Aiming at the problem of large size differences in infrared small targets and poor detection results in complex scenes, an infrared small target detection method based on cascaded nested U-Net is proposed. First, in order to solve the problem of large size differences between small targets in different scenarios, three depths of U-Net networks were built, and the three U-Net networks were cascaded and nested to form a detection model; secondly, contrast was used information extraction module to further enrich feature information and suppress the interference of dense background noise; finally, the proposed algorithm is compared with five mainstream algorithms. The experimental results show that the performance of this algorithm is better than other algorithms, and the average intersection and union ratio, the precision rate and recall rate reached 78.61%, 93.36% and 81.78% respectively.
ZhaYue, TangYe. Review of infrared sea surface small target detection algorithm [J]. Journal of Astronautic Metrology and Measurement, 2022, 42(6): 57-65.
[3]
RivestJ F, FortinR. Detection of dim targets in digital infrared imagery by morphological image processing[J]. Optical Engineering, 1996, 35(7): 1886-1893.
[4]
ChenC L P, LiH, WeiY, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 52(1): 574-581.
ZhangWen-jie, XiongQing-yu. Joint segmentation of optic cup and disc based on high resolution network [J]. Journal of Jilin University (Engineering and Technology Edition), 2015, 45(5): 1709-1716.
[7]
RenS, HeK, GirshickR, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015, 28: 7485869.
[8]
RedmonJ, DivvalaS, GirshickR, et al. You only look once: unified, real-time object detection[C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 779-788.
[9]
WangH, ZhouL, WangL. Miss detection vs false alarm: adversarial learning for small object segmentation in infrared images[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), 2019: 8509-8518.
[10]
DengC, WangM, LiuL, et al. Extended feature pyramid network for small object detection[J]. IEEE Transactions on Multimedia, 2021, 24: 1968-1979.
[11]
GoodfellowI, PougetA J, MirzaM, et al. Generative adversarial nets[J]. Advances in Neural Information Processing Systems, 2014, 2: 2672-2680.
[12]
WuX, HongD, ChanussotJ. UIU-Net: U-Net in U-Net for infrared small object detection[J]. IEEE Transactions on Image Processing, 2022, 32: 364-376.
[13]
RonnebergerO, FischerP, BroxT. U-Net: convolutional networks for biomedical image segmentation[C]// Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 2015: 234-241.
[14]
LinT Y, DollárP, GirshickR, et al. Feature pyramid networks for object detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 2117-2125.
[15]
WooS, ParkJ, LeeJ Y, et al. Cbam: convolutional block attention module[C]∥Proceedings of the European Conference on Computer Vision, Munich, Germany, 2018: 3-19.
[16]
DaiY, WuY, ZhouF, et al. Asymmetric contextual modulation for infrared small target detection[C]∥Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, 2021: 950-959.
[17]
LiB, XiaoC, WangL, et al. Dense nested attention network for infrared small target detection[J]. IEEE Transactions on Image Processing, 2022, 32: 1745-1758.
[18]
DaiY, WuY, ZhouF, et al. Attentional local contrast networks for infrared small target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(11): 9813-9824.
[19]
SunY, YangJ, AnW. Infrared dim and small target detection via multiple subspace learning and spatial-temporal patch-tensor model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(5): 3737-3752.