基于改进的Faster R-CNN的目标检测与识别  

Target Detection and Recognition Based on Improved Faster R-CNN

作　　者：房靖晶 成金勇[1] 

机构地区：[1]齐鲁工业大学(山东省科学院),计算机科学与技术学院,山东济南

出　　处：《图像与信号处理》2019年第2期43-50,共8页Journal of Image and Signal Processing

基　　金：山东省自然科学基金(23170807,ZR2017LB024,ZR2018LF004)项目资助。

摘　　要：近年来,随着深度学习不断的发展,基于深度学习的图像研究与应用已经在很多领域取得了优异的成绩。RCNN网络与全卷积网络等技术框架使得目标检测技术发展越来越迅速。Faster R-CNN算法被提出并广泛应用于目标检测和目标识别领域。在本文中,主要研究了基于Faster R-CNN算法对自制办公用品数据集中的图像进行的目标检测。相较于RCNN系列算法,Faster R-CNN提出了区域建议网络,同时将特征抽取、候选框提取、边界框回归、分类整合到一个网络当中,使得综合性能有很大改进。本文提出基于AlexNet改进的Faster R-CNN算法,在提取特征时,数据集通常具有大量高密度的连续性特征,而激活函数具有稀疏性,解决了目标小且背景复杂情况下的办公用品目标检测问题,提高了检测速度和检测精度。In recent years,with the continuous development of in-depth learning,image research and appli-cation based on in-depth learning has achieved excellent results in many fields.RCNN network and full convolution network make the development of target detection technology more and more rapid.Faster R-CNN algorithm has been proposed and widely used in the field of target detection and recognition.In this paper,we mainly study the object detection based on Faster R-CNN algo-rithm for the image in the data set of self-made office supplies.Compared with RCNN series algo-rithms,Faster R-CNN proposes a regional recommendation network,and integrates feature ex-traction,candidate box extraction,boundary box regression and classification into a network,which greatly improves the overall performance.In this paper,an improved Faster R-CNN algorithm based on activation function is proposed.When extracting features,the data set usually has a large number of high-density continuity characteristics,while the activation function is sparse,which solves the problem of target detection of office supplies under small targets and complex background,and improves the detection speed and accuracy.

关 键 词：深度学习 目标检测 区域建议网络 特征提取 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]