Abstract
Object detection has always been a challenging task in the field of computer vision due to complex background, large scale variation and many small objects, which are especially pronounced for remote sensing imagery. In recent years, object detection in remote sensing with the development of deep learning has also made great breakthroughs. At present, almost all state-of-the-art object detectors rely on pre-defined anchor boxes for remote sensing imagery. However, too many anchor boxes will introduce a large number of hyper-parameters, which not only increase the memory footprint, but also increase the computational redundancy of the detection model. In contrast, we propose an anchor-free single-stage detector for remote sensing imagery object detection, avoiding a large number of hyper-parameters related to the anchor box, which usually affect the performance of the detection model. Specially, considering the large-scale differences in the objects and the characteristics of small objects in remote sensing imagery, we design a dense path aggregation feature pyramid network (DPAFPN), which can make full use of the high-level semantic information and low-level location information in remote sensing imagery, and to a certain extent, avoid information loss during shallow feature transfer. In our experiments, extensive experiments on two public remote sensing datasets DOTA, NWPU VHR-10 were conducted. The experimental results demonstrate that our detector has good performance and is meaningful for object detection in remote sensing imagery.
Original language | English |
---|---|
Article number | 9051994 |
Pages (from-to) | 63121-63133 |
Number of pages | 13 |
Journal | IEEE Access |
Volume | 8 |
DOIs | |
Publication status | Published - 2020 |
Bibliographical note
Funding Information:This work was supported in part by the National Natural Science Foundation of China under Grant 61772399, Grant U1701267, Grant 61773304, Grant 61672405, and Grant 61772400, in part by the Key Research and Development Program in Shaanxi Province of China under Grant 2019ZDLGY09-05, in part by the Program for Cheung Kong Scholars and Innovative Research Team in University under Grant IRT_15R53, and in part by the Technology Foundation for Selected Overseas Chinese Scholar in Shaanxi under Grant 2017021 and Grant 2018021.
Publisher Copyright:
© 2013 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
Keywords
- anchor-free
- deep learning
- object detection
- Remote sensing
ASJC Scopus subject areas
- Computer Science(all)
- Materials Science(all)
- Engineering(all)