CNN, Segmentation or Semantic Embeddings: Evaluating Scene Context for Trajectory Prediction
Document Type
Conference Proceeding
Publication Date
12-7-2020
Publication Title
International Symposium on Visual Computing
First page number:
706
Last page number:
717
Abstract
For autonomous vehicles (AV) and social robot’s navigation, it is important for them to completely understand their surroundings for natural and safe interactions. While it is often recognized that scene context is important for understanding pedestrian behavior, it has received less attention than modeling social-context – influence from interactions between pedestrians. In this paper, we evaluate the effectiveness of various scene representations for deep trajectory prediction. Our work focuses on characterizing the impact of scene representations (sematic images vs. semantic embeddings) and scene quality (competing semantic segmentation networks). We leverage a hierarchical RNN autoencoder to encode historical pedestrian motion, their social interaction and scene semantics into a low dimensional subspace and then decode to generate future motion prediction. Experimental evaluation on the ETH and UCY datasets show that using full scene semantics, specifically segmented images, can improve trajectory prediction over using just embeddings.
Keywords
Trajectory prediction; Scene context; RNN autoencoder
Disciplines
Computer Sciences | Numerical Analysis and Scientific Computing | Physical Sciences and Mathematics
Language
English
Repository Citation
Syed, A.,
Morris, B.
(2020).
CNN, Segmentation or Semantic Embeddings: Evaluating Scene Context for Trajectory Prediction.
International Symposium on Visual Computing
706-717.
http://dx.doi.org/10.1007/978-3-030-64559-5_56