Abandoned Object Detection Using Dual Background Model from Surveillance Videos
Purvi Bhandari, Tushar V. Ratanpara, Dr.Wandra K.H · International Journal of Engineering and Technology · 2017
with increase in threats and concerns in security, detection of suspicious activities in public areas has attracted an enormous level of attention.In general, video processing system are been employed for post-event analysis.However, there is a need to build an intelligent video surveillance system so as to find ways to prevent such events.The proposed system is used todetect the abandoned object from the surveillance videos with the use of dual background model.The division of video into frames is done and are pre-processed.In this approach, dual background method is used to subtract the foreground objects from the background, which generates two backgrounds called buffered background and current background.The foreground blobs are generated using subtraction of the two backgrounds and it is tracked to detect the abandoned objects.Tracking is done by maintaining a Track set which includes blobProperties, namely Area, Centroid, Major Axis length, Minor Axis Length and Convex Area, and two separate count set.The system is tested on various videoswhich are publically available.Keyword -Abandoned object detection, Dual background, Object tracking, Suspicious activity in crowd, Video Surveillance I. INTRODUCTION Video Surveillance has been an immensely popular tool for security for years.In present days, it is very common to see CCTV cameras located at every public places especially in crowded places like airports, shopping malls, railway stations, movie theatres etc. [19][ 20].Due to the increased crime rate around the world, many organizations are deploying video surveillance systems at their locations with Closed Circuit TV (CCTV) cameras.The captured video data is useful to prevent the threats before the crime actually happens [1].Video surveillance accounts for regular inspect of the crowd and the security norms can rely on such systems to facilitate their work.However this task remains labour intensive as it become tedious to monitor the entire day footage to detect that one abnormal event.In order to reduce these efforts, intelligent surveillance systems need to be built that can automatically detect if any suspicious activity is encountered and alert the officials whenever required.This provides an efficient and reliable way of monitoring.In video surveillance system, effective and efficient abandoned object detection is one of the important tasks for public security as the bag may contain dangerous bombing components.An object is considered as abandoned if its owner has left it at a place and the object remains stationary for more than an expected time.Considering a scenario where a person enters with an object and places the object onto the floor or a seat in the detection area.The person then leaves the detection area without the object and does not return to the object for a certain pre-determined duration of time [2].The object continues to remain in the detection area and thus considered as abandoned.These objects are of major concern and needs to be taken care of so as to prevent the hazardous outcome.In order to detect abandoned object from the scene, dual background model is employed.This model comprises two separate backgrounds-Buffered and Current Background.An example image is shown in Fig. 1 below showing abandoned object [3].