Research on Bidirectional Attenuation Loss Method for Rotating Object Detection in Remote Sensing Image

被引：0
|
作者：
Zhang Z. [1 ]
Ma Y. [1 ]
Liu C. [1 ]
Tian Q. [1 ]
机构：
[1] School of Information Science and Technology, North China University of Technology, Beijing
来源：
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | 2023年 / 45卷 / 10期
关键词：
Deep neural network; Loss function; Object detection; Remote sensing image;
D O I：
10.11999/JEIT220991
中图分类号：
学科分类号：
摘要：
Object detection in remote sensing image is one of the hot research topics in the field of remote sensing. In order to adapt to complex backgrounds and multi-directional objects in remote sensing images, the mainstream object detection model uses rotation detection method. However, most of positioning losses used for rotation detection generally has the problem that its trend is inconsistent with the trend of SkewIoU(Skew Intersection-over-Union). To solve this problem, a new bidirectional attenuation loss for rotating object detection is designed. Specifically, this method simulates SkewIoU by Gaussian product, and attenuates the product from two directions according to the deviation of the predicted position. The bidirectional attenuation loss has stronger trend-level alignment with SkewIoU and works better compared with other methods, thanks to its ability to reflect the SkewIoU change caused by position deviation. Experiments on DOTAv1.0 show the effectiveness of this method of various loss forms and different accuracy conditions. © 2023 Science Press. All rights reserved.
引用
收藏
页码：3578 / 3586
页数：8
相关论文
共 23 条
  • [1] Xiaobo LI, SUN Wenfang, LI Li, Ocean moving ship detection method for remote sensing satellite in geostationary orbit[J], Journal of Electronics & Information Technology, 37, 8, pp. 1862-1867, (2015)
  • [2] CHEN Qi, LU Jun, ZHAO Lingjun, Et al., Harbor detection method of SAR remote sensing images based on feature[J], Journal of Electronics & Information Technology, 32, 12, pp. 2873-2878, (2010)
  • [3] LI Xuan, LIU Yunqing, Oil tank detection in optical remote sensing imagery based on quasi-circular shadow[J], Journal of Electronics & Information Technology, 38, 6, pp. 1489-1495, (2016)
  • [4] ZHANG Zheng, MIAO Chunle, LIU Chang'an, Et al., DCSTransUperNet: Road segmentation network based on CSwin transformer with dual resolution, Applied Sciences, 12, 7, (2022)
  • [5] ZHANG Zheng, XU Zhiwei, LIU Chang'an, Et al., Cloudformer: Supplementary aggregation feature and mask-classification network for cloud detection, Applied Sciences, 12, 7, (2022)
  • [6] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation[C], 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [7] GIRSHICK R., Fast R-CNN[C], 2015 IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [8] REN Shaoqing, HE Kaiming, GIRSHICK R, Et al., Faster RCNN: Towards real-time object detection with region proposal networks[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [9] REDMON J, FARHADI A., YOLOv3: An incremental improvement, (2018)
  • [10] BOCHKOVSKIY A, WANG C Y, LIAO H Y M., YOLOv4: Optimal speed and accuracy of object detection[J], (2020)
123