Abstract
This article defines a new methodology for pre-recognition of events with object motion analysis in a video without any prior knowledge. This unsupervised application is named as ‘conceptualization’. This conceptualization technique is also tested with real-time video data in an internet of things (IoT) architecture. The merits of rough sets in the framework of granular computing are explored to execute the task. The proposed method is designed for the video sequences that are acquired by simple static RGB sensors. Here the video sequences are granulated with our newly defined ‘motion granules’ and then those are modeled as rough sets over this granulation for moving object/ background estimation. Video conceptualization is performed afterwards by quantifying the approximation with a new measure, namely, motion entropy. The values obtained by this measure reflect the amount of uncertainty present in the motion of each individual moving object which enables precognition of events. The effectiveness of the proposed method is verified with extensive experiments in identifying the different motion patterns present in a video sequence. The frames with possibilities of events present therein are identified with this analysis. Both offline and real-time sequences are used for this verification. An IoT architecture is formed to test the proposed algorithm with physical devices in identifying the frames containing possible events.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.