基于特征对齐和关键点辅助激励的退化热成像图目标检测

doi:10.16451/j.cnki.issn1003-6059.202012005

摘要
图/表
参考文献(31)
相关文章 (15)

全文: PDF (2169 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

在热成像图目标检测中,存在图像的纹理单一、目标边界模糊等退化现象,这造成目标定位困难、目标与预定义锚点框无法精准匹配等问题.因此,文中提出基于特征对齐和关键点辅助激励的退化热成像图目标检测算法.引入可见光图分支,计算2个分支指定层的特征差异,提升热成像域与可见光域之间的相似度.为了丰富网络高层中的目标细节信息,修改特征图级联和检测尺度.部署包含关键点辅助激励的无锚点检测器,较好地定位目标并学习预定义锚点框覆盖较差的实例.在2个数据集上的对比实验表明,文中算法可准确定位热成像目标,有效提升退化热成像图目标检测精度.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘盛
	金坤
	王俊
	叶焕然
	程豪豪

关键词 ：热成像图, 目标检测, 特征对齐, 关键点辅助激励

Abstract：

In the object detection of thermal images,the image degradation phenomena,like the simple texture and the blurred object boundary,result in difficulties in localizing objects and matching the objects with the predefined anchor boxes.Therefore,an object detection algorithm for degraded thermal image based on feature alignment and assisted excitation of key points is proposed.Firstly,the visible image branch is introduced,and the similarity between the thermal domain and the visible domain is improved by calculating the feature difference of specified layers in two branches.Then,feature map concatenation and detection scale are modified to enrich the details of objects in the high-level network layers.Finally,an anchor-free detector with assisted excitation of key points is deployed,and thus the model localizes objects better and learn the instances poorly covered by the predefined anchor boxes.Comparative experiments on two datasets show that the proposed algorithm localizes thermal objects accurately and improves the accuracy of object detection in degraded thermal image effectively.

Key words： Thermal Image Object Detection Feature Alignment Assisted Excitation of Key Points

收稿日期: 2020-09-10

基金资助:

国家重点研发计划项目(No.2018YFB1305200)、浙江省科学技术厅项目(No.LGG19F020010)资助

通讯作者: 刘盛,博士,副教授,主要研究方向为计算机视觉、数字图像处理.E-mail:edliu@zjut.edu.cn.

作者简介: 金坤,硕士研究生,主要研究方向为计算机视觉、目标检测.E-mail:jinkun@zjut.edu.cn;王俊,博士研究生,主要研究方向为计算机视觉、目标跟踪.E-mail:1111912011@zjut.edu.cn;叶焕然,硕士研究生,主要研究方向为计算机视觉、语义分割.E-mail:huanran@zjut.edu.cn;程豪豪,硕士研究生,主要研究方向为计算机视觉、人体姿态估计.E-mail:2111812002@zjut.edu.cn.

引用本文:

刘盛, 金坤, 王俊, 叶焕然, 程豪豪. 基于特征对齐和关键点辅助激励的退化热成像图目标检测[J]. 模式识别与人工智能, 2020, 33(12): 1104-1114. LIU Sheng, JIN Kun, WANG Jun, YE Huanran, CHENG Haohao. Object Detection in Degraded Thermal Image Based on Feature Alignment and Assisted Excitation of Key Points. , 2020, 33(12): 1104-1114.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202012005 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2020/V33/I12/1104

