一种可变锚框候选区域网络的目标检测方法

doi:10.13700/j.bh.1001-5965.2019.0531

北京航空航天大学学报 ›› 2020, Vol. 46 ›› Issue (8): 1610-1617.doi: 10.13700/j.bh.1001-5965.2019.0531

一种可变锚框候选区域网络的目标检测方法

李承昊¹, 茹乐², 何林远¹, 迟文升^2,3

1. 空军工程大学航空工程学院, 西安 710038;
2. 空军工程大学装备管理与无人机工程学院, 西安 710038;
3. 西安电子科技大学机电工程学院, 西安 710126

收稿日期:2019-09-29 发布日期:2020-08-27
通讯作者: 茹乐 E-mail:ru-le@163.com
作者简介:李承昊男,硕士研究生。主要研究方向:计算机视觉、航空电子信息及其智能化。
茹乐男,博士,教授,博士生导师。主要研究方向:抗干扰通信、航空电子信息及其智能化。
何林远男,博士,副教授。主要研究方向:图像去雾、超分辨率重建、模式识别。
基金资助:
国家自然科学基金（61701524）；中国博士后科学基金（2019M653742）；陕西省自然科学基础研究计划（2017JM6071）

Target detection method for region proposal network with variable anchor box

LI Chenghao¹, RU Le², HE Linyuan¹, CHI Wensheng^2,3

1. Aeronautics Engineering Institute, Air Force Engineering University, Xi'an 710038, China;
2. Equipment Management and Unmanned Aerial Vehicle Engineering College, Air Force Engineering University, Xi'an 710038, China;
3. School of Mechano-Electronic Engineering, Xidian University, Xi'an 710126, China

Received:2019-09-29 Published:2020-08-27
Supported by:
National Natural Science Foundation of China (61701524); China Postdoctoral Science Foundation (2019M653742); Natural Science Basic Research Program of Shaanxi (2017JM6071)

摘要/Abstract

摘要： 目标检测作为计算机视觉领域的热点问题，目前基于深度学习的目标检测方法可以分为2类：两步检测和一步检测，前者有着较高准确性，后者有着较好速度，但是为提高检测的性能两者都引入了锚机制。为提高目标检测系统的性能，基于深度卷积神经网络的两步检测算法引入了注意力引导（AG）模块，通过对候选区域网络（RPN）的锚机制进行引导，使得对于预选锚框形状的选择更具有多样性；同时针对传统的后处理方式非极大值抑制（NMS）算法存在的误检和漏检的问题，提出了一种置信度因子的NMS （Cf-NMS）算法，对于模型的整体性能有着很大的贡献。实验结果说明，所提方法虽然在速度性能上有略微的下降，但是无论是在RPN变体还是现有的先进算法在准确性方面都有提升。

关键词: 计算机视觉, 目标检测, 深度学习, 候选区域网络(RPN), 非极大值抑制(NMS)

Abstract: Object detection is a hot topic in the field of computer vision. At present, object detection methods based on deep learning can be divided into two categories: two-stage detection and one-stage detection. The former has higher accuracy, while the latter has better speed. In order to improve the performance of detection, anchor mechanism is introduced in both categories. In this paper, Attention Guidance (AG) module is introduced in the two-stage detection method based on the deep convolutional neural network, which guides the anchor mechanism of Region Proposal Network (RPN), making the selection of preselected box shape more diversified. At the same time, to solve the problem of false detection and missed detection in the traditional post-processing Non-Maximum Suppression (NMS) algorithm, a Confidence factor NMS (Cf-NMS) method is proposed, which makes a great contribution to the overall performance of the model. Experiment results showed that, although it has a slight decrease in speed performance, the proposed method has an improvement in accuracy in both the RPN variant and the existing advanced method.

Key words: computer vision, object detection, deep learning, Region Proposal Network (RPN), Non-Maximum Suppression (NMS)

中图分类号:

李承昊, 茹乐, 何林远, 迟文升. 一种可变锚框候选区域网络的目标检测方法[J]. 北京航空航天大学学报, 2020, 46(8): 1610-1617.

