2017 · 61 citations · 13 references
EngineeringMachine LearningInformation ForensicsVideo SurveillanceLarge-scale DatasetsVisual SurveillanceImage AnalysisData ScienceIpatch DatasetBiomedical Data ScienceObject TrackingMachine VisionBenchmark DatasetsArena DatasetPets 2017Knowledge DiscoveryMoving Object TrackingComputer ScienceDeep LearningMedical Image ComputingComputer VisionPets 2016Tracking SystemMarine Surveillance
This paper indicates the dataset and challenges evaluated under PETS2017. In this edition PETS continues the evaluation theme of on-board surveillance systems for protection of mobile critical assets as set in PETS 2016. The datasets include (1) the ARENA Dataset; an RGB camera dataset, as used for PETS2014 to PETS 2016, which addresses protection of trucks; and (2) the IPATCH Dataset; a multi sensor dataset, as used in PETS2016, addressing the application of multi sensor surveillance to protect a vessel at sea from piracy. The datasets allow for performance evaluation of tracking in low-density scenarios and detection of various surveillance events ranging from innocuous abnormalities to dangerous and criminal situations. Training data for tracking algorithms is released with the dataset; tracking data is also available for authors addressing only surveillance event detection challenges but not working on tracking.
13
A Novel Method for Video Tracking Performance Evaluation
J. Black, Tim Ellis, Paul L. Rosin · 2003 · 180 citations · Full text