Related Experiment Video
Updated: Sep 17, 2025
16:14
Trajectory Data Analyses for Pedestrian Space-time Activity Study
Published on: February 25, 2013
13.7K
A pedestrian group crossing intention prediction model integrating spatiotemporal features
Hai Zou1, Yongqing Guo2, Fulu Wei1
1School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo, 255000, China.
Scientific Reports
|July 2, 2025
Summary
Predicting pedestrian crossing intentions is key for road safety. This study introduces a model using spatiotemporal data and group information to improve pedestrian behavior prediction for autonomous vehicles.
Area of Science:
- Computer Science
- Robotics
- Transportation Engineering
Background:
- Pedestrians are vulnerable road users (VRUs) lacking protection in traffic accidents.
- Accurate pedestrian behavior prediction is vital for advanced driver-assistance systems (ADAS), autonomous vehicles, and traffic management.
Purpose of the Study:
- To develop a pedestrian group crossing intention prediction model for autonomous driving.
- To enhance prediction accuracy by integrating spatiotemporal features and group dynamics.
Main Methods:
- The model integrates spatiotemporal features: pedestrian pose key points, 2D positional trajectories, and group information.
- Utilized JAADbeh and JAADall datasets for experimental validation.
Main Results:
- The proposed model demonstrated superior performance in accuracy, precision, and F1-Score.
- Achieved 0.82 accuracy on the large-scale JAADall dataset, showing robustness.
- Incorporating pedestrian group information significantly improved prediction accuracy, especially for groups.
Conclusions:
- The study offers a reliable framework for pedestrian intention prediction in autonomous driving and intelligent transportation systems.
- Provides a foundation for future research on non-visual features and complex scenarios.
Related Concept Videos
01:03Prediction Intervals
2.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.3K
01:07End Point Prediction: Gran Plot
605
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
For potentiometric titration, the Gran plot is created by plotting...
605