Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 60, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2021.3113473
Keywords
Detectors; Task analysis; Object detection; Proposals; Location awareness; Head; Feature extraction; Aerial images; multihead; oriented object detection; rotated proposals
Categories
Funding
- National Natural Science Foundation of China [62022011, 62176017, 41871283]
Ask authors/readers for more resources
The article proposes an AO-RPN for generating oriented proposals and introduces the MRDet multihead rotated object detector for accurately detecting objects by decoupling the detection task into multiple subtasks. The proposed methods show very promising results in challenging benchmarks, demonstrating their effectiveness in object detection.
Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected. Many of the recent developed methods attempt to solve these issues by estimating an extra orientation parameter and placing dense anchors, which will result in high model complexity and computational costs. In this article, we propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors. The AO-RPN is very efficient with only a few amounts of parameters increase than the original RPN. Furthermore, to obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multihead network to accomplish them. Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately. We name it multihead rotated object detector (MRDet). We evaluate the performance of the proposed MRDet on two challenging benchmarks, i.e., DOTA and HRSC2016, and compare it with several state-of-the-art methods. Our method achieves very promising results, which clearly demonstrates its effectiveness. Code has been available at https://github.com/qinr/MRDet.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available