Treffer: Developing a deep learning-based system for automated speed limit identification and monitoring using Raspberry Pi.

Sadly, traffic accidents are commonplace in the modern era. Our deep learning-based system for automatic speed limit identification on posted limits was developed to circumvent this issue. The technology for capturing and detecting billboards relies heavily on digital image processing. The collected signs are resized by the appropriate means by the image processing algorithms. The work suggested aims to automate the process of identifying limitations on speed on limited-speed sign boards with the aid of a pi camera and a raspberry pi zero 2 W. The suggested method uses deep learning to identify and extract data from signs in real-world images captured by a Pi camera connected to a Raspberry Pi. The raspberry pi is fed data that includes many different speed restriction signs. The raspberry pi processor gets the input through pi camera and it is compared using the data set and relying on such the system recognizes the speed limit sign and displays on LCD module along with it activates the buzzer if the system finds a sign board. The model will be assessed utilizing standard performance indicators such as reliability, recollection, precision, and F1 score. As a consequence, the system can take preventative measures against human error, such as that which causes vehicular accidents. Python is used for the system's development and deep learning is employed for the system's image processing. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)