Multi-camera multi-person tracking for EasyLiving

By John Krumm, Steve Harris, Brian Meyers, Barry Brumitt, M. Hale, Steve Shafer. Proceedings Third IEEE International Workshop on Visual Surveillance, 2000

825 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/36be61a5abccbf49fb26f340bf8ceea84fdb5d14

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

In Electrical and Electronic Engineering

In Global and Planetary Change

Citations in the corpus

EasyLiving: Technologies for Intelligent Environments (2000, methodology): “The EasyLiving person tracking software is described in greater detail in [11], which also contains numerous references to similar work.”
Multicamera People Tracking with a Probabilistic Occupancy Map (2008, methodology): “Occlusion handling is facilitated by using two sets of stereo color cameras [ 14 ].”
Combining multiple depth cameras and projectors for interactions on, above and between surfaces (2010, methodology): “[16] used several stereoscopic cameras to track people throughout the EasyLiving room, enabling such functionality as automatically moving the user’s Windows session to an appropriately viewable display, or pausing a movie when getting up from the couch.”
A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint (2006, background): “[11] use stereo cameras and combine information from multiple stereo cameras in 3D space.”
Location Systems for Ubiquitous Computing (2001, methodology): “Easy Living uses the Digiclops real-time 3D cameras shown in Figure 3 to provide stereo-vision positioning capability in a home environment.(11) Although Easy Living uses high-performance cameras, vision systems typically use substantial amounts of processing power to analyze frames captured with co”
Learning Motion Patterns of People for Compliant Robot Motion (2005, methodology): “Fod et al. [11] use multiple statically mounted laser-range finders and apply Kalman filters to maintain an estimate of the positions of people in everyday environments whereas Krumm et al. [ 30 ] deployed multiple stationary cameras for multi-person tracking in a living room.”
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes (2009, background): “Integration of stereo pairs is another popular approach, adopted by [31], [37], [9], [1] among others.”
M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene (2003, methodology): “Krumm et al. (2000) present an algorithm that has goals very similar to ours.”
A survey on visual surveillance of object motion and behaviors (2004, methodology): “As an example of recognition-based methods, Krumm et al. [57] use color histograms to match regions.”
Kernel-Based Object Tracking (2003, background): “lance [44, 16, 32], perceptual user interfaces [10], augmented reality [26], smart rooms [39, 75, 47 ],”
A survey of active and passive indoor localisation systems (2012, background): “The DfP vision system [18] can track multiple persons using two sets of colours cameras.”
Challenges: device-free passive localization for wireless environments (2007, neutral): “[7], and physical contact systems, e.”
Robotics-Based Location Sensing Using Wireless Ethernet (2002, background): “Microsoft Research’s Easy Living uses stereo-vision cameras to measure three-dimensional position in a home environment [25].”
WLAN location determination via clustering and probability distributions (2003, background): “Examples include GPS [7], wide-area cellular-based systems [16], infrared-based systems [18, 3], ultrasonic-based systems [12], various computer vision systems [9], physical contact systems [11], and radio frequency (RF) based systems [4, 20, 14, 5, 13, 10, 8].”
Intelligent multi-camera video surveillance: A review (2013, background): “Color histograms of the whole image regions are widely used as global features to match objects across camera views because they are robust to the variations of poses and viewpoints (Orwell et al., 1999; Krumm et al., 2000; Mittal and Davis, 2003; Park et al., 2006; Cheng and Piccardi, 2006).”