期刊文献+

基于人工智能的大规模激光图像分类研究 被引量:5

Research on large scale laser image classification based on Artificial Intelligence
下载PDF
导出
摘要 传统激光图像分类研究主要针对小规模数据,而当前激光图像以海量、大规模形式存在,对分类速度和分类效率提出了更高的要求,结合大规模激光图像的特点,设计了一种基于人工智能的大规模激光图像分类方法。首先收集大规模激光图像,并提取激光图像的特征,然后采用人工智能技术-人工鱼群算法对激光图像特征进行筛选,最后设计了大规模激光图像的分类器,并采用多种类型的激光图像进行了验证性测试,测试结果表明本文方法的激光图像的分类正确率超过95%,激光图像分类时间平均低于6ms,十分适用于大规模激光图像的在线分类,且大规模激光图像综合分类性能要优于当前其它分类方法,实际应用价值更高。 The traditional laser image classification mainly for small scale data, and the current laser image to massive, large -scale form, put forward higher requirements on the classification speed and classification efficiency, combined with the characteristics of large scale laser image, design a large - scale laser image classification method based on artificial intelligence. The first collection of large - scale laser image and feature extraction of laser image, and then use artificial intelligence technology, the artificial fish swarm algorithm for laser image feature selection, the final design of the large - scale laser image classifier, and the use of laser image of various types of verification test, laser image classification accuracy of more than 95%, the laser image classification time the average of less than 2.45ms, is very suitable for online classification of large - scale laser image, and the classification of large - scale laser image has better performance than the other classification methods, the actual application of higher value.
作者 张春娥 赵晓东 杨丽娟 ZHANG Chune1, ZHAO Xiaodong2, YANG Lijuan1.(1. School of Computer and Remote Sensing Information Technology, North China Institute of Aerospace Engineering, Langfang Hebei 065000, China; 2. Center of Information Construction and Management, Hebei University of Science and Technology, Shijiazhuang 050018, Chin)
出处 《激光杂志》 北大核心 2018年第5期66-69,共4页 Laser Journal
基金 河北省科技支撑计划项目(No.17210803D) 北华航天工业学院科研项目(No.KY-2017-06)
关键词 人工智能技术 激光图像 分类器设计 特征向量 人工鱼群算法 artificial intelligence technology laser image classifier design feature vector artificial fishswarm algorithm
  • 相关文献

参考文献14

二级参考文献132

共引文献233

同被引文献62

引证文献5

二级引证文献17

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