基于激光图像特征提取的危险目标越界识别研究
Research on dangerous target crossing recognition based on laser image feature extraction
魏琛 1庄子波 1曹博书1
作者信息
- 1. 中国民航大学飞行分校,天津 301500
- 折叠
摘要
为了提升危险目标越界激光识别准确性和效率,提出基于激光图像特征提取的危险目标越界识别研究.利用非线性直接变换方法完成激光点云反射图像转换的尺度不变特征点匹配;设计反锐化双掩模法图像增强结构,优化增强处理图像;对点云反射特征点展开沃尔什变换与融合,利用BP神经网络结构,识别越界的危险目标.实验结果表明,所提方法应用后图像特征细节信息得到增强,不存在局部曝光问题,对危险目标越界的错检率和漏检率最低,且具有较高的识别精度和识别效率.
Abstract
In order to improve the accuracy and efficiency of dangerous target boundary crossing laser recognition,a research on dangerous target boundary crossing recognition based on laser image feature extraction is proposed.Using nonlinear direct transformation method to achieve scale invariant feature point matching in laser point cloud reflection image conversion;Design an anti sharpening dual mask image enhancement structure to optimize image enhancement processing;Perform Walsh transform and fusion on the reflection feature points of the point cloud,and use the BP neu-ral network structure to identify dangerous targets that are out of bounds.The experimental results show that the pro-posed method enhances the detailed information of image features after application,does not have local exposure is-sues,has the lowest false detection rate and missed detection rate for dangerous targets exceeding the boundary,and has high recognition accuracy and efficiency.
关键词
激光反射强度/图像融合/反锐化双掩膜增强/危险目标识别/BP神经网络Key words
laser reflection intensity/image fusion/anti sharpening double mask enhancement/hazard target i-dentification/BP neural network引用本文复制引用
基金项目
天津市自然科学基金多元投入基金面上项目(21JCYBJC00740)
中国气象局气象软科学项目(2023ZZXM29)
出版年
2024
NETL
NSTL
万方数据