EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow,
Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with
Monocular or Stereo Algorithms
- URL: http://arxiv.org/abs/2205.03467v1
- Date: Fri, 6 May 2022 20:09:18 GMT
- Title: EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow,
Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with
Monocular or Stereo Algorithms
- Authors: Levi Burner, Anton Mitrokhin, Cornelia Ferm\"uller, Yiannis Aloimonos
- Abstract summary: dataset consists of 41 minutes of data from three 640$times$480 event cameras, one 2080$times$1552 classical color camera.
The dataset's 173 sequences are arranged into three categories.
Some sequences were recorded in low-light conditions where conventional cameras fail.
- Score: 10.058432912712396
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A new event camera dataset, EVIMO2, is introduced that improves on the
popular EVIMO dataset by providing more data, from better cameras, in more
complex scenarios. As with its predecessor, EVIMO2 provides labels in the form
of per-pixel ground truth depth and segmentation as well as camera and object
poses. All sequences use data from physical cameras and many sequences feature
multiple independently moving objects. Typically, such labeled data is
unavailable in physical event camera datasets. Thus, EVIMO2 will serve as a
challenging benchmark for existing algorithms and rich training set for the
development of new algorithms. In particular, EVIMO2 is suited for supporting
research in motion and object segmentation, optical flow, structure from
motion, and visual (inertial) odometry in both monocular or stereo
configurations.
EVIMO2 consists of 41 minutes of data from three 640$\times$480 event
cameras, one 2080$\times$1552 classical color camera, inertial measurements
from two six axis inertial measurement units, and millimeter accurate object
poses from a Vicon motion capture system. The dataset's 173 sequences are
arranged into three categories. 3.75 minutes of independently moving household
objects, 22.55 minutes of static scenes, and 14.85 minutes of basic motions in
shallow scenes. Some sequences were recorded in low-light conditions where
conventional cameras fail. Depth and segmentation are provided at 60 Hz for the
event cameras and 30 Hz for the classical camera. The masks can be regenerated
using open-source code up to rates as high as 200 Hz.
This technical report briefly describes EVIMO2. The full documentation is
available online. Videos of individual sequences can be sampled on the download
page.
Related papers
- Event-Free Moving Object Segmentation from Moving Ego Vehicle [90.66285408745453]
Moving object segmentation (MOS) in dynamic scenes is challenging for autonomous driving.
Most state-of-the-art methods leverage motion cues obtained from optical flow maps.
We propose to exploit event cameras for better video understanding, which provide rich motion cues without relying on optical flow.
arXiv Detail & Related papers (2023-04-28T23:43:10Z) - InstMove: Instance Motion for Object-centric Video Segmentation [70.16915119724757]
In this work, we study the instance-level motion and present InstMove, which stands for Instance Motion for Object-centric Video.
In comparison to pixel-wise motion, InstMove mainly relies on instance-level motion information that is free from image feature embeddings.
With only a few lines of code, InstMove can be integrated into current SOTA methods for three different video segmentation tasks.
arXiv Detail & Related papers (2023-03-14T17:58:44Z) - A Neuromorphic Dataset for Object Segmentation in Indoor Cluttered
Environment [3.6047642906482142]
This paper proposes a new Event-based ESD dataset for object segmentation in an indoor environment.
Our proposed dataset comprises 145 sequences with 14,166 RGB frames that are manually annotated with instance masks.
Overall 21.88 million and 20.80 million events from two event-based cameras in a stereo-graphic configuration are collected.
arXiv Detail & Related papers (2023-02-13T12:02:51Z) - MOSE: A New Dataset for Video Object Segmentation in Complex Scenes [106.64327718262764]
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence.
The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets.
We collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments.
arXiv Detail & Related papers (2023-02-03T17:20:03Z) - Moving Object Detection for Event-based vision using Graph Spectral
Clustering [6.354824287948164]
Moving object detection has been a central topic of discussion in computer vision for its wide range of applications.
We present an unsupervised Graph Spectral Clustering technique for Moving Object Detection in Event-based data.
We additionally show how the optimum number of moving objects can be automatically determined.
arXiv Detail & Related papers (2021-09-30T10:19:22Z) - TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset [50.8779574716494]
Event cameras are bio-inspired vision sensors which measure per pixel brightness changes.
They offer numerous benefits over traditional, frame-based cameras, including low latency, high dynamic range, high temporal resolution and low power consumption.
To foster the development of 3D perception and navigation algorithms with event cameras, we present the TUM-VIE dataset.
arXiv Detail & Related papers (2021-08-16T19:53:56Z) - VisEvent: Reliable Object Tracking via Collaboration of Frame and Event
Flows [93.54888104118822]
We propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task.
Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios.
Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods.
arXiv Detail & Related papers (2021-08-11T03:55:12Z) - Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation [93.22300146395536]
We design a computational architecture that discovers camouflaged objects in videos, specifically by exploiting motion information to perform object segmentation.
We collect the first large-scale Moving Camouflaged Animals (MoCA) video dataset, which consists of over 140 clips across a diverse range of animals.
We demonstrate the effectiveness of the proposed model on MoCA, and achieve competitive performance on the unsupervised segmentation protocol on DAVIS2016 by only relying on motion.
arXiv Detail & Related papers (2020-11-23T18:59:08Z) - A Multi-spectral Dataset for Evaluating Motion Estimation Systems [7.953825491774407]
This paper presents a novel dataset for evaluating the performance of multi-spectral motion estimation systems.
All the sequences are recorded from a handheld multi-spectral device.
The depth images are captured by a Microsoft Kinect2 and can have benefits for learning cross-modalities stereo matching.
arXiv Detail & Related papers (2020-07-01T17:11:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.