Tracking multiple humans in complex situations

By Tao Zhao, Ramkant Nevatia. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

576 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b60ea458dc5d571c7bc028d9fd98fb545c0070d1

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Monocular Pedestrian Detection: Survey and Experiments (2009, background): “These include application-specific constraints such as the flat-world assumption, ground-plane-based objects and common geometry of pedestrians, e.g., object height or aspect ratio [15], [23], [39], [50], [62], [82].”
Pose estimation for a partially observable human body from RGB-D cameras (2015, background): “Zhao and Nevatia [10] and Gammeter et al.”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, background): “While many tracking methods rely on background subtraction from one or several static cameras [3], [20], [24], [42], [49], recent progress in object detection has stimulated interest in combining tracking and detection.”
Robust tracking-by-detection using a detector confidence particle filter (2009, background): “While many approaches rely on background subtraction from one or several static cameras [3, 14, 23, 27], recent progress in object detection has increased interest in combining tracking and detection [2, 16, 20, 26].”
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes (2009, methodology): “For a detailed review of the state of the art in tracking research, the reader is referred to the recent survey by Yilmaz et al. [61].”
Unsupervised Bayesian Detection of Independent Motion in Crowds (2006, background): “For qualitative comparison, the video and Figures 7 and 8 show side-by-side performance of our independent motion detector on the sequences from Zhao and Nevatia’s [32] and Rittscher et al.’s [18] people tracking, respectively.”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, methodology): “In earlier related work [54], Zhao and Nevatia modeled the human body as a 3D ellipsoid and human hypotheses were proposed based on head top detection from foreground boundary peaks.”
A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint (2006, methodology): “Zhao and Nevatia [3] presented a method for tracking multiple people in a single camera.”
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, unknown): “In Zhao and Nevatia (2004a), a part-based representation is used for segmenting motion blobs by considering various articulations and their appearances but parts are not tracked explicitly.”
Video object tracking using adaptive Kalman filter (2006, background): “Additionally, many works have been done by motion model based human recognition and estimating human body postures [21–25].”
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “Most prior methods that have used world constraints focus on interaction with a ground plane [69] or simply constrain the body to move along the ground plane [74].”
Structured Determinantal Point Processes (2010, background): “We would like a distribution over sets of trajectories that (1) includes sets of different cardinality and (2) prefers sets of trajectories that are spread out in space-time, as objects are likely to be [11, 15].”
Robust Object Tracking by Hierarchical Association of Detection Responses (2008, background): “Traditional feature-based tracking methods, such as those based on color [1], salient points [2] or motion blobs [3], do not have a discriminative model that distinguishes the object category of interest from others.”