Video Spatio-Temporal Filtering Based on Cameras and Target Objects Trajectories -- Videosurveillance Forensic Framework

Abstract

To cite this version:Dana Codreanu, André Péninou, Florence Sèdes. Video spatio-temporal filtering based on cameras and target objects trajectories -Videosurveillance forensic framework. 10 th International Conference on Availability, Reliability and Security (ARES 2015) Abstract-This paper presents our work about assisting videosurveillance agents in the search for particular video scenes of interest in transit network. This work has been developed based on requirements defined within different projects with the French National Police in a forensic goal. The video-surveillance agent inputs a query in the form of a hybrid trajectory (date, time, locations expressed with regards to different reference systems) and potentially some visual descriptions of the scene. The query processing starts with the interpretation of the hybrid trajectory and continues with a selection of a set of cameras likely to have filmed the spatial trajectory. The main contributions of this paper are: (1) a definition of the hybrid trajectory query concept, trajectory that is constituted of geometrical and symbolic segments represented with regards to different reference systems (e.g., geodesic system, road network), (2) a spatiotemporal filtering framework based on a spatio-temporal modeling of the transit network and associated cameras.

(Meta-)data modelling

“…on a trajectory given as a query during a specified interval of time, and to look for cameras that could have filmed this trajectory. Our work can be instantiated in the context of forensic, for example during an investigation [1]. We plan to extend this context in order to be able to deal with real-time queries or predict the trajectories based on statistics realized on stored data.…”

INFORSID 2018 Forum Jeunes Chercheuses Jeunes Chercheurs

“…Cette étude a été appliquée dans le cadre du projet ANR METHODEO 3 . L'approche utilisée dans (Codreanu et al, 2015) vise à aider les opérateurs humains de vidéosurveillance dans la recherche de séquences vidéo d'intérêt en leur proposant un ensemble de caméras susceptibles d'avoir filmé une scène recherchée. Une extension de cette approche est décrite dans (Panta, Sèdes, 2016).…”

Modeling metadata of CCTV systems and Indoor Location Sensors for automatic filtering of relevant video content

“…In the literature, some approaches address post-processing of data that highlight relevant elements (persons, objects, etc.). Video shots search by reconstitution of trajectories is addressed in [2], [3]. Authors have proposed a method which, starting from trajectory segments, selects the cameras that may have filmed the given segments and identifies the video sequences corresponding to each camera according to the inferred locations and time interval.…”

“…To do this, it is necessary to search for cameras whose field of view (which can be variable) intersected the trajectories built in the given interval [t 1 , t 2 ]. Using the hasSeen operator defined in [2], [12] as follows: given a spatial trajectory composed of segments t r = (u 1 , . .…”