output
20022026
most citedThe 2014 KIDA network for interstellar chemistry

399 citations

Showing 2020 · cs.CVShow all

5 papers · 2 filters

cs.CV2020★ 9 cited

Graph-based non-linear least squares optimization for visual place recognition in changing environments

Stefan Schubert, Peer Neubert, Peter Protzel

Visual place recognition is an important subproblem of mobile robot localization. Since it is a special case of image retrieval, the basic source of information is the pairwise sim…

cs.CV2020★ 8 cited

Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection

Tobias Scheck, Ana Perez Grassi, Gangolf Hirtz

Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN).…

cs.CV2020★ 6 cited

Where to drive: free space detection with one fisheye camera

Tobias Scheck, Adarsh Mallandur, Christian Wiede +1

The development in the field of autonomous driving goes hand in hand with ever new developments in the field of image processing and machine learning methods. In order to fully exp…

cs.CV2020★ 1 cited

A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications

Tobias Scheck, Ana Perez Grassi, Gangolf Hirtz

A Convolutional Neural Network (CNN) is sometimes confronted with objects of changing appearance ( new instances) that exceed its generalization capability. This requires the CNN t…

cs.CV2020★ 26 cited

Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning

Tobias Scheck, Roman Seidel, Gangolf Hirtz

Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this…