R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object

Abstract

Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through pixel-wise feature interpolation to realize feature reconstruction and alignment. For more accurate rotation estimation, an approximate SkewIoU loss is proposed to solve the problem that the calculation of SkewIoU is not derivable. Experiments on three popular remote sensing public datasets DOTA, HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show the effectiveness of our approach. Tensorflow and Pytorch version codes are available at https://github.com/Thinklab-SJTU/R3Det_Tensorflow and https://github.com/SJTU-Thinklab-Det/r3det-on-mmdetection, and R3Det is also integrated in our open source rotation detection benchmark: https://github.com/yangxue0827/RotationDetection.

arXiv comment13 pages, 12 figures, 9 tables

References in corpus (18)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Deformable Convolutional Networks
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• Hybrid Task Cascade for Instance Segmentation
• Learning a Rotation Invariant Detector with Rotatable Bounding Box
• SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• Objects detection for remote sensing images based on polar coordinates
• Rethinking Classification and Localization for Cascade R-CNN
• Propose-and-Attend Single Shot Detector

Cited by in corpus (13)

• Anchor-free Oriented Proposal Generator for Object Detection
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
• Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• Arbitrary-Oriented Ship Detection through Center-Head Point Extraction
• Learning Modulated Loss for Rotated Object Detection
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
• PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
• FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection
• ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera
• Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images