Pedestrian Motion State Estimation From 2D Pose

  title={Pedestrian Motion State Estimation From 2D Pose},
  author={Fei Li and Shiwei Fan and Pengzhen Chen and Xiangxu Li},
  journal={2020 IEEE Intelligent Vehicles Symposium (IV)},
Traffic violation and the flexible and changeable nature of pedestrians make it more difficult to predict pedestrian behavior or intention, which might be a potential safety hazard on the road. Pedestrian motion state (such as walking and standing) directly affects or reflects its intention. In combination with pedestrian motion state and other influencing factors, pedestrian intention can be predicted to avoid unnecessary accidents. In this paper, pedestrian is treated as non-rigid object… 

Figures and Tables from this paper


Pedestrian Path, Pose, and Intention Prediction Through Gaussian Process Dynamical Models and Pedestrian Activity Recognition
A method to predict future pedestrian paths, poses, and intentions up to 1 s in advance based on balanced Gaussian process dynamical models (B-GPDMs), which reduce the 3-D time-related information extracted from key points or joints placed along pedestrian bodies into low-dimensional spaces.
Pedestrian Intention and Pose Prediction through Dynamical Models and Behaviour Classification
A method to carry out the prediction of pedestrian locations and pose and to classify intentions up to 1 s ahead in time applying Balanced Gaussian Process Dynamical Models (B-GPDM) and naïve-Bayes classifiers and these classifiers are combined in order to increase the action classification precision.
Context-Based Pedestrian Path Prediction
It is demonstrated that the proposed approach results in more accurate path prediction than only SLDS, at the relevant short time horizon (1 s), and slightly outperforms a computationally more demanding state-of-the-art method.
Social LSTM: Human Trajectory Prediction in Crowded Spaces
This work proposes an LSTM model which can learn general human movement and predict their future trajectories and outperforms state-of-the-art methods on some of these datasets.
Learning and predicting on-road pedestrian behavior around vehicles
  • Nachiket Deo, M. Trivedi
  • Computer Science
    2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
  • 2017
This work sub-categorize pedestrian trajectories in an unsupervised manner based on their estimated sources and destinations, and train a separate VGMM for each sub- category, showing that the sub-category VGMMs outperform a monolithic VGMM of equivalent complexity, especially for longer prediction intervals.
Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
This work proposes a solution for the problem of pedestrian action anticipation at the point of crossing using a novel stacked RNN architecture in which information collected from various sources, both scene dynamics and visual features, is gradually fused into the network at different levels of processing.
Context-based detection of pedestrian crossing intention for autonomous driving in urban environments
It is shown that a lack of information about the pedestrian's posture and body movement results in a delayed detection of the pedestrians changing their crossing intention when compared to a human observer.
Pedestrian Path Prediction with Recursive Bayesian Filters: A Comparative Study
A comparative study on recursive Bayesian filters for pedestrian path prediction at short time horizons (< 2s) based on single dynamical models and Interacting Multiple Models combining several such basic models (constant velocity/acceleration/turn).
Multimodal interaction-aware motion prediction for autonomous street crossing
This article proposes a multimodal convolutional neural network framework to predict the safety of a street intersection for crossing and deploys the proposed architectural framework on a robotic platform and conducts real-world experiments that demonstrate the suitability of the approach for real-time deployment and robustness to various environments.
Context-Based Path Prediction for Targets with Switching Dynamics
This work proposes to extract various types of cues with computer vision to provide context on the target’s behavior, and incorporate these in a Dynamic Bayesian Network (DBN), which extends the SLDS by conditioning the mode transition probabilities on additional context states.