基于深度学习利用特征图加权融合的目标检测方法

doi:10.3969/j.issn.1000-1158.2020.11.06

摘要
图/表
参考文献(20)
相关文章 (15)

全文: PDF (1728 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为了提高目标检测的准确性,提出了一种基于深度学习利用特征图加权融合实现目标检测的方法。首先,提出将卷积神经网络中的浅层特征图采样后与最深层特征图进行加权融合的思想;其次,根据所提的特征图加权融合思想以及卷积神经网络的具体结构,制定相应的特征图加权融合方案,并由该方案得到新特征图;然后,提出改进的RPN网络,并将新特征图输入到改进的RPN网络得到区域建议;最后,将新特征图和区域建议输入到后续网络层完成目标检测。实验结果表明所提方法取得了更高的目标检测精度以及更好的目标检测效果。

	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

关键词 ：计量学, 目标检测, 视觉测量, 深度学习, 特征图加权融合, 改进的RPN网络

Abstract：In order to improve the accuracy of object detection, a method based on deep learning using feature map weighted fusion is proposed. Firstly, the idea fusing the sampled shallow feature maps and the deepest feature map in the convolutional neural network is proposed. Secondly, the corresponding feature map weighted fusion scheme is developed according to the idea of feature map weighted fusion and the specific structure of convolutional neural network, and a new feature map is obtained from the scheme. Thirdly, an improved RPN network is proposed, and the new feature map is input into the improved RPN network to obtain the region proposals. Finally, the new feature map and the region proposals are input subsequent network layers to realize object detection. The experimental results show that the proposed method achieves higher object detection precision and better object detection effect.

Key words： metrology object detection visual measurement deep learning feature map weighted fusion improved RPN network

收稿日期: 2019-01-30 发布日期: 2020-11-02

PACS:

TB96

基金资助:国家自然科学基金(61379065);河北省自然科学基金(F2014203119);装备发展部信息系统局“十三五”预研课题(31511040401)

作者简介: 张世辉(1973-),男,河北赞皇人,燕山大学教授,博士生导师,主要从事视觉信息处理方面的研究。Email: sshhzz@ysu.edu.cn

引用本文:

张世辉,王红蕾,陈宇翔,刘新焕,张健,何欢,任卫东. 基于深度学习利用特征图加权融合的目标检测方法[J]. 计量学报, 2020, 41(11): 1344-1351.
ZHANG Shi-hui,WANG Hong-lei,CHEN Yu-xiang,LIU Xin-huan,. An Object Detection Method Based on Deep LearningUsing Feature Map Weighted Fusion. Acta Metrologica Sinica, 2020, 41(11): 1344-1351.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2020.11.06 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2020/V41/I11/1344

［1］Du Y, Wang W, Wang L. Hierarchical recurrent neural network for skeleton based action recognition ［C］// 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA, 2015:1110-1118.
［2］Hu P Y, Ramanan D. Finding tiny faces ［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017:1522-1530.
［3］王洪斌, 于菲, 李一骏, 等. 分块特征匹配与局部差分结合的运动目标检测［J］. 计量学报, 2015, 36(4): 352-355.
Wang H B, Yu F, Li Y J, et al. Detection of moving object by combining block features matching and local differential ［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2015, 36(4): 352-355.
［4］Wu Z X, Fu Y W, Jiang Y G, et al. Harnessing object and scene semantics for large-scale video understanding ［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:3112-3121.
［5］Cordts M, Omran M, Ramos S, et al. The cityscapes dataset for semantic urban scene understanding ［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:3213-3223.
［6］Lienhart R, Maydt J. An extended set of Haar-like features for rapid object detection ［C］//Proceedings of International Conference on Image Processing. Rochester, NY, USA, 2002: 900-903.
［7］Ren X F, Ramanan D. Histograms of sparse codes for object detection ［C］//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland OR, USA, 2013:3246-3253.
［8］Dalal N, Triggs B. Histograms of oriented gradients for human detection ［C］//2005 IEEE Conference on Computer Vision and Pattern Recognition. San Diego,CA, USA, 2005:886-893.
［9］程淑红, 高许, 周斌. 基于多特征提取和SVM参数优化的车型识别［J］. 计量学报, 2018, 39(3): 348-352.
Chen S H, Gao X, Zhou B. Vehicle recognition based on multi-feature extraction and SVM parameter optimization ［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2018, 39(3): 348-352.
［10］Viola P, Jones M. Rapid object detection using a boosted cascade of simple features ［C］//2001 IEEE Conference on Computer Vision and Pattern Recognition. Kauai, HI, USA, 2001:511-518.
［11］Kazemi F M, Samadi S, Poorreza H R, et al. Vehicle recognition using Curvelet transform and SVM ［C］// Fourth International Conference on Information Technology. Las Vegas NV, USA , 2007:516-521.
［12］Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation ［C］//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:580-587.
［13］Uijlings J R, Sande K E, Gevers T, et al. Selective search for object recognition ［J］. [WTBX][STBX]International Journal of Computer Vision[STBZ][WTBZ], 2013, 104(2): 154-171.
［14］Ren S, He K, Sun J, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition ［J］. [WTBX][STBX]IEEE Transactions on Pattern Analysis and Machine Intelligence[STBZ][WTBZ], 2015, 37(9): 1904-1916.
［15］Girshick R. Fast R-CNN ［C］// 2015 IEEE International Conference on Computer Vision. Santiago,Chile, 2015:1440-1448.

［16］Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks ［J］. [WTBX][STBX]IEEE Transactions on Pattern Analysis and Machine Intelligence[STBZ][WTBZ], 2016, 39(6): 1137-1149.
［17］Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector ［C］//Proceedings of the European Conference on Computer Vision. Amsterdam, Holland, 2016: 21-37.
［18］Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection ［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:779-788.
［19］田卓,佘青山,甘海涛,等.面向人脸特征点定位和姿态估计任务协同的DCNN方法［J］.计量学报, 2019, 40(4): 576-582.
Tian Z, She Q S, Gan H T, et al. DCNN for Task Coordination of Facial Landmark Localization and Head Pose Estimation［J］.Acta Metrologica Sinica, 2019, 40(4): 576-582.
［20］张世辉,耿勇,张笑维,等. 基于深度图像利用BP网络实现遮挡边界检测［J］.计量学报, 2020, 41(10): 1205-1211.
Zhang S H, Geng Y, Zhang X W, et al. Using BP Network for Occlusion Boundary Detection Based on Depth Image［J］. Acta Metrologica Sinica, 2020, 41(10): 1205-1211.