PROJECT TITLE :
Abnormal Scene Change Detection From a Moving Camera Using Bags of Patches and Spider-Web Map
This paper proposes a novel surveillance system for detecting exceptional scene changes as abnormal events with a mobile camera mounted on a robot. In distinction to abnormal event analysis using mounted cameras, three key problems ought to be tackled in this technique, i.e., scene construction, robot localization, and scene comparison. For the first problem, scene construction, a clustering theme is proposed for extracting a set of key frames from the surveillance atmosphere. Each key frame is any divided into a collection of patches, which forms a sparse illustration for representing scene contents. In addition to the compression impact, the scheme will tackle the consequences of misalignment and lighting changes well. For the localization problem, a unique patch matching method is proposed to cut back not only the size of the search area but also the scale of the feature dimensions in similarity matching. To prune the search house, a set of projection kernels is used to construct a ring structure. Then, one order of time complexity within the similarity calculation can be reduced from the structure. Once scene searching, the robot location isn't continuously sure to be successfully registered to the scene map. So, a novel spider-web map is proposed to tackle the effect of misalignment and then detect completely different exceptional scene changes from the videos. The proposed method has been rigorously tested on a selection of videos to demonstrate its superiority in object detection and abnormal scene amendment detection.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here