Pedestrian crossing prediction using multiple context-based models

Bonnin, Sarah; Weisswange, Thomas H.; Kummert, Franz; Schmuedderich, Jens

doi:10.1109/itsc.2014.6957720

Cited by 54 publications

(33 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, [19] uses LIDAR and camera data to predict pedestrian intent based on location and velocity. Bonnin et al [20] use context information to calculate predefined crafted features for intent prediction. [36] proposes hierarchical movements to represent human action and predict human action from human appearance.…”

Section: Related Workmentioning

confidence: 99%

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

Liu

Adeli

Cao

et al. 2020

IEEE Robot. Autom. Lett.

128

View full text Add to dashboard Cite

Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting the next events or actions in videos. In recent years, various models have been developed based on convolution operations for prediction or forecasting, but they lack the ability to reason over spatiotemporal data and infer the relationships of different objects in the scene. In this paper, we present a framework based on graph convolution to uncover the spatiotemporal relationships in the scene for reasoning about pedestrian intent. A scene graph is built on top of segmented object instances within and across video frames. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is very crucial piece of information for autonomous vehicles to navigate safely and more smoothly. We approach the problem of intent prediction from two different perspectives and anticipate the intention-to-cross within both pedestrian-centric and location-centric scenarios. In addition, we introduce a new dataset designed specifically for autonomousdriving scenarios in areas with dense pedestrian populations: the Stanford-TRI Intent Prediction (STIP) dataset. Our experiments on STIP and another benchmark dataset show that our graph modeling framework is able to predict the intention-to-cross of the pedestrians with an accuracy of 79.10% on STIP and 79.28% on Joint Attention for Autonomous Driving (JAAD) dataset up to one second earlier than when the actual crossing happens. These results outperform baseline and previous work. Please refer to http://stip.stanford.edu/ for the dataset and code.Index Terms-spatiotemporal graphs, forecasting, graph neural networks, autonomous-driving. Recent work [19]-[23] introduced pedestrian intent prediction and have typically tackled the problem by observing pedestrian-specific features such as location, velocity, and

show abstract

Section: Related Workmentioning

confidence: 99%

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

Liu

Adeli

Cao

et al. 2020

IEEE Robot. Autom. Lett.

128

View full text Add to dashboard Cite

show abstract

“…The computation problems are solved in [12], yet being applied only for static scenes with learned trajectories. Last, [13] looks at the distance of the pedestrian from the kerb, position and velocity of the car from the cross-walk to learn an "Inner city model " to predict pedestrian crossings.…”

Section: Related Workmentioning

confidence: 99%

Natural vision based method for predicting pedestrian behaviour in urban environments

Vasishta

Vaufreydaz

Spalanzani

2017

2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

This paper proposes to model pedestrian behaviour in urban scenes by combining the principles of urban planning and the sociological concept of Natural Vision. This model assumes that the environment perceived by pedestrians is composed of multiple potential fields that influence their behaviour. These fields are derived from static scene elements like side-walks, cross-walks, buildings, shops entrances and dynamic obstacles like cars and buses for instance. Using this model, autonomous cars increase their level of situational awareness in the local urban space, with the ability to infer probable pedestrian paths in the scene to predict, for example, legal and illegal crossings.

show abstract

“…This is done by using motion prediction models (cf. [18], [19], [20], [21], [22], [23]). Using motion prediction models afterwards, instead of using the implemented behaviour model for simulation, for pre-filtering has got advantages.…”

Section: Extracting Relevant Situationsmentioning

confidence: 99%

From Simulation Data to Test Cases for Fully Automated Driving and ADAS

Sippl

Bock

Wittmann

et al. 2016

Testing Software and Systems

View full text Add to dashboard Cite

Within this paper we present a new concept on deriving test cases from simulation data and outline challenging tasks when testing and validating fully automated driving functions and Advanced Driver Assistance Systems (ADAS). Open questions on topics like virtual simulation and identification of relevant situations for consistent testing of fully automated vehicles are given. Well known criticality metrics are assessed and discussed with regard to their potential to test fully automated vehicles and ADAS. Upon our knowledge most of them are not applicable to identify relevant traffic situations which are of importance for fully automated driving and ADAS. To overcome this limitation, we present a concept including filtering and rating of potentially relevant situations. Identified situations are described in a formal, abstract and human readable way. Finally, a situation catalogue is built up and linked to system requirements to derive test cases using a Domain Specific Language (DSL).

show abstract

Pedestrian crossing prediction using multiple context-based models

Cited by 54 publications

References 14 publications

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

Natural vision based method for predicting pedestrian behaviour in urban environments

From Simulation Data to Test Cases for Fully Automated Driving and ADAS

Contact Info

Product

Resources

About