Anticipating human motion is an essential requirement for au- tonomous vehicles and robots in order to primary guarantee people’s safety. In urban scenarios, they interact with humans, the surrounding environment, and other vehicles relying on several cues to forecast crossing or not crossing intentions. For these reasons, this challenging task is often tackled using both visual and non-visual features to anticipate future actions from 2 s to 1 s earlier the event. Our work primarily aims to revise this standard evaluation protocol to forecast crossing events as early as possible. To this end, we conceive a solu- tion upon an extensively used model for egocentric action an- ticipation (RU-LSTM), proposing to envision future features, or modalities, that can better infer human intentions using a properly attention-based fusion mechanism. We validate our model against JAAD and PIE datasets and demonstrate that an intent prediction model can benefit from these additional clues for anticipating pedestrians crossing events.
Early Pedestrian Intent Prediction via Features Estimation / N. Osman, E. Cancelli, G. Camporese, P. Coscia, L. Ballan (PROCEEDINGS - INTERNATIONAL CONFERENCE ON IMAGE PROCESSING). - In: 2022 IEEE International Conference on Image Processing (ICIP)[s.l] : IEEE, 2022. - ISBN 978-1-6654-9620-9. - pp. 3446-3450 (( convegno 2022 IEEE International Conference on Image Processing (ICIP) tenutosi a Bordeaux, France nel 2022 [10.1109/ICIP46576.2022.9897636].
Early Pedestrian Intent Prediction via Features Estimation
P. Coscia;
2022
Abstract
Anticipating human motion is an essential requirement for au- tonomous vehicles and robots in order to primary guarantee people’s safety. In urban scenarios, they interact with humans, the surrounding environment, and other vehicles relying on several cues to forecast crossing or not crossing intentions. For these reasons, this challenging task is often tackled using both visual and non-visual features to anticipate future actions from 2 s to 1 s earlier the event. Our work primarily aims to revise this standard evaluation protocol to forecast crossing events as early as possible. To this end, we conceive a solu- tion upon an extensively used model for egocentric action an- ticipation (RU-LSTM), proposing to envision future features, or modalities, that can better infer human intentions using a properly attention-based fusion mechanism. We validate our model against JAAD and PIE datasets and demonstrate that an intent prediction model can benefit from these additional clues for anticipating pedestrians crossing events.File | Dimensione | Formato | |
---|---|---|---|
Early_Pedestrian_Intent_Prediction_via_Features_Estimation.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
2.2 MB
Formato
Adobe PDF
|
2.2 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.