TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Griesser, Dennis
A1  - Dold, Daniel
A1  - Umlauf, Georg
A1  - Franz, Matthias O.
T1  - CNN-Based Monocular 3D Ship Detection Using Inverse Perspective
T2  - Global Oceans 2020, Oceans Conference and Exposition, October 5th - 30th 2020, virtual
N2  - Three-dimensional ship localization with only one camera is a challenging task due to the loss of depth information caused by perspective projection. In this paper, we propose a method to measure distances based on the assumption that ships lie on a flat surface. This assumption allows to recover depth from a single image using the principle of inverse perspective. For the 3D ship detection task, we use a hybrid approach that combines image detection with a convolutional neural network, camera geometry and inverse perspective. Furthermore, a novel calculation of object height is introduced. Experiments show that the monocular distance computation works well in comparison to a Velodyne lidar. Due to its robustness, this could be an easy-to-use baseline method for detection tasks in navigation systems.
KW  - Inverse perspective
KW  - Mask R-CNN
KW  - 3D ship detection
KW  - Ship dataset
Y1  - 2020
SN  - 978-1-7281-8409-8
SB  - 978-1-7281-8409-8
SN  - 978-1-7281-5446-6
SB  - 978-1-7281-5446-6
U6  - https://doi.org/10.1109/IEEECONF38699.2020.9389028
DO  - https://doi.org/10.1109/IEEECONF38699.2020.9389028
SP  - 8
S1  - 8
PB  - IEEE
ER  -