Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu

Links

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group


Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
research:vslam:omni-lsdslam [2015/09/21 21:58]
engelj
research:vslam:omni-lsdslam [2015/09/21 22:10] (current)
engelj
Line 1: Line 1:
- +~~REDIRECT>​data:datasets:omni-lsdslam~~
-====== Large-Scale Direct SLAM for Omnidirectional Cameras ====== +
- +
-We propose a real-time, direct monocular SLAM +
-method for omnidirectional or wide field-of-view fisheye cam- +
-eras. Both tracking (direct image alignment) and mapping +
-(pixel-wise distance filtering) are directly formulated for the +
-unified omnidirectional model, which can model central imaging +
-devices with a field of view well above 150◦ . This is in stark +
-contrast to existing direct mono-SLAM approaches like DTAM +
-or LSD-SLAM, which operate on rectified images, limiting +
-the field of view to well below 180◦ . Not only does this +
-allow to observe – and reconstruct – a larger portion of the +
-surrounding environment,​ but it also makes the system more +
-robust to degenerate (rotation-only) movement. The two main +
-contribution are (1) the formulation of direct image alignment +
-for the unified omnidirectional model, and (2) a fast yet accurate +
-approach to incremental stereo directly on distorted images. We +
-evaluated our framework on real-world sequences taken with a +
-185◦ fish-eye lens, and compare it to a rectified and a piecewise +
-rectified approach. +
- +
-====== Video ====== +
- +
-<​html><​center><​iframe width="​640"​ height="​360"​ src="//​www.youtube.com/​embed/​v0NqMm7Q6S8"​ frameborder="​0"​ allowfullscreen></​iframe></​center></​html>​ +
- +
- +
-====== Dataset ====== +
- +
-  * ** T1 (2:40min @ 50fps)**  +
-    * Video Preview: ​ [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] +
-    * PNG[[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] +
-    * RosBag: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] +
-    * Calibration File: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationRect.yaml|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationOrig.yaml|[Pinhole-Rectified]]] +
- +
-  * ** T2 (1:19min @ 50fps)**  +
-    * Video Preview: ​ [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] +
-    * PNG: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] +
-    * RosBag: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] +
-    * Calibration File: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationRect.yaml|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationOrig.yaml|[Pinhole-Rectified]]] +
- +
-  * ** T3 (2:17min @ 50fps)**  +
-    * Video Preview: ​ [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] +
-    * PNG: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] +
-    * RosBag: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] +
-    * Calibration File: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationRect.yaml|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationOrig.yaml|[Pinhole-Rectified]]] +
- +
-  * ** T4 (2:08min @ 50fps)**  +
-    * Video Preview: ​ [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] +
-    * PNG: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] +
-    * RosBag: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] +
-    * Calibration File: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationRect.yaml|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationOrig.yaml|[Pinhole-Rectified]]] +
- +
-  * ** T4 (2:45min @ 50fps)**  +
-    * Video Preview: ​ [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.mp4|[Pinhole-Rectified]]] +
-    * PNG: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.tar.gz|[Pinhole-Rectified]]] +
-    * RosBag: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​T1_rectified.bag|[Pinhole-Rectified]]] +
-    * Calibration File: [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationRect.yaml|[Pinhole-Rectified]]] [[http://​vision.in.tum.de/​~engelj/​OmniDataset/​T1/​calibrationOrig.yaml|[Pinhole-Rectified]]] +
- +
-====== Related publications ====== +
-<​bibtex>​ +
-<​keywords>​semidense</​keywords>​ +
-</​bibtex>​+

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group