Header

UZH-Logo

Maintenance Infos

EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras


Mitrokhin, Anton; Ye, Chengxi; Fermüller, Cornelia; Aloimonos, Yiannis; Delbruck, Tobi (2019). EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras. arXiv.org 1903.07520, University of Zurich.

Abstract

We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network with just 40k parameters, which is able to compute depth and egomotion.
Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fast moving objects simultaneously in the camera field of view. The objects and the camera are tracked by the VICON motion capture system. By 3D scanning the room and the objects, accurate depth map ground truth and pixel-wise object masks are obtained, which are reliable even in poor lighting conditions and during fast motion. We then train and evaluate our learning pipeline on EV-IMO and demonstrate that our approach far surpasses its rivals and is well suited for scene constrained robotics applications.

Abstract

We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network with just 40k parameters, which is able to compute depth and egomotion.
Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fast moving objects simultaneously in the camera field of view. The objects and the camera are tracked by the VICON motion capture system. By 3D scanning the room and the objects, accurate depth map ground truth and pixel-wise object masks are obtained, which are reliable even in poor lighting conditions and during fast motion. We then train and evaluate our learning pipeline on EV-IMO and demonstrate that our approach far surpasses its rivals and is well suited for scene constrained robotics applications.

Statistics

Downloads

1 download since deposited on 14 Feb 2020
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Working Paper
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2019
Deposited On:14 Feb 2020 11:10
Last Modified:14 Feb 2020 11:14
Series Name:arXiv.org
ISSN:2331-8422
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:https://arxiv.org/abs/1903.07520

Download

Green Open Access

Download PDF  'EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras'.
Preview
Content: Published Version
Filetype: PDF
Size: 4MB