Tracking Groups of People

By Stephen J. McKenna, S. Jabri, Zoran Duric, Azriel Rosenfeld, Harry Wechsler. Computer Vision and Image Understanding, 2000

776 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/24644d5eb05e6b0ba31bc28b798656b77c4cc004

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

Evaluation of background subtraction techniques for video surveillance (2011, neutral): “Merely, the approaches that incorporate two different features ( Li , McKenna ) were able to stand somewhat out from the bad performance of the other methods.”
A Review on Video-Based Human Activity Recognition (2013, methodology): “[123] propose a method to track groups of people by an adaptive background subtraction method combining color and gradient information to remove shadows and unreliable color cues.”
Detecting Moving Objects, Ghosts, and Shadows in Video Streams (2003, methodology): “In the absence of any a priori knowledge about target and environment, the most widely adopted approach for moving object detection with fixed camera is based on background subtraction [1], [2], [3], [4], [5], [6], [7], [8], [9].”
Recent developments in human motion analysis (2003, methodology): “[35] proposed an adaptive background subtraction method that combined color and gradient information to effectively cope with shadows and unreliable color cues in motion segmentation.”
A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint (2006, methodology): “These and other similar algorithms [ 6 , 7, 8] are challenged by occluding and partially occluding objects, as well as appearance changes.”
A system for learning statistical motion patterns (2006, background): “While there exist some algorithms [23], [24], [28], [31], [39], [51] for tracking multiple objects, most of them fail due to the complexity of motions in crowded traffic scenes.”
Motion history image: its variants and applications (2012, neutral): “, color and gradient information in [95])”
Tracking multiple humans in complex situations (2004, methodology): “In contrast to the ground-level camera setup used in some of the previous work (e.g., [15], [25], etc.), we deploy the camera a few meters above the ground looking down.”
Activity summarisation and fall detection in a supportive home environment (2004, methodology): “The tracker used here employs a particle filter (Iterated Likelihood Weighting [12]) with image evidence provided using an adaptive background model with shadow detection [10].”
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].”
A survey on visual surveillance of object motion and behaviors (2004, methodology): “McKenna et al. [11] use an adaptive background model with color and gradient information to reduce the influences of shadows and unreliable color cues.”
Crowd analysis: a survey (2008, background): “[69] perform tracking at three levels: regions, people and groups.”