Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors

By Bo Wu, Ramkant Nevatia. International Journal of Computer Vision, 2007

841 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/49bdd3fb166e0faf7ad1c917aee32c22ebc0f9db

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

DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation (2017, background): “Therefore, part and shape based models are introduced in [10, 20, 39], where ensembles of classifiers are built for specific body parts and regions.”
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].”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, background): “The context information inves tigated in previous works includes regions surrounding objects [9, 12, 22], object-scene interaction [ 13], and the presence, location, orientation and size relationship among ob jects [3, 57, 58, 11, 41, 22, 49, 13, 61, 12, 59, 40, 10, 45, 51].”
Modeling Occlusion by Discriminative AND-OR Structures (2013, background): “…models estimate the visibilities of parts from image appearance, using assumptions that the visibility of a part is independent from other parts [30] [29] [13], is consistent with neighbouring parts [7] [9], or is consistent with its parent or child parts describing object appearance at…”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, background): “Researchers have attempted to address this issue by adopting part-based detection methods [29, 57, 101], where one constructs boosted classiﬁers for speciﬁc body parts such as the head and shoulder to estimate the people counts in a designated area [54].”
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.”
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].”
Robust Object Tracking by Hierarchical Association of Detection Responses (2008, methodology): “2) and check whether they are occluded by other objects by applying the occupancy map based occlusion reasoning method in [6] to T L.”
Robust tracking-by-detection using a detector confidence particle filter (2009, methodology): “[26] additionally learn color histograms for each part, which however do not always distinguish very well.”
Multiobject tracking as maximum weight independent set (2011, background): “Tracking-bydetection approaches have demonstrated impressive results in addressing these challenges [16, 8, 13, 22, 1, 10, 23, 3, 4].”
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017, neutral): “object-scene interaction [60], [61], and the presence, location, orientation and size relationship among objects [33], [58], [59], [60], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72].”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, neutral): “[3], [41], [42], [88], [89], [91].”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, methodology): “As a consequence, using the output of an object detector as observation has become increasingly popular (e.g. Okuma et al. 2004; Avidan 2005; Gavrila and Munder 2007; Wu and Nevatia 2007; Zhang et al. 2008; Leibe et al. 2008b).”