规范化(社会学)
计算机科学
人工智能
计算机视觉
残余物
遥感
熵(时间箭头)
Kullback-Leibler散度
特征(语言学)
模式识别(心理学)
特征提取
算法
物理
社会学
哲学
地质学
量子力学
语言学
人类学
作者
Shun Nian Luo,Jian Yu,Yunjiang Xi Xi,Liao Xiao
出处
期刊:IEEE Access
[Institute of Electrical and Electronics Engineers]
日期:2022-01-01
卷期号:10: 5184-5192
被引量:37
标识
DOI:10.1109/access.2022.3140876
摘要
Dealing with the insufficient detection accuracy and speed of aircraft targets in remote sensing images under complex background, this paper proposes a new detection method, YOLOv5-Aircraft, based on the YOLOv5 network. The YOLOv5-Aircraft model is improved in 3 ways: (1) At the beginning and end of original batch normalization module, centering and scaling calibration are added to enhance the effective features and form a more stable feature distribution, which strengthens the feature extraction ability of network model. (2) The cross-entropy loss function in the confidence of the original loss function is improved to the loss function based on smoothed Kullback-Leibler divergence. (3) For reducing information loss, the CSandGlass module is designed on the backbone feature extraction network of YOLOv5 to replace the residual module. Meanwhile, low-resolution feature layers are eliminated to reduce semantic loss. Experiment results demonstrate that the YOLOv5-Aircraft model can enhance the accuracy and speed of aircraft target detection in remote sensing images while achieving easier convergence.
科研通智能强力驱动
Strongly Powered by AbleSci AI