Abstract
Understanding the behaviors and intentions of humans is still one of the main challenges for vehicle autonomy. More specifically, inferring the intentions and actions of vulnerable actors, namely pedestrians, in complex situations such as urban traffic scenes remains a difficult task and a blocking point towards more automated vehicles. Answering the question “Is the pedestrian going to cross?” is a good starting point in order to advance in the quest to the fifth level of autonomous driving. In this paper, we address the problem of real-time discrete intention prediction of pedestrians in urban traffic environments by linking the dynamics of a pedestrian’s skeleton to an intention. Hence, we propose SPI-Net (Skeleton-based Pedestrian Intention network): a representation-focused multi-branch network combining features from 2D pedestrian body poses for the prediction of pedestrians’ discrete intentions. Experimental results show that SPI-Net achieved 94.4% accuracy in pedestrian crossing prediction on the JAAD data set while being efficient for real-time scenarios since SPI-Net can reach around one inference every 0.25 ms on one GPU (i.e., RTX 2080ti), or every 0.67 ms on one CPU (i.e., Intel Core i7 8700K).
Highlights
Within the context of autonomous vehicle development and the field of Advanced DriverAssistance Systems (ADAS), determining the pedestrians’ discrete intention is mandatory
We propose a real-time and context-invariant approach based on 2D pedestrian body poses to address the Crossing/Not Crossing (C/NC) prediction in realistic driving conditions
While we firmly believe that for the task of pedestrian intention prediction, it is better to use pedestrian specific dynamics information and contextual scenes conjointly, we propose in this paper a context-invariant approach based on 2D pedestrian body pose only to address the C/NC task
Summary
Within the context of autonomous vehicle development and the field of Advanced DriverAssistance Systems (ADAS), determining the pedestrians’ discrete intention is mandatory. Preserving the pedestrians’ integrity in a more efficient way than when triggered by an emergency stop once the pedestrians have moved on to the road and become a direct obstacle for the vehicle would be safer for all actors. In such decisive applications, a desirable intention prediction model should run efficiently for real-time usage and should be robust to a multitude of complexities and conditions (e.g., weather, location). The latter requires, Algorithms 2020, 13, 331; doi:10.3390/a13120331 www.mdpi.com/journal/algorithms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
