Learning Orientation-Aware Distances for Oriented Object Detection

Chaofan Rao, Jiabao Wang, Gong Cheng, Xingxing Xie, Junwei Han

科研成果: 期刊稿件文章同行评审

19 引用 (Scopus)

摘要

Oriented object detectors have suffered severely from the discontinuous boundary problem for a long time. In this work, we ingeniously avoid this problem by relating regression outputs to regression target orientations. The core idea of our method is to build a contour function which imports orientations and outputs the corresponding distance predictions. Inspired by Fourier transformations, we assume this function can be represented as a linear combination of trigonometric functions and Fourier series. We replace the final 4-D layer in the regression branch of fully convolutional one-stage object detector (FCOS) with a Fourier series transformation (FST) module and term this new network FCOSF. By this unique design, the regression outputs in FCOSF can adaptively vary according to the regression target orientations. Thus, the discontinuous boundary has no impact on our FCOSF. More importantly, FCOSF avoids building complicated oriented box representations, which usually cause extra computations and ambiguities. With only flipping augmentation and single-scale training and testing, FCOSF with ResNet-50 achieves 73.64% mean average precision (mAP) on the DOTA-v1.0 dataset with up to 23.6-frames/s speed, surpassing all one-stage oriented object detectors. On the more challenging DOTA-v2.0 dataset, FCOSF also achieves the highest results of 51.75% mAP among one-stage detectors. More experiments on DIOR-R and HRSC2016 are also conducted to verify the robustness of FCOSF. Code and models will be available at https://github.com/DDGRCF/FCOSF.

源语言英语
文章编号5610911
期刊IEEE Transactions on Geoscience and Remote Sensing
61
DOI
出版状态已出版 - 2023

指纹

探究 'Learning Orientation-Aware Distances for Oriented Object Detection' 的科研主题。它们共同构成独一无二的指纹。

引用此