Open AccessAn Intelligent Reconnaissance Framework for Homeland Security
Author(s) -
T. Rajesh Kumar,
Dharmender Singh Kushwaha
Publication year - 2019
Publication title -
defence science journal/defence science journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.198
H-Index - 32
eISSN - 0976-464X
pISSN - 0011-748X
DOI - 10.14429/dsj.69.12514
Subject(s) - homeland security , border security , computer security , identification (biology) , computer science , terrorism , tracking (education) , vehicle tracking system , track (disk drive) , automatic identification system , real time computing , artificial intelligence , geography , business , operating system , psychology , pedagogy , botany , archaeology , segmentation , international trade , biology
The cross border terrorism and internal terrorist attacks are critical issues for any country to deal with. In India, such types of incidents that breach homeland security are increasing now a day. Tracking and combating such incidents depends only on the radio communications and manual operations of security agencies. These security agencies face various challenges to get the real-time location of the targeted vehicles, their direction of fleeing, etc. This paper proposes a novel application for automatic tracking of suspicious vehicles in real-time. The proposed application tracks the vehicle based on their registration number, type, colour and RFID tag. The proposed approach for vehicle recognition based on image processing achieves 92.45 per cent accuracy. The RFID-based vehicle identification technique achieves 100 per cent accuracy. This paper also proposes an approach for vehicle classification. The average classification accuracy obtained by the proposed approach is 93.3 per cent. An integrated framework for tracking of any vehicle at the request of security agencies is also proposed. Security agencies can track any vehicles in a specific time period by using the user interface of the application.