LR-CNN: Local-aware region cnn for vehicle detection in aerial imagery

Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

6 Citations (Scopus)
66 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Subtitle of host publicationXXIV ISPRS Congress
EditorsN. Paparoditis, C. Mallet, F. Lafarge, F. Remondino, I. Toschi, T. Fuse
Place of PublicationNice
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Number of pages8
Publication statusPublished - 3 Aug 2020
EventXXIVth ISPRS Congress 2020 - Virtual Event, Nice, France
Duration: 4 Jul 202010 Jul 2020
Conference number: 24

Publication series

NameISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
ISSN (Print)2194-9042


ConferenceXXIVth ISPRS Congress 2020
Abbreviated titleISPRS 2020
Internet address


Dive into the research topics of 'LR-CNN: Local-aware region cnn for vehicle detection in aerial imagery'. Together they form a unique fingerprint.

Cite this