Tracking Social Groups Within and Across Cameras

@article{Solera2017TrackingSG,
  title={Tracking Social Groups Within and Across Cameras},
  author={Francesco Solera and Simone Calderara and Ergys Ristani and Carlo Tomasi and Rita Cucchiara},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2017},
  volume={27},
  pages={441-453}
}
We propose a method for tracking groups from single and multiple cameras with disjointed fields of view. [...] Key Method Multicamera group tracking is handled inside the framework by adopting an orthogonal feature encoding that allows the classifier to learn inter- and intra-camera feature weights differently. Experiments were carried out on a novel annotated group tracking data set, the DukeMTMC-Groups data set. Since this is the first data set on the problem, it comes with the proposal of a suitable…Expand
Multi-target Tracking in Multiple Non-overlapping Cameras Using Fast-Constrained Dominant Sets
TLDR
This paper proposes fast-constrained dominant set clustering (FCDSC), a novel method which is several orders of magnitude faster (close to real time) than existing methods for solving multi-target tracking in non-overlapping cameras and shows that it can be used in conjunction with state-of-the-art video-based re-identification algorithms, to increase their already good performances. Expand
Enhancing the association in multi‐object tracking via neighbor graph
TLDR
This work first utilizes the spatio-temporal relations produced by the tracking self to efficiently select suitable neighbors for the targets, then employs the graph convolution networks (GCN) to learn the graph features. Expand
Multi-camera Multi-Object Tracking
TLDR
This work model's the tracking problem as a global graph, and adopts Generalized Maximum Multi Clique optimization problem as the core algorithm to take both across frame and across camera data correlation into account all together. Expand
Deep Neural Network with Extracted Features for Social Group Detection
TLDR
In the latest years, the use of deep neural networks (DNNs) for learning and detecting has been increased, and in this work, DNNs are used for detecting social groups with extracted features. Expand
Data-driven Online Group Detection Based on Structured Prediction
TLDR
This paper extends the features of pairwise trajectories with velocity and orientation to obtain more valid information and adopts the adaptive-sampling BCFW algorithm to learn the mapping from trajectories to groups. Expand
Extensions of dominant sets and their applications in computer vision
TLDR
This thesis proposes a method for simultaneous clustering and outliers detection, and shows that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, the author is in a position to extract groups of dominant sets clusters which are constrained to contain user-specified elements. Expand
Wide-Baseline Multi-Camera Calibration using Person Re-Identification
TLDR
This work proposes a method that uses ideas from person re-identification (re-ID) for wide-baseline camera calibration, which first employs a re-ID method to associate human bounding boxes across cameras, then converts bounding box correspondences to point correspondences, and finally solves for camera pose using multi-view geometry and bundle adjustment. Expand
Group Split and Merge Prediction With 3D Convolutional Networks
TLDR
This work formulates this as a video prediction problem, where group splits or merges are predicted given a history of geometric social group shape transformations, and develops a modified C3D model that performs significantly better at predicting the occurrence of splits and merges. Expand
Towards a Principled Integration of Multi-camera Re-identification and Tracking Through Optimal Bayes Filters
TLDR
This work presents a theoretically principled way of integrating ReID with tracking formulated as an optimal Bayes filter, which conveniently side-steps the need for dataassociation and opens up a direct path from full images to the core of the tracker. Expand
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies
TLDR
The robustness of the data-driven approach is demonstrated by tracking multiple targets using their appearance, motion, and even interactions and it outperforms previous works on multiple publicly available datasets including the challenging MOT benchmark. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 53 REFERENCES
Improving multi-target tracking via social grouping
  • Zhen Qin, C. Shelton
  • Computer Science
  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
TLDR
A general optimization framework that adds social grouping behavior (SGB) to any basic affinity model based upon a simple affinity model is built and shows very promising performance on two publicly available real-world datasets with different tracklet extraction methods. Expand
Target Identity-aware Network Flow for online multiple target tracking
TLDR
It is shown that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. Expand
Detection and tracking of groups in crowd
TLDR
The method embeds plausible human behaviors to predict interactions in a crowd by iteratively minimizing the error between predictions and measurements and outperforms existing group localization techniques on three publicly available datasets. Expand
Probabilistic group-level motion analysis and scenario recognition
TLDR
This work builds on a mature multi-camera multi-target person tracking system that operates in real-time and derives probabilistic models to analyze individual track motion as well as group interactions to recognize group interactions without making hard decisions about the underlying group structure. Expand
Joint Individual-Group Modeling for Tracking
TLDR
A novel probabilistic framework that jointly models individuals and groups for tracking, promoting the idea that groups are better modeled if individuals are considered and vice versa and provides convincing results on two recent challenging tracking benchmarks. Expand
Associating Groups of People
TLDR
A novel people group representation and a group matching algorithm are proposed that addresses changes in the relative positions of people in a group and the latter deals with variations in illumination and viewpoint across camera views. Expand
Learning to Divide and Conquer for Online Multi-target Tracking
TLDR
This paper claims that the ambiguities in tracking could be solved by a selective use of the features, by working with more reliable features if possible and exploiting a deeper representation of the target only if necessary. Expand
Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings
TLDR
A third-order graphical model is proposed that is able to jointly estimate correct trajectories and group memberships over a short time window and a set of experiments underline the importance of joint reasoning for data association in crowded scenarios. Expand
Structured learning for detection of social groups in crowd
TLDR
A new Structural SVM-based learning framework able to solve the group detection task by exploiting annotated video data to deduce a sociologically motivated distance measure founded on Hall's proxemics and Granger's causality is built. Expand
Decentralized particle filter for joint individual-group tracking
TLDR
The proposed strategy factorizes the joint individual-group state space in two dependent subspaces where individuals and groups share the knowledge of the jointindividual-group distribution, promoting the idea that groups are better tracked if individuals are considered, and viceversa. Expand
...
1
2
3
4
5
...