面向安检X光图像的违禁物品语义分割与识别研究
Semantic segmentation and recognition of contraband for security X-ray images
李广睿 1刘琼 2张熠卿 1张馨瑶 1黄景煦 3傅健4
作者信息
- 1. 北京信息科技大学自动化学院 北京 100192
- 2. 北京信息科技大学自动化学院 北京 100192;北京航空航天大学江西研究院 南昌 330200
- 3. 西安电子科技大学人工智能学院 西安 710071
- 4. 北京航空航天大学江西研究院 南昌 330200;北京航空航天大学机械工程及自动化学院 北京 100083;北京航空航天大学宁波创新研究院 宁波 315800
- 折叠
摘要
针对安检X光图像中违禁物品大小不一、物品摆放随意且存在重叠遮挡的技术难题,提出了一种改进的HRNet多尺度特征融合网络模型,实现图像中违禁物品的自动分割与识别.在编码阶段,利用HRNet网络中的多分辨率并行网络架构,提取多尺度特征,解决安检X光图像违禁物品尺度多样化的问题.在解码阶段,提出一种多层级特征聚合模块,采用数据相关上采样方法减少信息丢失,并聚合编码阶段提取的特征,以对物品进行更完整表征.在网络整体架构中,嵌入基于注意力机制的去遮挡模块加强模型的边缘感知能力,缓解安检 X光图像中物品重叠遮挡严重的问题,提高模型的分割识别精度.通过在PIDray安检图像公开数据集进行实验,结果表明,在Easy、Hard、Hidden 3 个验证子集上分别取得了73.15%、69.47%、58.33%的平均交并比,相比原始HRNet模型,分别提升了 0.49%、1.17%、5.69%,总体平均交并比提升约 2.45%.
Abstract
In response to the technical challenges posed by the varying sizes,haphazard arrangement,and overlapping occlusion of prohibited items in security X-ray images,we propose an enhanced HRNet-based multi-scale feature fusion network model.This model aims to achieve automatic segmentation and recognition of prohibited items in images.In the encoding stage,we leverage the multi-resolution parallel network architecture of HRNet to extract multi-scale features,addressing the diverse scale of prohibited items in security X-ray images.In the decoding stage,a multi-level feature aggregation module is introduced that uses data-dependent upsampling instead of bilinear interpolation.upsampling to reduce information loss during aggregation,thus ensuring a more comprehensive representation of the features of the features extracted in the coding stage for a more complete characterisation of objects.In the overall architecture of the network,a de-obscuration module based on the attention mechanism is embedded to strengthen the edge-awareness ability of the model,alleviate the problem of serious overlapping occlusion of items in security X-ray images,and improve the segmentation and recognition accuracy of the model.By experimenting on the public dataset of PIDray security check images,the results show that the average intersection ratio of 73.15%,69.47%,and 58.33%are achieved in the three validation subsets of Easy,Hard,and Hidden,respectively,which are 0.49%,1.17%,and 5.69%,respectively,and the overall average intersection ratio is improved by about 2.45%.
关键词
安检X光图像/语义分割/违禁品识别/深度学习Key words
security X-ray images/semantic segmentation/contraband identification/deep learning引用本文复制引用
基金项目
国家自然科学基金(62302051)
国家自然科学基金面上项目(51975026)
大科学装置项目(U1932111)
国家重点研发计划(2022YFF0607400)
出版年
2024
NETL
NSTL
万方数据