SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects

Abstract

Object detection has been a building block in computer vision. Though considerable progress has been made, there still exist challenges for objects with small size, arbitrary direction, and dense distribution. Apart from natural images, such issues are especially pronounced for aerial images of great importance. This paper presents a novel multi-category rotation detector for small, cluttered and rotated objects, namely SCRDet. Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects. Meanwhile, the supervised pixel attention network and the channel attention network are jointly explored for small and cluttered object detection by suppressing the noise and highlighting the objects feature. For more accurate rotation estimation, the IoU constant factor is added to the smooth L1 loss to address the boundary problem for the rotating bounding box. Extensive experiments on two remote sensing public datasets DOTA, NWPU VHR-10 as well as natural image datasets COCO, VOC2007 and scene text data ICDAR2015 show the state-of-the-art performance of our detector. The code and models will be available at https://github.com/DetectionTeamUCAS.

10 pages, 10 figures, 6 tables, ICCV2019

References in corpus (14)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• DSSD : Deconvolutional Single Shot 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
• Deformable Convolutional Networks
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
• Learning a Rotation Invariant Detector with Rotatable Bounding Box
• Non-local Neural Networks
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• PixelLink: Detecting Scene Text via Instance Segmentation
• Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery

Cited by in corpus (10)

• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection
• FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
• RarePlanes: Synthetic Data Takes Flight
• LUAI Challenge 2021 on Learning to Understand Aerial Images