PETS2009: Dataset and challenge

By James M. Ferryman, Ali Shahrokni. 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, 2009

523 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cfc58fafd4c39262b0aa52807c24e9db55f8ad53

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Detecting Partially Occluded Objects with an Implicit Shape Model Random Field (2012, unknown): “The PETS 2009 Benchmark Data [16] includes several datasets of which we take View001 of sequence S1.”
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (2020, methodology): “For this release, we organized a Joint Workshop on Tracking and Surveillance in conjunction with the Performance Evaluation of Tracking and Surveillance (PETS) (Ferryman and Ellis 2010; Ferryman and Shahrokni 2009) workshop and the Conference on Vision and Pattern Recognition (CVPR) in 2017.”
Transformer Networks for Trajectory Forecasting (2020, background): “In fact, TrajNet is a superset of diverse datasets that requires to train on four families of trajectories, namely 1) BIWI Hotel [33] (orthogonal bird’s eye ﬂight view, moving people), 2) Crowds UCY [28] (3 datasets, tilted bird’s eye view, camera mounted on building or utility poles, moving people)”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “Some of the most widely used multi-object tracking evaluation datasets include the PETS09 (Ferryman and Shahrokni, 2009), PETS16 (Patino), KITTI (Geiger et al., 2012), MOT15 (Leal-Taix´e et al., 2015) and MOT16 (Milan et al., 2016), and UAVDT (Du et al., 2018) (Zitnick and Doll´ar, 2014) with the…”
Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment (2020, methodology): “It has a wide range of applications in pedestrian monitoring [1], [2], video surveillance [3]–[5], in-store customer behavior analysis [6], city trafﬁc control [7], and crowd behavior analysis [8], [9].”
Vision Meets Drones: A Challenge (2018, methodology): “Speciﬁcally, the PETS09 [45] and PETS16 [46] datasets mainly focus on multi-pedestrian detection, tracking and counting in the surveillance scenarios.”
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs (2012, methodology): “One common approach to computing the motion cost is to calculate the deviation from a presumed model, such as constant velocity.”
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (2021, background): “PETS2009 [11] dataset is one of the earliest in this area.”
DETRAC: A New Benchmark and Protocol for Multi-Object Tracking (2015, methodology): “The PETS2009 dataset is a large crowd dataset that focuses on multi-pedestrian tracking and counting.”
Deep learning in video multi-object tracking: A survey (2019, methodology): “8http://www.xiaoyumu.com/project/detection 9https://detrac-db.rit.albany.edu/Tracking 10https://www.d2.mpi-inf.mpg.de/node/428 11http://www.cvg.reading.ac.uk/PETS2009/a.html”
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking (2018, unknown): “ch [14] 132k 347k D ! 2012 KAIST [23] 95k 86k D ! ! 2015 KITTI-D [19] 15k 80:3k D ! ! 2014 MOT17Det [1] 11:2k 392:8k D ! 2017 CARPK [22] ! 1:5k 90k D ! 2017 Okutama [3] ! 77:4k 422:1k D 2017 PETS2009 [18] 1:5k 18:5k D,M ! 2009 KITTI-T [19] 19k > 47:3k M ! ! 2014 MOT15 [26] 11:3k > 101k M ! 201”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Whereas PETS and TUD only provide data from a static observer, the others were acquired with a mobile platform which comes closer to the autonomous driving setting.”
A survey of video datasets for human action and activity recognition (2013, background): “PETS 2009, Winter-PETS 09, PETS 2010 2009 [42,193]/[52,53] Crowd Behavior”
Object Tracking Benchmark (2015, methodology): “There exist several datasets for visual tracking in the surveillance scenarios, such as the VIVID [14], CAVIAR [21], and PETS databases.”
Joint Probabilistic Data Association Revisited (2015, methodology): “We demonstrate the performance of our method for visual tracking in surveillance by evaluating our results on the popular PETS 2009 video sequences [15], in particular those with high target density: S1.”
Individualness and Determinantal Point Processes for Pedestrian Detection (2016, methodology): “Finally, while finding the optimal subset of detections using a DPP is NP-hard, we show that a simple and efficient greedy algorithm performs favorably against existing pedestrian detection methods on the INRIA [5], PETS 2009 [9], and EPFL Terrace [10] datasets.”
Continuous Energy Minimization for Multitarget Tracking (2014, background): “Six of them are part of the PETS 2009/2010 benchmark [17], [18].”
Learning People Detectors for Tracking in Crowded Scenes (2013, background): “L2 [12], as well as the recent ParkingLot dataset [16].”