Intelligent Systems Research Group
SLAM with Plenoptic Cameras
Research and industry proceed to build autonomous driving cars, self-navigating unmanned aerial vehicles and intelligent, mobile robots. For these tasks, systems are needed which reliably map the 3D surroundings and are able to self-localize in these created maps. Such systems or methods can be summarized under the terms Simultaneous Localization And Mapping (SLAM).
On the other hand, during the last decade plenoptic cameras (or light field cameras) have become available as commercial products. This technology opens up a large variety of possible applications. Particularly when classical stereo camera systems require too much space.
To the best of our knowledge, we developed the first SLAM algorithm that performs tracking and mapping for plenoptic cameras directly on the recorded micro images. A detailed description of the method and quanitative results are given in our ECCV 2018 paper.
Externer Inhalt
Um diesen Inhalt zu verwenden (Quelle: www.xyz.de), klicken Sie bitte auf Akzeptieren. Wir möchten Sie darauf hinweisen, dass durch die Annahme dieser IFrames Daten an Dritte übertragen oder Cookies gespeichert werden könnten.
Weitere Informationen finden Sie in unserer Datenschutzerklärung.
Visual Odometrie Dataset
We present a Visual Odometrie Dataset (VOD) for the evaluation and comparison of plenoptic, monocular and stereo camera based visual odometry and SLAM algorithms. The dataset contains 11 sequences recorded by a hand-held platform consisting of a plenoptic camera and a pair of stereo cameras. The sequences are comprising different indoor and outdoor sequences with trajectory length ranging from 25 meters up to several hundred meters. The recorded sequences show moving objects as well as changing lighting conditions.
Related Data & Publications
Zeller N., Quint F., Stilla U.
Scale-Awareness of Light Field Camera based Visual Odometry
Computer Vision - ECCV 2018, Springer Lecture Notes in Computer Science LNCS 11212, p. 732-747, 2018. [pdf]
Zeller N., Quint F., Stilla U.
A Synchronized Stereo and Plenoptic Visual Odometry Dataset
arXiv:1807.09372, 2018. VOD
Ziebarth M., Zeller N., Heizmann M., Quint F.
Modeling the unified measurement uncertainty of deflectometric and plenoptic 3-D sensors
Journal of Sensors and Sensor Systems, 7, pp 517-533, 2018. [pdf]
Zeller N., Quint F., Stilla U.
From the Calibration of a Light-Field Camera to Direct Plenoptic Odometry
IEEE Journal of Selected Topics in Signal Processing, Vol. 11, Nr. 7, p. 1004-1019, 2017.