[1] QI B,JOHN V,LIU Z,et al.Use of Sparse Representation for Pedestrian Detection in Thermal Images//Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2014:274-280.
[2] LIU Y C,HUANG S S,LU C H,et al.Thermal Pedestrian Detection Using Block LBP with Multi-level Classifier//Proc of the International Conference on Applied System Innovation.Washington,USA:IEEE, 2017:602-605.
[3] KHANDHEDIYA Y,SAV K,GAJJAR V.Human Detection for Night Surveillance using Adaptive Background Subtracted Image[C/OL].[2020-09-04].https://arxiv.org/ftp/arxiv/papers/1709/1709.09389.pdf.
[4] HEO D,LEE E,CHUL K B.Pedestrian Detection at Night Using Deep Neural Networks and Saliency Maps.Journal of Imaging Science and Technology,2017,61(6):060403-1-060403-9.
[5] REDMON J,FARHADI A.YOLO9000:Better,Faster,Stronger//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2017:6517-6525.
[6] GHOSE D,DESAI S M,BHATTACHARYA S,et al.Pedestrian Detection in Thermal Images Using Saliency Maps//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:988-997.
[7] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks//Proc of the 28th International Conference on Neural Information Processing Systems.Cambridge,USA:The MIT Press,2015:91-99.
[8] LI N,BI H B,ZHANG Z,et al.Performance Comparison of Saliency Detection[J/OL].[2020-09-04].http://downloads.hindawi.com/journals/am/2018/9497083.pdf.
[9] GUO T T,HUYNH C P,SOLH M.Domain-Adaptive Pedestrian Detection in Thermal Images//Proc of the IEEE International Conference on Image Processing.Washington,USA:IEEE,2019:1660-1664.
[10] GUAN D Y,LUO X,CAO Y P,et al.Unsupervised Domain Adaptation for Multispectral Pedestrian Detection//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:434-443
[11] MUNIR F,AZAM S,RAFIQUE M A,et al.Thermal Object Detection Using Domain Adaptation through Style Consistency[C/OL].[2020-09-04].https://arxiv.org/pdf/2006.00821.pdf.
[12] LIU J J,ZHANG S T,WANG S,et al.Multispectral Deep Neural Networks for Pedestrian Detection[C/OL].[2020-09-04].https://arxiv.org/pdf/1611.02644.pdf.
[13] LI C Y,SONG D,TONG R F,et al.Illumination-Aware Faster R-CNN for Robust Multispectral Pedestrian Detection.Pattern Re-cognition,2019,85:161-171.
[14] DEVAGUPTAPU C,AKOLEKAR N,SHARMA M M,et al.Bo-rrow from Anywhere:Pseudo Multi-modal Object Detection in Thermal Imagery//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:1029-1038.
[15] LIU M Y,BREUEL T,KAUTZ J.Unsupervised Image-to-Image Translation Networks//Proc of the 31st International Conference on Neural Information Processing Systems.Cambridge,USA:The MIT Press,2017:700-708.
[16] ZHU J Y,PARK T,ISOLA P,et al.Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks//Proc of the IEEE International Conference on Computer Vision.Washington,USA:IEEE,2017:2242-2251.
[17] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[C/OL].[2020-09-04].https://arxiv.org/pdf/1804.02767.pdf.
[18] HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2016:770-778.
[19] TIAN Z,SHEN C H,CHEN H,et al.FCOS:Fully Convolutional One-Stage Object Detection//Proc of the IEEE/CVF International Conference on Computer Vision.Washington,USA:IEEE,2019:9626-9635.
[20] HWANG S,PARK J,KIM N,et al.Multispectral Pedestrian Detection:Benchmark Dataset and Baseline//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2015:1037-1045.
[21] ZHU C C,HE Y H,SAVVIDES M.Feature Selective Anchor-Free Module for Single-Shot Object Detection//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:840-849.
[22] DERAKHSHANI M M,MASOUDNIA S,SHAKER A H,et al.Assisted Excitation of Activations:A Learning Technique to Improve Object Detectors//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:9193-9202.
[23] REZATOFIGHI H,TSOI N,GWAK J Y,et al.Generalized Intersection over Union:A Metric and a Loss for Bounding Box Regre-ssion//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:658-666.
[24] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection.IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[25] KONIG D,ADAM M,JARVERS C,et al.Fully Convolutional Region Proposal Networks for Multispectral Person Detection//Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition.Washington,USA:IEEE,2017:241-250
[26] GUAN D Y,CAO Y P,YANG J X,et al.Fusion of Multispectral Data through Illumination-Aware Deep Neural Networks for Pedestrian Detection.Information Fusion,2019,50:148-157.
[27] KONG T,SUN F C,LIU H P,et al.FoveaBox:Beyound Anchor-Based Object Detection.IEEE Transactions on Image Processing,2020,29:7389-7398.
[28] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection[C/ OL].[2020-09-04].https://arxiv.org/pdf/2004.10934.pdf.
[29] WANG C Y,LIAO H Y M,WU Y H,et al.CSPNet:A New Backbone That Can Enhance Learning Capability of CNN//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2020:1571-1580.
[30] HE K M,ZHANG X Y,REN S Q,et al.Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition//Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2014:346-361.
[31] LIU S,QI L,QIN H F,et al.Path Aggregation Network for Instance Segmentation//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2018:8759-8768.