IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection

Abstract

Object detection in aerial images is a challenging task due to the lack of visible features and variant orientation of objects. Significant progress has been made recently for predicting targets from aerial images with horizontal bounding boxes (HBBs) and oriented bounding boxes (OBBs) using two-stage detectors with region based convolutional neural networks (R-CNN), involving object localization in one stage and object classification in the other. However, the computational complexity in two-stage detectors is often high, especially for orientational object detection, due to anchor matching and using regions of interest (RoI) pooling for feature extraction. In this paper, we propose a one-stage anchor free detector for orientational object detection, namely, an interactive embranchment network (IENet), which is built upon a detector with prediction in per-pixel fashion. First, a novel geometric transformation is employed to better represent the oriented object in angle prediction, then a branch interactive module with a self-attention mechanism is developed to fuse features from classification and box regression branches. Finally, we introduce an enhanced intersection over union (IoU) loss for OBB detection, which is computationally more efficient than regular polygon IoU. Experiments conducted demonstrate the effectiveness and the superiority of our proposed method, as compared with state-of-the-art detectors.

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Self-Attention Generative Adversarial Networks
• 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
• Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• Interlaced Sparse Self-Attention for Semantic Segmentation

Cited by in corpus (8)

• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images
• EARL: An Elliptical Distribution aided Adaptive Rotation Label Assignment for Oriented Object Detection in Remote Sensing Images
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
• FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection
• OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection