Bridging the gaps between cameras

By Dimitrios Makris, T. Ellis, J. Black. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

357 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4ea0ed06daa083e13d1c9ecb4ab4dd33cff0f549

How researchers see this paper

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

Citations in the corpus

Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views (2008, methodology): “In this paper, we organize the multi-camera tracking literature into two major categories based on the requirement of overlapping or non-overlapping views.”
Relaxed Pairwise Learned Metric for Person Re-identification (2012, unknown): “[23] and Rahimi et al.”
Intelligent multi-camera video surveillance: A review (2013, background): “For correspondence-free approaches, Ellis et al. (2003), Makris et al. (2004) learn the temporal transitions between sources and sinks from the cross-correlation between disappearing events and appearing events.”
Learning semantic scene models from observing activity in visual surveillance (2005, background): “Table III illustrates the success rate for different values of and the overall success rate which is 85.7%.”
Multi-camera activity correlation analysis (2009, methodology): “Most previous work on multi-camera activity analysis with non-overlapping views focuses on two related issues: (1) object re-identification (inter-camera object tracking) [2, 6, 7, 14] and (2) camera network topology inference [6, 12, 16].”
Person re-identification by symmetry-driven accumulation of local features (2010, background): “Other approaches assume easier operative conditions: they simplify the problem by adding temporal reasoning on the spatial layout of the monitored environment, in order to prune the candidate set to be matched [10, 14, 17].”
Appearance modeling for tracking in multiple non-overlapping cameras (2005, background): “Object correspondences were not assumed to be known in [10], while they were assumed to be known in [14].”
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking (2016, background): “People entry and exit points may be explicitly modeled on the ground [6,18,19,26] or image plane [24,27].”
A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance (2008, background): “The cameras would need to establish correspondences between each other and their relative position within the network [51], [88].”
Person Re-identification by Descriptive and Discriminative Classification (2011, unknown): “[14] and Rahimi et al.”
A survey of approaches and trends in person re-identification (2014, unknown): “Entry–exit points of each camera and transition times between cameras are learned in [20], in order to calibrate all the cameras in the network.”
Features for Multi-target Multi-camera Tracking and Re-identification (2018, background): “People entry and exit points may be explicitly modeled on the ground [14, 19, 42, 48] or image plane [32, 39].”