摘要
在基于深度网络的目标检测模型中,仅利用串行的卷积操作,模型会缺少描述网络不同层次的细节信息和特征图全局信息的能力,减弱小目标的检测能力,影响检测精度.基于残差网络结构,文中提出融合多维空洞卷积(MDC)算子和多层次特征的深度网络检测算法.首先设计MDC算子,卷积核具有5种不同的感受野,可获取8种不同语义的特征图,并引入串行网络的特征提取环节,构造特征层.再通过转置卷积操作实现检测层升维,用于级联不同层次的特征层,得到检测层并保证能在最大程度上保留目标的原始特征.最后使用非极大抑制完成检测算法的构建.实验表明,文中算法有效提高目标平均检测精度和小目标的检测能力.
The exclusive usage of sequential convolution operation in the deep networks results in the lack of the target detailed information of feature layers and global characteristics.The detection performance for small objects and the detection accuracy are reduced.In this paper,a deep networks detection algorithm fusing multiple dilated convolution(MDC)operator and multi-level characteristics is proposed based on the residual network structure.The convolution kernel is composed of 5 different receptive fields and 8 different semantic feature maps can be generated.The MDC operator is introduced into the feature extraction block to build a new feature layer.The transposition convolution is employed to increase the dimension of the detection layer and make a collage of multi-level feature layers.Thus,the original features of the targets can be retained in the newly generated detection layer to the most extent.Finally,the detection model is constructed by the non-maximal suppression.The experimental results show that the proposed model with the multi-leveled features and MDC operator can effectively improve the mean average precision and detection performance for small targets.
作者
张新良
谢恒
赵运基
王琬如
魏胜强
ZHANG Xinliang;XIE Heng;ZHAO Yunji;WANG Wanru;WEI Shengqiang(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo 454000)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2020年第10期898-905,共8页
Pattern Recognition and Artificial Intelligence
基金
河南省高等学校重点科研项目(No.21A120004)
河南省创新型科技人才队伍建设工程(No.CXTD2016054)
中原高水平人才专项支持计划(No.ZYQR201912031)
河南理工大学基础科研基金项目(No.NSFRF170501)资助。
关键词
多维空间卷积(MDC)算子
目标检测
转置卷积
细节信息
全局信息
Multiple Dilated Convolution(MDC)Operator
Target Detection
Transposition Convolution
Detailed Information
Global Information
