Detection of Pedestrians in Reverse Camera Using Multimodal Convolutional Neural Networks

Reveles-Gómez, Luis C.; Luna-García, Huizilopoztli; Celaya-Padilla, José M.; Barría-Huidobro, Cristian; Gamboa-Rosales, Hamurabi; Solís-Robles, Roberto; Arceo-Olague, José G.; Galván-Tejada, Jorge I.; Galván-Tejada, Carlos E.; Rondon, David; Villalba-Condori, Klinge O.

doi:10.3390/s23177559

Cited by 2 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fact is that modern vehicles are equipped with various safety systems, e.g., obstacle detection, active cruise control, lane keeping, or blind spot detection system. Each of these systems contributes to improving the safety of all road users [7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Head Displacement during a Frontal Collision at a Speed of 20 km/h—Experimental Studies

Frej

2023

Sustainability

View full text Add to dashboard Cite

The aim of the research is to compare the head displacements of volunteers with the head displacements of the KPSIT C50 dummy, taking into account the change of vehicle seat belts. Unfortunately, sudden braking or collisions between vehicles is becoming more and more common, especially during traffic jams. There is considerable ignorance in the literature on the behavior of the human body during a low-speed collision, which motivates the development of low-speed crash test procedures in order to reduce the risk of cervical spine injuries. The tests were carried out at a teaching station designed to measure the forces in seat belts and the displacements of individual body elements (dummy or volunteer) during a low-speed crash test. The article is part of extensive research on crash tests using volunteers and KPSIT physical dummies. The study involved 150 volunteers who were divided into specific percentile groups. The article compares the head displacements of the constructed KPSIT C50 dummy with the head displacements of volunteers representing the 50th percentile group of the male population. The study conducted with volunteers was under control and was completely safe for people participating in the study. The research shows that the use of a bucket sports seat equipped with four-point or five-point seat belts significantly reduces the movement of the head during a low-speed collision. This type of vehicle seat is safer and provides a reduced risk of injury from hitting the head on the steering column in a low-speed collision when the airbag has not deployed. Moreover, research shows that standard seat belts placed in passenger vehicles allow the head to move freely forward in the event of an accident or low-speed collision. Therefore, if the speed is too low to deploy the airbag, there is a high probability that the driver and passengers will hit their heads against the cockpit of the passenger vehicle during a collision at a speed of 20 km/h.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of Head Displacement during a Frontal Collision at a Speed of 20 km/h—Experimental Studies

Frej

2023

Sustainability

View full text Add to dashboard Cite

show abstract

Multimodal driver emotion recognition using motor activity and facial expressions

Espino-Salinas,

Luna-García,

Celaya-Padilla

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Driving performance can be significantly impacted when a person experiences intense emotions behind the wheel. Research shows that emotions such as anger, sadness, agitation, and joy can increase the risk of traffic accidents. This study introduces a methodology to recognize four specific emotions using an intelligent model that processes and analyzes signals from motor activity and driver behavior, which are generated by interactions with basic driving elements, along with facial geometry images captured during emotion induction. The research applies machine learning to identify the most relevant motor activity signals for emotion recognition. Furthermore, a pre-trained Convolutional Neural Network (CNN) model is employed to extract probability vectors from images corresponding to the four emotions under investigation. These data sources are integrated through a unidimensional network for emotion classification. The main proposal of this research was to develop a multimodal intelligent model that combines motor activity signals and facial geometry images to accurately recognize four specific emotions (anger, sadness, agitation, and joy) in drivers, achieving a 96.0% accuracy in a simulated environment. The study confirmed a significant relationship between drivers' motor activity, behavior, facial geometry, and the induced emotions.

show abstract

Detection of Pedestrians in Reverse Camera Using Multimodal Convolutional Neural Networks

Cited by 2 publications

References 46 publications

Analysis of Head Displacement during a Frontal Collision at a Speed of 20 km/h—Experimental Studies

Analysis of Head Displacement during a Frontal Collision at a Speed of 20 km/h—Experimental Studies

Multimodal driver emotion recognition using motor activity and facial expressions

Contact Info

Product

Resources

About