Single Level Feature-to-Feature Forecasting with Deformable Convolutions

07/26/2019
by   Josip Šarić, et al.
4

Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 10

page 11

page 12

page 15

page 16

page 17

01/26/2021

Joint Forecasting of Features and Feature Motion for Dense Semantic Future Prediction

We present a novel dense semantic forecasting approach which is applicab...
09/21/2018

Recurrent Flow-Guided Semantic Forecasting

Understanding the world around us and making decisions about the future ...
02/19/2021

Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems

Advanced Driver-Assistance Systems rely heavily on perception tasks such...
10/10/2021

Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

Prediction of movements is essential for successful cooperation with int...
07/20/2018

Future Semantic Segmentation with Convolutional LSTM

We consider the problem of predicting semantic segmentation of future fr...
07/27/2021

Vision-Guided Forecasting – Visual Context for Multi-Horizon Time Series Forecasting

Autonomous driving gained huge traction in recent years, due to its pote...
07/30/2019

Orientation-aware Semantic Segmentation on Icosahedron Spheres

We address semantic segmentation on omnidirectional images, to leverage ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.