İscen, AhmetWang Y.Duygulu, PınarHauptmann, A.2016-02-082016-02-082014-09http://hdl.handle.net/11693/28152Date of Conference: 6-7 and 12 September, 2014Conference name: European Conference on Computer Vision. ECCV 2014: Computer Vision - ECCV 2014 WorkshopsDue to increasing hospital costs and traveling time, more and more patients decide to use medical devices at home without traveling to the hospital. However, these devices are not always very straight-forward for usage, and the recent reports show that there are many injuries and even deaths caused by the wrong use of these devices. Since human supervision during every usage is impractical, there is a need for computer vision systems that would recognize actions and detect if the patient has done something wrong. In this paper, we propose to use Snippet Based Trajectory Statistics Histograms descriptor to recognize actions in two medical device usage problems; inhaler device usage and infusion pump usage. Snippet Based Trajectory Statistics Histograms encodes the motion and position statistics of densely extracted trajectories from a video. Our experiments show that by using Snippet Based Trajectory Statistics Histograms technique, we improve the overall performance for both tasks. Additionally, this method does not require heavy computation, and is suitable for real-time systems. © Springer International Publishing Switzerland 2015.EnglishAction recognitionAssisted living systemsMedical device usageBiomedical equipmentComputer visionGraphic methodsHospitalsInteractive computer systemsMedical computingMedical problemsStatisticsTrajectoriesAction recognitionAssisted livingAssistive technologyComputer vision systemHuman supervisionMedical DevicesStatistics histogramsTraveling timeReal time systemsConference Paper10.1007/978-3-319-16220-1_1