FAR-Net: Fast Anchor Refining for Arbitrary-Oriented Object Detection

Chenwei Deng

doi:10.1109/LGRS.2022.3144513

2022-01-01

PRE

DOI：10.1109/LGRS.2022.3144513

原文链接

原文求助

摘要

En 中文

Compared with natural images, targets in remote-sensing images are often distributed with more flexible orientation, aspect ratio, and scale. Thus, anchor-based algorithms often employ plenty of preset anchors to encode the above-mentioned attributes in object detection tasks. However, they often suffer from the following issues: 1) significant computational burden caused by dense-sampling anchors; 2) serious background interference since many anchors only cover small parts of the actual target; and 3) feature misalignment between the targets with the preset anchors due to the absence of the most discriminant features for target extraction. Therefore, in this letter, a fast anchor refining network (FAR-Net) is advocated to address the remaining issues for arbitrary-oriented object detection in the remote-sensing field. To be specific, a rotation alignment module (RAM) and balanced regression loss function (BR-loss) are carefully designed in the FAR-Net. The RAM is capable of generating high-quality anchors based on a refinement convolution and adaptively aligning the convolutional features by complying with the anchor boxes to reduce redundant calculation. The BR-loss is designed by employing a balanced loss function to prevent misaligned anchors from causing major gradient descents, thereby achieving a more stable network training procedure. Extensive experiments on public remote-sensing datasets (HRSC2016 and UCAS-AOD) demonstrate the excellent detection performance of our algorithm in comparison with numerous existing detectors.

Keyword:

Remote sensing

Random access memory

Training

Object detection

Feature extraction

Task analysis

Sensors

Convolutional neural network (CNN)

oriented object detection

remote-sensing images

rotation alignment

期刊

IEEE Geoscience and Remote Sensing Magazine

IF:

16.4

论文数:

1.0W

被引数:

5.1K

机构

tsinghua university

学者数:

11.9W

论文数: 10.0W

被引数: 137

beijing institute of technology

学者数:

5.5W

论文数: 4.0W

被引数: 63

引用论文

Blastococcus capsensis sp. nov., isolated from an archaeological Roman pool and emended description of the genus Blastococcus, B. aggregatus, B. saxobsidens, B. jejuensis and B. endophyticus

International Journal of Systematic and Evolutionary Microbiology

IF0

2016-11-01

OAAI

Karima Hezbri; Moussa Louati; Imen Nouioui; Maher Gtari; Manfred Rohde; Cathrin Spröer; Peter Schumann; Hans-Peter Klenk; Faten Ghodhbane-Gtari; Maria del Carmen Montero-Calasanz

Align Deep Features for Oriented Object Detection 对齐面向对象检测的深度特征

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

IF8.6

2022-01-01

492