TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Himmelsbach, Urban
A1  - Süme, Sinan
A1  - Wendt, Thomas
T1  - Classification of Thermal Images for Human-Machine Differentiation in Human-Robot Collaboration Using Convolutional Neural Networks
T2  - 2023 20th International Conference on Ubiquitous Robots (UR)
N2  - Differentiation between human and non-human objects can increase efficiency of human-robot collaborative applications. This paper proposes to use convolutional neural networks for classifying objects in robotic applications. The body temperature of human beings is used to classify humans and to estimate the distance to the sensor. Using image classification with convolutional neural networks it is possible to detect humans in the surroundings of a robot up to five meters distance with low-cost and low-weight thermal cameras. Using transfer learning technique we trained the GoogLeNet and MobilenetV2. Results show accuracies of 99.48 % and 99.06 % respectively.
KW  - Temperature sensors
KW  - Meters
KW  - Transfer learning
KW  - Robot vision systems
KW  - Collaboration
KW  - Cameras
KW  - Convolutional neural networks
Y1  - 2023
SN  - 979-8-3503-3517-0 (Elektronisch)
SB  - 979-8-3503-3517-0 (Elektronisch)
SN  - 979-8-3503-3518-7 (Print on Demand)
SB  - 979-8-3503-3518-7 (Print on Demand)
U6  - https://doi.org/10.1109/UR57808.2023.10202384
DO  - https://doi.org/10.1109/UR57808.2023.10202384
SP  - 730
EP  - 734
PB  - IEEE
ER  -