Related Experiment Video
Updated: Jun 26, 2025
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
Published on: February 6, 2020
Child face detection on front passenger seat through deep learning
Carlos Hernández-Aguilar1, José A Aguilar-Saguilan1, Alejandro I Trejo-Castro2
1Escuela de Ingeniería y Tecnologías, Universidad de Monterrey, San Pedro Garza García, México.
Insights
Car crashes are a leading cause of death for young people. A new child face detection system alerts drivers if a child is in the front seat, preventing fatalities from airbag deployment.
Area of Science:
- Computer Science
- Artificial Intelligence
- Automotive Safety
Background:
- Road traffic accidents are a major cause of mortality among young individuals globally.
- Airbag deployment in frontal collisions poses a lethal risk to children seated in the front passenger seat, particularly those under 13 years of age.
Purpose of the Study:
- To develop and evaluate an interior monitoring system utilizing child face detection to mitigate the risk of child fatalities in car accidents.
- To raise driver awareness regarding the danger of allowing children to occupy the front passenger seat.
Main Methods:
- The system employs deep learning techniques, including transfer learning, fine-tuning, and facial detection, for robust child identification.
- A custom dataset was created for training, and the MobileNetV2 architecture was selected for its performance and low computational cost, enabling implementation on a Raspberry Pi 4B.
- Data augmentation techniques were used to expand the dataset, resulting in 2,496 adult and 2,310 child images.
Main Results:
- The system achieved 98% accuracy and 100% precision in face classification without a sliding window.
- Real-time detection of children in the front passenger seat was accomplished with a 1-second delay per decision, reaching 100% accuracy.
- The developed system demonstrated robust performance in identifying children in the front seat.
Conclusions:
- The study demonstrates the feasibility of implementing a robust, non-invasive child detection system in automobiles using deep learning on a Raspberry Pi 4 Model B.
- While experimental accuracy was 100%, real-world conditions like sunlight and debris may affect performance.
- The system offers a potential solution for enhancing child safety in vehicles by preventing front-seat placement.
Objective:
One of the main causes of death worldwide among young people are car crashes, and most of these fatalities occur to children who are seated in the front passenger seat and who, at the time of an accident, receive a direct impact from the airbags, which is lethal for children under 13 years of age. The present study seeks to raise awareness of this risk by interior monitoring with a child face detection system that serves to alert the driver that the child should not be sitting in the front passenger seat.
Methods:
The system incorporates processing of data collected, elements of deep learning such as transfer learning, fine-tunning and facial detection to identify the presence of children in a robust way, which was achieved by training with a dataset generated from scratch for this specific purpose. The MobileNetV2 architecture was used based on the good performance shown when compared with the Inception architecture for this task; and its low computational cost, which facilitates implementing the final model on a Raspberry Pi 4B.
Results:
The resulting image dataset consisted of 102 empty seats, 71 children (0-13 years), and 96 adults (14-75 years). From the data augmentation, there were 2,496 images for adults and 2,310 for children. The classification of faces without sliding window gave a result of 98% accuracy and 100% precision. Finally, using the proposed methodology, it was possible to detect children in the front passenger seat in real time, with a delay of 1 s per decision and sliding window criterion, reaching an accuracy of 100%.
Conclusions:
Although our 100% accuracy in an experimental environment is somewhat idealized in that the sensor was not blocked by direct sunlight, nor was it partially or completely covered by dirt or other debris common in vehicles transporting children. The present study showed that is possible the implementation of a robust noninvasive classification system made on Raspberry Pi 4 Model B in any automobile for the detection of a child in the front seat through deep learning methods such as Deep CNN.
Related Concept Videos
01:24Prosopagnosia
01:21Association Areas of the Cortex
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...