小样本条件下的公路建设项目场景识别与安全预警
Scene Recognition and Safety Precaution of Highway Construction Projects Under Few-shot Conditions
周志宇 1王天一 1左治江 2冀虹 1杨刚 3任明龙 4高智1
作者信息
- 1. 武汉大学 遥感信息工程学院,湖北 武汉 430079
- 2. 江汉大学 智能制造学院,湖北 武汉 430056
- 3. 中交路桥建设有限公司,北京 101107
- 4. 广州市高速公路有限公司,广东 广州 510030
- 折叠
摘要
由于具有系统性、完整性的公路样本数据集的短缺,使得传统深度学习范式难以满足应用需求.针对该问题,提出一种基于小样本的双阶段场景识别框架,并以容易获取的遥感数据进行训练测试,最后应用于公路场景中.小样本学习首先从大规模基类数据集中获取先验知识、学习基础模型,再将学习结果泛化至训练时未出现的或训练样本很少的新类别中.在框架的第一阶段,引入多任务模型,从两个辅助任务中学习跨语义类的内在特征;在第二阶段,基于标签传播实现对有标签和无标签数据的联合预测.实验表明,该场景识别方法取得了 80.58%的分类精度,相较于SIB和CAN+T分别提升了 13.24%和 10.69%,在测试数据集中取得了 69.37%的分类精度,可用于各类实际公路建设项目中工程车辆行驶安全的场景识别与智能预警任务.
Abstract
The shortage of systematic and complete highway sample datasets makes it difficult for the traditional deep learning paradigm to meet the application requirements.Therefore,to address this problem,this paper proposed a two-stage scene recognition framework under small-sample conditions,with easily accessible remote sensing data for training tests,and then finally applied to highway scenes.The small-sample learning started with obtaining a priori knowledge from a large-scale base class dataset,learning the base model,and then generalizing the model to new classes that did not appear in the training process or had few training samples.In the first stage of the framework,we introduced a multi-task model to learn the intrinsic features across semantic classes from two auxiliary tasks,and then in the second stage,we implemented joint prediction of labeled and unlabeled data based on label propagation.Extensive experiments showed that the scene recognition method proposed in this article achieved a classification accuracy of 80.58%,which was an improvement of 13.24% and 10.69% compared to SIB and CAN+T,respectively.It performed excellently in the test dataset with a classification accuracy of 69.37%.This method can be used for scene recognition and intelligent warning tasks for engineering vehicle driving safety in various highway construction projects.
关键词
小样本场景分类/公路建设/安全巡检/遥感影像Key words
few-shot scene classification/road construction/safety inspection/remote sensing image引用本文复制引用
基金项目
国家自然科学基金重大项目(42192580)
国家自然科学基金重大项目(42192583)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据