A Detection System for Stolen Vehicles Using Vehicle Attributes With Deep Learning

There is phenomenal growth in numbers of vehicles on road as well as in numbers of theft cases. In a few countries, vehicle theft cases are believed to be one in every 10 minutes. In such high-intensity scenario, it is not possible to identify the stolen vehicle with traditional methods such as manual check, RFID base technologies where it is easy to manipulate and remove. This paper presents a design with the implementation of a system based on deep learning technique where SSD algorithm is coupled with K-Nearest Neighbors algorithm and convolutional neural network classifier, to identify the stolen/suspicious vehicles without human intervention. This design operates in two stages: At first stage Tensor flow, Tensor Flow detection API from Google is used to detect the vehicle with sub-modules to identify color and registration number from a real-time video stream. In second stage it compares the extracted characteristic i.e. vehicle registration number and color with the RTO record. If in comparison it observes any anomaly in two sets or matched with stolen vehicle complaint record at police station. It would notify the concerned authorities. A prototype model is developed based on the presented design.