For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this paper we investigate the usage of optical flow for predicting future semantic segmentations. To do so we propose a model that forecasts flow fields autoregressively. Such predictions are then used to guide the inference of a learned warping function that moves instance segmentations on to future frames. Results on the Cityscapes dataset demonstrate the effectiveness of optical-flow methods.

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping / Ciamarra A.; Becattini F.; Seidenari L.; Del Bimbo A.. - ELETTRONICO. - 13233 LNCS:(2022), pp. 349-361. (Intervento presentato al convegno International Conference on Image Analysis and Processing) [10.1007/978-3-031-06433-3_30].

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping

Ciamarra A.;Becattini F.;Seidenari L.;
2022

Abstract

For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this paper we investigate the usage of optical flow for predicting future semantic segmentations. To do so we propose a model that forecasts flow fields autoregressively. Such predictions are then used to guide the inference of a learned warping function that moves instance segmentations on to future frames. Results on the Cityscapes dataset demonstrate the effectiveness of optical-flow methods.
2022
Image Analysis and Processing – ICIAP 2022
International Conference on Image Analysis and Processing
Ciamarra A.; Becattini F.; Seidenari L.; Del Bimbo A.
File in questo prodotto:
File Dimensione Formato  
ICIAP_231-1.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 4.33 MB
Formato Adobe PDF
4.33 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1281140
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact