Looking to Relations for Future Trajectory Forecast

Abstract

Inferring relational behavior between road users as well as road users and their surrounding physical space is an important step toward effective modeling and prediction of navigation strategies adopted by participants in road scenes. To this end, we propose a relation-aware framework for future trajectory forecast. Our system aims to infer relational information from the interactions of road users with each other and with the environment. The first module involves visual encoding of spatio-temporal features, which captures human-human and human-space interactions over time. The following module explicitly constructs pair-wise relations from spatio-temporal interactions and identifies more descriptive relations that highly influence future motion of the target road user by considering its past trajectory. The resulting relational features are used to forecast future locations of the target, in the form of heatmaps with an additional guidance of spatial dependencies and consideration of the uncertainty. Extensive evaluations on the public benchmark datasets demonstrate the robustness and efficacy of the proposed framework as observed by performances higher than the state-of-the-art methods.

Multiple Object Forecasting: Predicting Future Object Locations in Diverse Environments

“…Pedestrian trajectory forecasting has been studied extensively in a surveillance setting from fixed cameras from a birds-eye view [1,44,12,7,46]. Methods typically focus on interactions between pedestrians and social conventions such as the pioneering Social Long-Short-Term-Memory (Social-LSTM) model [1], in addition to scene semantics.…”

Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis

“…This task is named as multimodal trajectory prediction. Note that a small part of methods [4,16] re-formulate this task by predicting probabilistic maps in pixel level. We mainly discuss prevailing approaches that outputs multiple possible trajectories of spatial coordinate system (meters) in real world in this paper.…”

Indoor Future Person Localization from an Egocentric Wearable Camera

“…Future person location and movement trajectory prediction have been an active research area, but predictions in most studies have only been carried out in videos captured from birds-eye or oblique views [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17]. Social-LSTM was proposed in [11] to predict human trajectory, which uses social pooling layers to model the effect of nearby people's behaviours on a person's future trajectory.…”

“…Most works on future person location and trajectory prediction, however, have only been focused on scenes captured by birds-eye or oblique views [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], or from vehicle-mounted cameras [18], [19], [20], [21], [22], [23]. Little research has been carried out in egocentric scenarios captured by wearable cameras [24], [25], [26].…”