# Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition

arXiv: https://arxiv.org/abs/2004.14747 · HTML: https://mlsanity.com/paper/2004.14747/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance](https://mlsanity.com/paper/2103.14231/) (2021)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment](https://mlsanity.com/paper/2503.17267/) (2025)
- [Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users' Trajectories](https://mlsanity.com/paper/2106.02598/) (2021)
- [Testing predictive automated driving systems: lessons learned and future recommendations](https://mlsanity.com/paper/2205.10115/) (2022)
- [Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion](https://mlsanity.com/paper/2203.02489/) (2022)
- [A Spatio-Temporal Multilayer Perceptron for Gesture Recognition](https://mlsanity.com/paper/2204.11511/) (2022)
- [Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2405.19202/) (2024)
- [From Pedestrian Detection to Crosswalk Estimation: An EM Algorithm and Analysis on Diverse Datasets](https://mlsanity.com/paper/2205.12579/) (2022)
- [Local and Global Contextual Features Fusion for Pedestrian Intention Prediction](https://mlsanity.com/paper/2305.01111/) (2023)
- [Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction](https://mlsanity.com/paper/2407.17162/) (2024)
- [Pedestrian Motion State Estimation From 2D Pose](https://mlsanity.com/paper/2103.00145/) (2021)
- [Fisheye Camera and Ultrasonic Sensor Fusion For Near-Field Obstacle Perception in Bird's-Eye-View](https://mlsanity.com/paper/2402.00637/) (2024)
- [Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information](https://mlsanity.com/paper/2106.15991/) (2021)
- [Cyclist Intention Detection: A Probabilistic Approach](https://mlsanity.com/paper/2104.09176/) (2021)
- [RCP-RF: A Comprehensive Road-car-pedestrian Risk Management Framework based on Driving Risk Potential Field](https://mlsanity.com/paper/2305.02493/) (2023)
- [Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle](https://mlsanity.com/paper/2309.06313/) (2023)
- [Reliable Heading Tracking for Pedestrian Road Crossing Prediction Using Commodity Devices](https://mlsanity.com/paper/2410.06400/) (2024)

## Abstract (arXiv)

According to several reports published by worldwide organisations, thousands of pedestrians die in road accidents every year. Due to this fact, vehicular technologies have been evolving with the intent of reducing these fatalities. This evolution has not finished yet since, for instance, the predictions of pedestrian paths could improve the current Automatic Emergency Braking Systems (AEBS). For this reason, this paper proposes a method to predict future pedestrian paths, poses and intentions up to 1s in advance. This method is based on Balanced Gaussian Process Dynamical Models (B-GPDMs), which reduce the 3D time-related information extracted from keypoints or joints placed along pedestrian bodies into low-dimensional spaces. The B-GPDM is also capable of inferring future latent positions and reconstruct their associated observations. However, learning a generic model for all kind of pedestrian activities normally provides less ccurate predictions. For this reason, the proposed method obtains multiple models of four types of activity, i.e. walking, stopping, starting and standing, and selects the most similar model to estimate future pedestrian states. This method detects starting activities 125ms after the gait initiation with an accuracy of 80% and recognises stopping intentions 58.33ms before the event with an accuracy of 70%. Concerning the path prediction, the mean error for stopping activities at a Time-To-Event (TTE) of 1s is 238.01mm and, for starting actions, the mean error at a TTE of 0s is 331.93mm.