OCR Applied for Identification of Vehicles with Irregular Documentation Using IoT

Abstract

Given the lack of investments in surveillance in remote places, this paper presents a prototype that identifies vehicles in irregular conditions, notifying a group of people, such as a network of neighbors, through a low-cost embedded system based on the Internet of things (IoT). The developed prototype allows the visualization of the location, date and time of the event, and vehicle information such as license plate, make, model, color, city, state, passenger capacity and restrictions. It also offers a responsive interface in two languages: Portuguese and English. The proposed device addresses technical concepts pertinent to image processing such as binarization, analysis of possible characters on the plate, plate border location, perspective transformation, character segmentation, optical character recognition (OCR) and post-processing. The embedded system is based on a Raspberry having support to GPS, solar panels, communication via 3G modem, wi-fi, camera and motion sensors. Tests were performed regarding the vehicle’s positioning and the percentage of assertiveness in image processing, where the vehicles are at different angles, speeds and distances. The prototype can be a viable alternative because the results were satisfactory concerning the recognition of the license plates, mobility and autonomy.

A Survey of AI Techniques in IoT Applications with Use Case Investigations in the Smart Environmental Monitoring and Analytics in Real-Time IoT Platform

“…The works of Glasenapp et al in [50] and Tham et al in [51] proposed innovative systems to improve public safety. Their works focus on the development of IoT solutions for license plate recognitions from video streams.…”

“…The addition of hardware accelerations is one solution to meet this demand. While the algorithms can be adapted for deployments on edge devices, it is noteworthy that additional GPUs will be required to achieve better performances, as shown in the studies of Glasenapp et al in [50], Tham et al in [51], Abdullah et al in [53], Dilshad et al in [55] and Cao et al in [58].…”

A Review of Automation and Sensors: Parameter Control of Thermal Treatments for Electrical Power Generation

“…Furthermore, within this realm, extensive exploration has been undertaken in smart grids [142][143][144] and the realm of the IoT [145]. Within this framework, machine learning stands as a subset of AI focused on constructing algorithms through data learning rather than predefined instructions [146].…”

Video-Based Human Activity Recognition Using Deep Learning Approaches

“…Another frequently used strategy is that of streams, in which various types of input are processed in different networks, the most common is the two-stream network that processes RGB video frames in one and an optical stream in the other; Hao and Zhang employed this architecture [ 29 ]. The use of artificial intelligence models is growing in line with increased processing power, making deep learning applications increasingly popular [ 30 ]; these applications include time series prediction [ 31 , 32 , 33 ] and classification, especially in computer vision [ 34 , 35 , 36 ].…”