Details
| Original language | English |
|---|---|
| Pages (from-to) | 381-388 |
| Number of pages | 8 |
| Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Volume | 5 |
| Issue number | 2 |
| Publication status | Published - 3 Aug 2020 |
| Event | 2020 24th ISPRS Congress on Technical Commission II - Nice, Virtual, France Duration: 31 Aug 2020 → 2 Sept 2020 |
Abstract
State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using interpolation to align RoI features can result in a lack of accuracy or even loss of location information. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery. We enhance translation invariance to detect dense vehicles and address the boundary quantization issue amongst dense vehicles by aggregating the high-precision RoIs' features. Moreover, we resample high-level semantic pooled features, making them regain location information from the features of a shallower convolutional block. This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation. The local feature invariance enhances the learning ability of the focal loss function, and the focal loss further helps to focus on the hard examples. Taken together, our method better addresses the challenges of aerial imagery. We evaluate our approach on several challenging datasets (VEDAI, DOTA), demonstrating a significant improvement over state-of-the-art methods. We demonstrate the good generalization ability of our approach on the DLR 3K dataset.
Keywords
- Deep Learning, Feature Enhancement, Object Detection, Twin Region Proposal, Vehicle Detection
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Physics and Astronomy(all)
- Instrumentation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 5, No. 2, 03.08.2020, p. 381-388.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - LR-CNN
T2 - 2020 24th ISPRS Congress on Technical Commission II
AU - Liao, Liao
AU - Chen, Xiang
AU - Yang, Jingfeng
AU - Roth, Stefan
AU - Goesele, Michael
AU - Yang, Michael Ying
AU - Rosenhahn, Bodo
N1 - Funding information: This work was supported by German Research Foundation (DFG) grants COVMAP (RO 2497/12-2) and PhoenixD (EXC 2122, Project ID 390833453).
PY - 2020/8/3
Y1 - 2020/8/3
N2 - State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using interpolation to align RoI features can result in a lack of accuracy or even loss of location information. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery. We enhance translation invariance to detect dense vehicles and address the boundary quantization issue amongst dense vehicles by aggregating the high-precision RoIs' features. Moreover, we resample high-level semantic pooled features, making them regain location information from the features of a shallower convolutional block. This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation. The local feature invariance enhances the learning ability of the focal loss function, and the focal loss further helps to focus on the hard examples. Taken together, our method better addresses the challenges of aerial imagery. We evaluate our approach on several challenging datasets (VEDAI, DOTA), demonstrating a significant improvement over state-of-the-art methods. We demonstrate the good generalization ability of our approach on the DLR 3K dataset.
AB - State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using interpolation to align RoI features can result in a lack of accuracy or even loss of location information. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery. We enhance translation invariance to detect dense vehicles and address the boundary quantization issue amongst dense vehicles by aggregating the high-precision RoIs' features. Moreover, we resample high-level semantic pooled features, making them regain location information from the features of a shallower convolutional block. This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation. The local feature invariance enhances the learning ability of the focal loss function, and the focal loss further helps to focus on the hard examples. Taken together, our method better addresses the challenges of aerial imagery. We evaluate our approach on several challenging datasets (VEDAI, DOTA), demonstrating a significant improvement over state-of-the-art methods. We demonstrate the good generalization ability of our approach on the DLR 3K dataset.
KW - Deep Learning
KW - Feature Enhancement
KW - Object Detection
KW - Twin Region Proposal
KW - Vehicle Detection
UR - http://www.scopus.com/inward/record.url?scp=85091068652&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-V-2-2020-381-2020
DO - 10.5194/isprs-annals-V-2-2020-381-2020
M3 - Conference article
AN - SCOPUS:85091068652
VL - 5
SP - 381
EP - 388
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 - 2
Y2 - 31 August 2020 through 2 September 2020
ER -