methodology): “The local methods [42], [43], [44] generally consider only two frames for data associ-”
Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning (2014, methodology): “[16] uses a partbased model to correctly associate detections under partial occlusion.”
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.”
Learning People Detectors for Tracking in Crowded Scenes (2013, background): “We also compare our method to two other state-of-the-art multi-person trackers [16, 23].”
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.”
Subgraph decomposition for multi-target tracking (2015, neutral): “[17] - - - - - - - - - - - 79.”
Visual Tracking: an Experimental Survey (2013, neutral): “To detect the structures of the parts from the first few frames is not trivially achievable, but see [79], [80].”
A Convnet for Non-maximum Suppression (2015, methodology): “4.2 PARKINGLOT RESULTS To verify that our Tnet can generalize beyond PETS, we run the same DPM detector as on the PETS experiment over the ParkingLot sequence and do NMS using the networks trained on PETS training set only.”
Spatial-Temporal Relation Networks for Multi-Object Tracking (2019, background): “According to what kind of information is used to establishing the association between objects in different frames, the existing methods can be categorized into online methods [2, 12, 19, 27, 33, 35, 38, 47, 50, 58, 59, 9], and offline methods [7, 14, 36, 39, 40, 44, 51, 52, 53, 62].”
Real-time part-based visual tracking via adaptive correlation filters (2015, background): “Recently part-based tracking methods [1, 9, 19, 34, 37, 47] become more popular partially because of their favor-”