Multicamera People Tracking with a Probabilistic Occupancy Map

By Franccois Fleuret, Jérôme Berclaz, Richard Lengagne, Pascal Fua. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

945 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/07d61392606dade00c08704e78f1c19b66d75261

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

Vision Meets Drones: A Challenge (2018, methodology): “The datasets in [45], [48] are recorded using multi-camera with fully overlapping views in constrained environments.”
Multiple Object Tracking Using K-Shortest Paths Optimization (2011, neutral): “The results of this comparative evaluation are presented in Ellis et al. [37] and illustrated in Fig. 3. They show that, for the tracking task, our current approachoutperformstheothersubmittedmethods.Furthermore,our earlier DynamicProgramming-based approach[ 3 ] isalsoshowntoperformwell.Intheremaind”
Features for Multi-target Multi-camera Tracking and Re-identification (2018, background): “Formulations with polynomial time solutions consider evidence along paths of time-consecutive edges [8, 16, 31, 37, 38, 39, 55, 75, 78] and some build on bipartite matching [12, 14, 20, 26, 42, 62, 71].”
Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment (2020, methodology): “[14] project targets into a probabilistic occupancy map (POM), and combine occupancy probabilities with color and motion attributes in the tracking process.”
Intelligent multi-camera video surveillance: A review (2013, methodology): “The behavior maps are combined with the multi-people tracking algorithm proposed in (Fleuret et al., 2007) under HMM.”
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking (2016, methodology): “ Th | {z } handover : (2) 4 Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, Carlo Tomasi Dataset IDs Duration Cams Actors Overlap Blind Spots Calib. Resolution FPS Scene Year Laboratory [8] 3 2.5 min 4 Yes Yes No Yes 320x240 25 Indoor 2008 Campus [8] 4 5.5 min 3 Yes Yes No Yes 320x240 2”
Building occupancy estimation and detection: A review (2018, background): “easily provide the number of indoor occupants [61].”
Online Model Distillation for Efficient Video Inference (2018, methodology): “Prior specialization approaches rely on tedious configuration of models [25, 9] or careful selection of model training samples so as not to miss rare events [26].”
On-line Boosting and Vision (2006, methodology): “More sophisticated methods, like a global occurrence-map [23] would limit these problems.”
Deep Affinity Network for Multiple Object Tracking (2018, methodology): “The approaches following this pipeline exploit several distinct types of representation models, including; appearance models [10], [11], [12], [13], motion models [14], [15], [16], [17], and composite models [9], [18], [19].”
Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes (2016, background): “Over the past decade, Multi-Target Tracking (MTT) algorithms have made great progress in solving the data association problem as a graph theoretic problem [34,35,36,30,37,38].”
Multiple object tracking: A literature review (2014, methodology): “The Probabilistic Occupancy Map (POM) [42], [88] is employed to estimate how likely an object would occur in a specific grid cell.”
Learning a Neural Solver for Multiple Object Tracking (2019, background): “Moreover, matrix A, is totally unimodular [6, 1], which implies that the integrality constraints can be relaxed to box constraints yint ∈ [0, 1]|E|×1.”
A Novel Performance Evaluation Methodology for Single-Target Trackers (2015, neutral): “The activity in the field is reflected in abundance of new tracking algorithms presented in journals and at conferences summarized in the many survey papers, e.g., [1], [2], [3], [4], [5], [6], [7].”
Individualness and Determinantal Point Processes for Pedestrian Detection (2016, methodology): “We evaluate the proposed algorithm with comparisons to other methods on the INRIA [5], PETS 2009 [9], and EPFL Terrace [10] datasets.”
Multi-view traffic sign detection, recognition, and 3D localisation (2011, methodology): “[9] use a multi-view probabilistic occupancy map for people detection and tracking.”