TY - GEN
T1 - MULTI-SCALE BIDIRECTIONAL FEATURE FUSION FOR ONE-STAGE ORIENTED OBJECT DETECTION IN AERIAL IMAGES
AU - Pei, Lei
AU - Cheng, Gong
AU - Sun, Xuxiang
AU - Li, Qingyang
AU - Zhang, Meili
AU - Miao, Shicheng
N1 - Publisher Copyright:
© 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
PY - 2021
Y1 - 2021
N2 - This paper aims to address the problem of oriented object detection under the complex background of remote sensing images. To this end, we propose a one-stage object detection method with feature fusion structure, and modify the loss function to enhance the detection of small objects. More specifically, on the basis of the end-to-end one-stage object detection model RetinaNet, the method of gliding the vertices of the horizontal bounding box is used to describe an oriented object. In order to obtain multi-scale context information, we design a feature fusion module. Besides, we propose a novel area-weighted loss function to pay more attention to small objects. Experimental results conducted on the DOTA dataset demonstrate that the proposed framework outperforms several state-of-the-art baselines.
AB - This paper aims to address the problem of oriented object detection under the complex background of remote sensing images. To this end, we propose a one-stage object detection method with feature fusion structure, and modify the loss function to enhance the detection of small objects. More specifically, on the basis of the end-to-end one-stage object detection model RetinaNet, the method of gliding the vertices of the horizontal bounding box is used to describe an oriented object. In order to obtain multi-scale context information, we design a feature fusion module. Besides, we propose a novel area-weighted loss function to pay more attention to small objects. Experimental results conducted on the DOTA dataset demonstrate that the proposed framework outperforms several state-of-the-art baselines.
KW - Deep Learning
KW - Feature Fusion
KW - Oriented Object Detection
KW - Remote Sensing Images
UR - https://www.scopus.com/pages/publications/85124642053
U2 - 10.1109/IGARSS47720.2021.9555142
DO - 10.1109/IGARSS47720.2021.9555142
M3 - 会议稿件
AN - SCOPUS:85124642053
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 2592
EP - 2595
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -