Details
Original language | English |
---|---|
Pages (from-to) | 15-23 |
Number of pages | 9 |
Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Volume | 5 |
Issue number | 1 |
Publication status | Published - 17 May 2022 |
Event | 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission I - Nice, France Duration: 6 Jun 2022 → 11 Jun 2022 |
Abstract
Vehicle instance segmentation is a major but challenging task in aerial remote sensing applications. More importantly, the current majority methods use horizontal bounding boxes which does not tell much about the orientation of vehicles and often leads to inaccurate mask proposals due to high background to foreground pixel-ratio. Given that the orientation of vehicles is important for numerous applications like vehicle tracking, we introduce in this paper a deep neural network to detect and segment vehicles using rotated bounding boxes in aerial images. Our method demonstrates that rotated instance segmentation improves the mask predictions, especially when objects are not axis aligned or are touching. We evaluate our model on the ISPRS benchmark dataset and our newly introduced UAV dataset for vehicle segmentation and show that we can significantly improve the mask accuracy compared to instance segmentation using axis-aligned bounding boxes.
Keywords
- Deep Learning, Instance Segmentation, Mask RCNN, Remote Sensing, Vehicle Detection
ASJC Scopus subject areas
- Physics and Astronomy(all)
- Instrumentation
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 5, No. 1, 17.05.2022, p. 15-23.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - VEHICLE INSTANCE SEGMENTATION WITH ROTATED BOUNDING BOXES IN UAV IMAGES USING CNN
AU - El Amrani Abouelassad, S.
AU - Rottensteiner, F.
N1 - Funding Information: This work was supported by the German Research Foundation (DFG) as a part of the Research Training Group i.c.sens [GRK2159].
PY - 2022/5/17
Y1 - 2022/5/17
N2 - Vehicle instance segmentation is a major but challenging task in aerial remote sensing applications. More importantly, the current majority methods use horizontal bounding boxes which does not tell much about the orientation of vehicles and often leads to inaccurate mask proposals due to high background to foreground pixel-ratio. Given that the orientation of vehicles is important for numerous applications like vehicle tracking, we introduce in this paper a deep neural network to detect and segment vehicles using rotated bounding boxes in aerial images. Our method demonstrates that rotated instance segmentation improves the mask predictions, especially when objects are not axis aligned or are touching. We evaluate our model on the ISPRS benchmark dataset and our newly introduced UAV dataset for vehicle segmentation and show that we can significantly improve the mask accuracy compared to instance segmentation using axis-aligned bounding boxes.
AB - Vehicle instance segmentation is a major but challenging task in aerial remote sensing applications. More importantly, the current majority methods use horizontal bounding boxes which does not tell much about the orientation of vehicles and often leads to inaccurate mask proposals due to high background to foreground pixel-ratio. Given that the orientation of vehicles is important for numerous applications like vehicle tracking, we introduce in this paper a deep neural network to detect and segment vehicles using rotated bounding boxes in aerial images. Our method demonstrates that rotated instance segmentation improves the mask predictions, especially when objects are not axis aligned or are touching. We evaluate our model on the ISPRS benchmark dataset and our newly introduced UAV dataset for vehicle segmentation and show that we can significantly improve the mask accuracy compared to instance segmentation using axis-aligned bounding boxes.
KW - Deep Learning
KW - Instance Segmentation
KW - Mask RCNN
KW - Remote Sensing
KW - Vehicle Detection
UR - http://www.scopus.com/inward/record.url?scp=85132795615&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-V-1-2022-15-2022
DO - 10.5194/isprs-annals-V-1-2022-15-2022
M3 - Conference article
AN - SCOPUS:85132795615
VL - 5
SP - 15
EP - 23
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 1
T2 - 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission I
Y2 - 6 June 2022 through 11 June 2022
ER -