극한 환경 회전 검출 네트워크 = Extreme Environment Rotated Object Detection Network

다국어 초록 (Multilingual Abstract)

With the advancement of object detection models, it is possible to efficiently infer synthetic aperture radar (SAR) and electro-optical (EO) satellite images. However, conventional object detection models using horizontal bounding boxes (HBB) struggle to detect small and densely grouped objects in satellite images. To address this issue, this paper proposes E^2RDet. This algorithm effectively modifies the structure of the Yolov7 object detection model, enabling it to accurately detect objects represented by oriented bounding boxes (OBB) in SAR images. This algorithm improves the object detection model architecture and loss function to facilitate learning of an object's dynamic (orientation) posture. Using various training datasets, E^2RDet demonstrates performance improvements across three benchmark SAR datasets. This indicates that existing HBB object detection models can train and perform object detection on objects represented by OBBs.

참고문헌 (Reference)

1 Glenn Jocher, "ultralytics/yolov5:v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations"

2 Joseph Redmon, "You only look once:Unified, real-time object detection" CoRR 2015

3 Chien-Yao Wang, "Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"

4 Chien-Yao Wang, "Yolov7 Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"

5 Chuyi Li, "Yolov6: A single-stage object detection framework for industrial applications"

6 Alexey Bochkovskiy, "Yolov4: Optimal speed and accuracy of object detection" 2020

7 Joseph Redmon, "Yolov3: An incremental improvement" 2018

8 Joseph Redmon, "YOLO9000: better, faster, stronger" 2016

9 Tianwen Zhang, "Sar ship detection dataset (ssdd): Official release and comprehensive data analysis" 13 (13): 2021

10 XU Congan, "Rsdd-sar: Rotated ship detection dataset in sar images"

11 Jingru Yi, "Oriented object detection in aerial images with box boundary-aware vectors" CoRR 2020

12 Jian Ding, "Learning roi transformer for detecting oriented objects in aerial images" 2019

13 Christian Szegedy, "Going deeper with convolutions" 1-9, 2015

14 Tsung-Yi Lin, "Feature pyramid networks for object detection" 936-944, 2017

15 Xue Yang, "Computer Vision –ECCV 2020" Springer International Publishing 677-694, 2020

16 Shunjun Wei, "A high resolution sar images dataset for ship detection and in stance segmentation" 8 : 120234-120254, 2020

17 Zikun Liu, "A high resolution optical satellite image dataset for ship recognition and some new baselines" Science and Technology Publications 2017