Learning Higher Quality Rotation Invariance Features for Multioriented Object Detection in Remote Sensing Images

Abstract

Multi-oriented object detection, an important yet challenging task because of the bird's-eye-view perspective, complex background and densely packed objects, is in the spotlight of detection in remote sensing images. Although existing methods have recently experienced substantial progress based on oriented head, they learn little about essential rotation invariance of the objects. In this article, a novel framework is proposed that can learn high-quality rotation invariance features of the multi-oriented objects by three measures. Given a remote sensing image, the MSFF module first merges the global semantic segmentation features predicted by the semantic segmentation branch and the multi-scale features extracted by the backbone with FPN in order to distinguish complex background. Then the discriminative features are used by rotation mainstream, whose structure is similar to Cascade R-CNN and can extract higher-quality rotation invariance features and predict more accurate location information by adaptively adjusting the distribution of the samples through progressive IoU thresholds. And in order to improve the performance of mainstream to predict more accurate oriented bounding box, the horizontal tributaries that can fully leverage the reciprocal relationship between the oriented detection and horizontal detection were added to the latter two stages. Extensive experiments on three public datasets for remote sensing images i.e. Gaofen Airplane, HRSC2016 and DOTA demonstrate that without bells and whistles, the proposed method achieves superior performances compared with the existing state-of-the-art methods for multi-oriented detection. Moreover, our overall system achieves 59.264% mAP of airplane Detection in 2020 Gaofen challenge, ranking 3rd in the final.

Fine-Grained Object Detection in Remote Sensing Images via Adaptive Label Assignment and Refined-Balanced Feature Pyramid Network

“…CHDONet learns external and internal representations independently from the dataset using a cascaded hierarchical structure. Zhang et al [43] proposed a multi-scale semantic segmentation feature fusion module, which merges the semantic features with the original features layer by layer to distinguish the foreground from the cluttered background. R 2 IPoints [44] employs a set of category-aware points to encode spatial and semantic information oriented to arbitrary objects.…”

One-Stage Arbitrary-Oriented Object Detection With Prediction Decoupling

“…Due to the complex background and the huge variation in the orientation, scale and appearance of the object instances in remote sensing images, it is difficult to apply the horizontal detection algorithms to rotated object detection. In order to predict the location and orientation of the rotated objects in remote sensing images, some researchers utilized five parameters including center coordinates, width, height, and orientation [14], [15]. And others utilized eight parameters which are the coordinates of corners to describe the bounding box of the rotated object directly [16], [17].…”