期刊文献+

基于目标特征分布增强卷积神经网络的红外目标检测算法

Infrared Target Detection Algorithm Based on Target Feature Distribution Enhanced Convolutional Neural Network
原文传递
导出
摘要 为了实现对水上红外弱小目标的探测,并减少由红外图像信噪比低、目标与背景的红外特征差异小等问题对检测结果的影响,通过结合红外图像的成分、纹理及目标形状特征,提出了基于目标特征分布增强卷积神经网络的红外目标检测(TFD_CNN)算法。该算法包含目标特征分布学习与深度神经网络,具备滤除红外图像中噪声的能力,并深度挖掘红外图像中目标的边缘、纹理及形状信息,提升了卷积神经网络的分类精度。通过与4种算法进行实验对比,TFD_CNN算法分类准确率为96%,高于其他算法。结果表明:TFD_CNN算法具备对红外图像中落水人员与船只的分类能力。 In order to achieve the detection of infrared weak small maritime targets and reduce the impact of low signal-to-noise ratio of infrared images and small differences in infrared features between targets and backgrounds on the detection results,a infrared target detection algorithm based on target feature distribution enhanced convolutional neural network(TFD_CNN)is proposed by combining the composition,texture,and target shape features of infrared images.The algorithm includes target feature distribution learning and deep neural networks,which has the ability to filter out noise in infrared images and deeply mines the edge,texture and shape information of the target in the infrared image to improve the classification accuracy of the convolutional neural network.Through the experimental comparison with four other algorithms,the classification accuracy of the TFD_CNN algorithm is 96%,which is higher than other algorithms.The results show that the TFD_CNN algorithm has the ability to classify drowning persons and ships in the infrared image.
作者 丁胜男 李威 蔡立明 李蒙 胡常青 DING Shengnan;LI Wei;CAI Liming;LI Meng;HU Changqing(Aerospace Times Marine Equipment Technology Development Co.,Ltd(Qingdao),Qingdao 266237;Beijing Institute of Aerospace Control Devices,Beijing 100039)
出处 《导航与控制》 2024年第1期97-106,62,共11页 Navigation and Control
基金 国家自然科学基金(编号:61971153,62271159)
关键词 红外弱小目标 目标特征分布学习 深度学习 目标分类 infrared weak small target target feature distribution learning deep learning object classification
  • 相关文献

参考文献3

二级参考文献18

  • 1张凯.基于立体视觉的自然手势识别[学位论文].北京:北京大学,2005.
  • 2LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. USA: IEEE, 1998: 2278-2324.
  • 3Lauer F, Suen CY, Bloch G. A trainable feature extractor for handwritten digit recognition. Pattern Recognition, 2007, 40(6):1816-1824.
  • 4Lawrence S, Giles CL, Tsoi AC, Back AD. Face recognition: A convolutional neural network approach. IEEE Trans. on Neural Networks, 1997, 8(1): 98-113.
  • 5Tivive FHC, Bouzerdoum A. An eye feature detector based on convolutional neural network. Proc. 8th Int. Symp. Signal Process. Applic. Sydney, New South Wales, Australia. IEEE, 2005: 90-93.
  • 6Mate S, Akira Y, Munetaka Y, Jun O. Pedestrian detection with convolutional neural networks. IEEE Intelligent Vehicles Symposium Proceedings. USA: IEEE, 2005: 224-229.
  • 7Cun YL, Muller U, Ben J, Cosatto E, Flepp B. Off-road obstacle avoidance through end-to-end learning. Advances in Neural Information Processing Systems. USA: MIT Press, 2005.
  • 8曾志强,吴群,廖备水,高济.一种基于核SMOTE的非平衡数据集分类方法[J].电子学报,2009,37(11):2489-2495. 被引量:48
  • 9赵志宏,杨绍普,马增强.基于卷积神经网络LeNet-5的车牌字符识别研究[J].系统仿真学报,2010,22(3):638-641. 被引量:151
  • 10徐姗姗,刘应安,徐昇.基于卷积神经网络的木材缺陷识别[J].山东大学学报(工学版),2013,43(2):23-28. 被引量:45

共引文献110

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部