Exploiting Semantic Information and Deep Matching for Optical Flow

04/06/2016
by   Min Bai, et al.
0

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level segmentation. For each traffic participant, we use the epipolar constraints that govern each independent motion for faster and more accurate estimation. Our second contribution is a new convolutional net that learns to perform flow matching, and is able to estimate the uncertainty of its matches. This is a core element of our flow estimation pipeline. We demonstrate the effectiveness of our approach in the challenging KITTI 2015 flow benchmark, and show that our approach outperforms published approaches by a large margin.

READ FULL TEXT

page 2

page 7

page 8

page 13

page 14

research
07/26/2016

Joint Optical Flow and Temporally Consistent Semantic Segmentation

The importance and demands of visual scene understanding have been stead...
research
04/18/2019

Deep Rigid Instance Scene Flow

In this paper we tackle the problem of scene flow estimation in the cont...
research
03/10/2023

SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving

Unsupervised optical flow estimation is especially hard near occlusions ...
research
08/07/2019

Mono-Stixels: Monocular depth reconstruction of dynamic street scenes

In this paper we present mono-stixels, a compact environment representat...
research
07/15/2022

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

In this paper we propose USegScene, a framework for semantically guided ...
research
07/29/2023

Freespace Optical Flow Modeling for Automated Driving

Optical flow and disparity are two informative visual features for auton...
research
02/16/2016

Fast, Robust, Continuous Monocular Egomotion Computation

We propose robust methods for estimating camera egomotion in noisy, real...

Please sign up or login with your details

Forgot password? Click here to reset