Learning to Forecast Pedestrian Intention from Pose Dynamics
Authors:
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1277-1284
Abstract
For an autonomous car, the ability to foresee a humans action is very useful for mitigating the risk of a possible collision. To humans this pedestrian intention foresight comes naturally as they are able to recognize another person's actions just by perceiving subtle changes in posture. Approximating this intention inference ability by directly training a deep neural network is useful but especially challenging. First, sufficiently large datasets for intention recognition with frame-wise human pose and intention annotations are rare and expensive to compile. Second, training on smaller datasets can lead to overfitting and make it difficult to adapt to intra-class variations in action executions. Therefore, in this paper, we propose a real time framework that learns (i) intention recognition using weak-supervision and (ii) locomotion dynamics of intention from pose information using transfer learning. This new formulation is able to tackle the lack of frame-wise annotations and to learn intra-class variation in action executions. We empirically demonstrate that our proposed approach leads to earlier and more stable detection of intention than other state of the art approaches with real time operation and the ability to detect intention one second before the pedestrian reaches the kerb.Keywords
This publication has 17 references indexed in Scilit:
- Robust Optimization for Deep Regression2015
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Goal-Directed Pedestrian Prediction2015
- Pedestrian Intention and Pose Prediction through Dynamical Models and Behaviour Classification2015
- Fine-grained classification of pedestrians in video: Benchmark and state of the art2015
- Pedestrian intention recognition using Latent-dynamic Conditional Random Fields2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Joint probabilistic pedestrian head and body orientation estimation2014
- More than one pathway to action understandingTrends in Cognitive Sciences, 2011
- Pedestrians at the kerb – Recognising the action intentions of humansTransportation Research Part F: Traffic Psychology and Behaviour, 2009