Appearance modeling for tracking in multiple non-overlapping cameras

By Omar Javed, Khurram Shafique, Mubarak Shah. Computer Vision and Pattern Recognition, 2005

350 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2b5326c3db946e708fc08d83c69b71601dd2fede

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

1. Xiaogang Wang
2. Yi Yang
3. Shaogang Gong
4. Tao A. Xiang
5. Qi Tian
6. Wanli Ouyang
7. Liang Zheng
8. Luc Van Gool

Citations in the corpus

• Person Re-identification by Descriptive and Discriminative Classification (2011, background): “Javed et al. [ 10 ] learn transitions between cameras to cope with problems such as illumination changes.”
• Color Invariants for Person Reidentification (2013, background): “We refer to this structure as an intradistribution structure, and show that it is invariant under a wide range of imaging conditions while being discriminative enough to be practical.”
• Human Reidentification with Transferred Metric Learning (2012, background): “They learned either the transformations of visual features between camera views [12–15] or visual distance metrics [16–18, 2, 19, 4] from a training set.”
• Shape and Appearance Context Modeling (2007, background): “In [9] the inter-camera brightness transfer functions is learnt to perform people track-linking across multiple cameras.”
• Person Reidentification Using Spatiotemporal Appearance (2006, background): “Recently, the brightness transfer functions between different cameras have been used to track individuals over multiple non-overlapping cameras [14] [8].”
• Deep Metric Learning for Person Re-identification (2014, background): “From 2005, numerous features are used or proposed for person re-identification [7].”
• DeepReID: Deep Filter Pairing Neural Network for Person Re-identification (2014, background): “One could assume the photometric or geometric transform models and learn the model parameters from training samples [18, 33, 34].”
• Locally Aligned Feature Transforms across Views (2013, background): “It has drawn a lot of attentions in recent years [11, 23, 32, 27] because of its important applications in video surveillance [16], such as cross-camera tracking, multi-camera behavior analysis and pedestrian search.”
• A survey of approaches and trends in person re-identification (2014, positive): “In order to model the changes in appearance of objects between two cameras a brightness transfer function (BTF) between each pair of cameras is learned from training data in [71].”
• Local Fisher Discriminant Analysis for Pedestrian Re-identification (2013, background): “To address the illumination variation across cameras, a learned inter-camera Brightness Transfer function (BTF) has been proposed [19].”
• Intelligent multi-camera video surveillance: A review (2013, background): “Javed et al. (2005), Prosser et al. (2008) learn the Brightness Transfer Functions (BTFs) and the bi-directional Cumulative Brightness Transfer Functions (CBTF), which map the color observed in one camera view to that in another camera view, from training examples which are collected from a pair of…”
• Multi-camera activity correlation analysis (2009, background): “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].”
• Deep Metric Learning for Practical Person Re-Identification (2014, background): “From 2005, numerous features are used or proposed for person re-identification [10].”
• Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, background): “, [7, 13, 20, 33, 58, 63, 64, 68, 73, 77, 88, 90, 107, 126, 127]) consider the body as a whole instead.”
• Relaxed Pairwise Learned Metric for Person Re-identification (2012, background): “[24] try to learn transitions between cameras to cope with illumination changes, and Zheng et al.”
• Evaluating Appearance Models for Recognition, Reacquisition, and Tracking (2007, background): “has shown how these changes can be compensated for by learning brightness transfer functions [18].”