Learning Rotated Inscribed Ellipse for Oriented Object Detection in Remote Sensing Images

Oriented object detection in remote sensing images (RSIs) is a significant yet challenging Earth Vision task, as the objects in RSIs usually emerge with complicated backgrounds, arbitrary orientations, multi-scale distributions, and dramatic aspect ratio variations. Existing oriented object detectors are mostly inherited from the anchor-based paradigm. However, the prominent performance of high-precision and real-time detection with anchor-based detectors is overshadowed by the design limitations of tediously rotated anchors. By using the simplicity and efficiency of keypoint-based detection, in this work, we extend a keypoint-based detector to the task of oriented object detection in RSIs. Specifically, we first simplify the oriented bounding box (OBB) as a center-based rotated inscribed ellipse (RIE), and then employ six parameters to represent the RIE inside each OBB: the center point position of the RIE, the offsets of the long half axis, the length of the short half axis, and an orientation label. In addition, to resolve the influence of complex backgrounds and large-scale variations, a high-resolution gated aggregation network (HRGANet) is designed to identify the targets of interest from complex backgrounds and fuse multi-scale features by using a gated aggregation model (GAM). Furthermore, by analyzing the influence of eccentricity on orientation error, eccentricity-wise orientation loss (ewoLoss) is proposed to assign the penalties on the orientation loss based on the eccentricity of the RIE, which effectively improves the accuracy of the detection of oriented objects with a large aspect ratio. Extensive experimental results on the DOTA and HRSC2016 datasets demonstrate the effectiveness of the proposed method.

[1]  Zhifeng Xiao,et al.  Axis Learning for Orientated Objects Detection in Aerial Images , 2020, Remote. Sens..

[2]  Courage Kamusoko,et al.  Importance of Remote Sensing and Land Change Modeling for Urbanization Studies , 2017 .

[3]  Yi Yang,et al.  DenseBox: Unifying Landmark Localization with End to End Object Detection , 2015, ArXiv.

[4]  Jian Guan,et al.  IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection , 2019, ArXiv.

[5]  Wei Li,et al.  R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection , 2017, ArXiv.

[6]  Michael Riegler,et al.  Social media and satellites , 2019, Multimedia Tools and Applications.

[7]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[8]  Junchi Yan,et al.  R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object , 2019, AAAI.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Menglong Yan,et al.  Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks , 2018, Remote. Sens..

[11]  Lin Lei,et al.  Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining , 2017, Sensors.

[12]  Hao Li,et al.  Oriented Objects as pairs of Middle Lines , 2019, ArXiv.

[13]  F. Foglini,et al.  New evidence of a Roman road in the Venice Lagoon (Italy) based on high resolution seafloor reconstruction , 2021, Scientific Reports.