Related Experiment Video
Updated: Jun 20, 2026
07:44
Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
Published on: March 23, 2019
DriveNet: A comprehensive dataset for driver posture recognition to enhance ergonomics and safety
Aishwarya N1, Ganesh Kumar Chellamani1, Sakthi Abirami Balakrishnan2
1Department of ECE, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, Tamil Nadu, India.
Data in Brief
|June 19, 2026
Summary
A new dataset, DriveNet, was created to train machine learning models for recognizing poor driving postures. This system aims to alert drivers, reducing musculoskeletal disorders and improving driver health.
Area of Science:
- Ergonomics and Occupational Health
- Computer Vision and Machine Learning
Background:
- Poor driving posture is a significant risk factor for musculoskeletal disorders among occupational drivers.
- Current driver monitoring systems often overlook seating posture, despite its impact on health and comfort.
Purpose of the Study:
- To introduce the DriveNet dataset, a novel resource for developing machine learning models for driver posture recognition.
- To facilitate research into automated systems that promote optimal seating posture and mitigate ergonomic risks.
Main Methods:
- Development of the DriveNet dataset, comprising 11,160 high-resolution RGB images.
- Images capture four distinct driver posture classes using an Android smartphone camera.
- The dataset is designed to represent various improper seating postures.
Main Results:
- The DriveNet dataset provides a comprehensive resource for training and evaluating driver posture recognition algorithms.
- It enables the development of alert systems to guide drivers toward better posture.
Conclusions:
- The DriveNet dataset is crucial for advancing machine learning-based driver posture classification.
- This resource will support the creation of systems to minimize ergonomic risks and enhance occupational driver well-being.
