Treffer: Pedestrian detection system for automobiles using computer vision and artificial intelligence using Raspberry Pi 4 and webcam.

Traffic accidents involving pedestrians have increased in recent years, causing a large number of deaths worldwide, some of the main causes being: distracted drivers or pedestrians, car blind spots, adverse environmental conditions among others. With the advent of autonomous driving systems at different levels, the development of pedestrian detection systems has become a priority task. In this work, an economical and easy-to-install pedestrian detection system for automobiles is proposed, which uses the Raspberry Pi 4 card, webcam and an LCD screen as hardware. In the software part, a computer vision system with artificial intelligence is implemented using the TensorFlow Lite library for the classification of people in real time, Python and Open CV as programming language and computer vision library. The aim is for the system to visually alert the driver about the presence of pedestrians on both sides of the road or that get in the way of driving in order to avoid possible accidents. [ABSTRACT FROM AUTHOR]

Los accidentes de tránsito que involucran peatones, se han incrementado en los últimos años, causando un gran número de muertes a nivel mundial, siendo algunas de las principales causas: conductores o peatones distraídos, puntos ciegos en el automóvil, condiciones ambientales adversas, entre otras. Con el advenimiento de los sistemas de conducción autónoma en sus diferentes niveles, el desarrollo de sistemas para la detección de peatones se ha vuelto una tarea prioritaria. En este trabajo se propone un sistema de detección de peatones para automóvil económico y de fácil instalación, el cual utiliza como hardware la tarjeta Raspberry Pi 4, cámara web y una pantalla LCD. En la parte del software se implementa un sistema de visión por computadora con inteligencia artificial utilizando la librería TensorFlow Lite para la clasificación de personas en tiempo real, Python y Open CV como lenguaje de programación y librería de Visión por computadora. Se busca que el sistema alerte al conductor de forma visual sobre la presencia de peatones a ambos lados del camino o que se interpongan en la trayectoria de conducción con el objetivo de evitar posibles accidentes. [ABSTRACT FROM AUTHOR]

Copyright of Journal Applied Computing / Revista de Cómputo Aplicado is the property of ECORFAN-Mexico S.C. 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.)