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

TL;DR

This paper introduces IENet, a novel one-stage anchor-free neural network for efficient and accurate orientation aerial object detection, utilizing a geometric transformation, feature fusion, and an improved IoU loss.

Contribution

The paper proposes a new one-stage anchor-free detector with a geometric angle representation, feature fusion via self-attention, and an efficient IoU loss for oriented object detection.

Findings

Outperforms state-of-the-art detectors in accuracy

Reduces computational complexity for orientation detection

Demonstrates effectiveness on aerial image datasets

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.