Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views
By Omar Javed, Khurram Shafique, Zeeshan Rasheed, Mubarak Shah. Computer Vision and Image Understanding, 2008
331 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/c1b007dc929e7d1841cdccf24708b9381793be22
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
- 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].”
- A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance (2016, methodology): “Spatiotemporal relations have been employed in many areas such as multi-camera surveillance [10], cross-camera tracking [11], and object retrieval [12].”
- Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment (2020, background): “…ambient environment caused by different viewpoints from different cameras make the cross-camera local tracklet matching extremely difficult [12], [13]; 3) The number of cameras in which each target appears, and the number of targets within the entire multi-camera network are both unknown, and…”
- VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild (2019, unknown): “We provide rich context information such as camera IDs, timestamp, tracks relation across cameras, which are potential to facilitate the research on behavior analysis in camera networks, like vehicle behavior modeling [14], cross-camera tracking [7] and graphbased retrieval [24].”
- Re-id: Hunting Attributes in the Wild (2014, background): “In particular, it is a fundamental capability for long-term tracking across multiple disjoint camera views [15].”
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking (2016, methodology): “Lighting variations are addressed through color normalization [18], exemplar based approaches [20], or brightness transfer functions learned with [23, 25] or without supervision [13, 19, 24, 29].”
- A survey of approaches and trends in person re-identification (2014, unknown): “Space-time cues are exploited in [19] to learn inter-camera relationships that are in turn used to constrain correspondences across cameras.”