Learning a Rotation Invariant Detector with Rotatable Bounding Box

Abstract

Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects. In this article, a new detection method is proposed which applies the newly defined rotatable bounding box (RBox). The proposed detector (DRBox) can effectively handle the situation where the orientation angles of the objects are arbitrary. The training of DRBox forces the detection networks to learn the correct orientation angle of the objects, so that the rotation invariant property can be achieved. DRBox is tested to detect vehicles, ships and airplanes on satellite images, compared with Faster R-CNN and SSD, which are chosen as the benchmark of the traditional bounding box based methods. The results shows that DRBox performs much better than traditional bounding box based methods do on the given tasks, and is more robust against rotation of input image and target objects. Besides, results show that DRBox correctly outputs the orientation angles of the objects, which is very useful for locating multi-angle objects efficiently. The code and models are available at https://github.com/liulei01/DRBox.

References in corpus (4)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Feature Pyramid Networks for Object Detection
• Oriented Response Networks

Cited by in corpus (23)

• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• Few-shot Object Detection on Remote Sensing Images
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• Learning Modulated Loss for Rotated Object Detection
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection
• PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
• Align Deep Features for Oriented Object Detection
• FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection
• Oriented Boxes for Accurate Instance Segmentation
• Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
• Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images
• A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
• Object grasping planning for the situation when soft and rigid objects are mixed together
• Real-time Human-Robot Collaborative Manipulations of Cylindrical and Cubic Objects via Geometric Primitives and Depth Information
• Weakly-Supervised Multi-Person Action Recognition in 360${}^{\circ }$ Videos
• Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks
• A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application
• OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection
• A Multi-task Learning Framework for Grasping-Position Detection and Few-Shot Classification