LI Chenghao, RU Le, HE Linyuan, CHI Wensheng. Target detection method for region proposal network with variable anchor box[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(8): 1610-1617.

参考文献

[1] 方路平,何杭江,周国民.目标检测算法研究综述[J].计算机工程与应用,2018,54(13):11-18.FANG L P,HE H J,ZHOU G M.Research overview of object detection methods[J].Computer Engineering and Applications,2018,54(13):11-18(in Chinese).
[2] 刘栋,李素,曹志冬.深度学习及其在图像物体分类与检测中的应用综述[J].计算机科学,2016,43(12):13-23.LIU D,LI S,CAO Z D.State-of-the-art on deep learning and its application in image object classification and detection[J].Computer Science,2016,43(12):13-23(in Chinese).
[3] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway:IEEE Press,2016:779-788.
[4] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//European Conference on Computer Vision.Berlin:Springer,2016:21-37.
[5] CHEN C,LIU M Y,TUZEL O,et al.R-CNN for small object detection[C]//Asian Conference on Computer Vision.Berlin:Springer,2016:214-230
[6] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2015:1440-1448.
[7] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[8] CAI Z,VASCONCELOS N.Cascade R-CNN:Delving into high quality object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway:IEEE Press,2018:6154-6162.
[9] HE K,GKIOXARI G,DOLLÁR P,et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2017:2961-2969.
[10] LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway:IEEE Press,2017:2117-2125.
[11] YAN Q,GONG D,SHI Q,et al.Attention-guided network for ghost-free high dynamic range imaging[EB/OL].(2019-04-23)[2019-09-20].https://arxiv.org/abs/1904.10293.
[12] VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[EB/OL].(2018-02-04)[2019-09-20].https://arxiv.org/abs/1710.10903.
[13] GUAN Q,HUANG Y,ZHONG Z,et al.Diagnose like a radiologist:Attention guided convolutional neural network for thorax disease classification[EB/OL].(2018-01-30)[2019-09-20].https://arxiv.org/abs/1801.09927.
[14] LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:Common objects in context[C]//European Conference on Computer Vision.Berlin:Springer,2014:740-755.
[15] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway:IEEE Press,2005:886-893.
[16] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[17] 张强,张陈斌,陈宗海.一种改进约束条件的简化非极大值抑制[J].中国科学技术大学学报,2016,46(1):6-11.ZHANG Q,ZHANG C B,CHEN Z H.A simplified non-maximum suppression with improved constraints[J].Journal University of Science and Technology of China,2016,46(1):6-11(in Chinese).
[18] 赵文清,严海,邵绪强.改进的非极大值抑制算法的目标检测[J].中国图象图形学报,2018,23(11):1676-1685.ZHAO W Q,YAN H,SHAO X Q.Object detection based on improved non-maximums suppression algorithm[J].Journal of Image and Graphics,2018,23(11):1676-1685(in Chinese).
[19] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems.Red Hook:Curran Associates Inc.,2012:1097-1105.

一种可变锚框候选区域网络的目标检测方法

Target detection method for region proposal network with variable anchor box

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李欣致, 董胜波, 崔向阳, 刘志哲, 郭广浩. 应用于智能芯片的可视化反馈系统研究[J]. 北京航空航天大学学报, 2020, 46(8): 1494-1502.
[2]	张阳, 牛之贤, 牛保宁, 常艳. 基于高分辨率网络的单声道歌声分离[J]. 北京航空航天大学学报, 2020, 46(8): 1555-1563.
[3]	吕娜, 周家欣, 陈卓, 刘鹏飞, 高维廷. 一种鲁棒性增强的机载网络流量分类方法[J]. 北京航空航天大学学报, 2020, 46(7): 1237-1246.
[4]	郑磊, 胡维多, 刘畅. 基于深度学习的大型陨石坑识别方法研究[J]. 北京航空航天大学学报, 2020, 46(5): 994-1004.
[5]	边亮, 罗霄阳, 李硕. 基于深度学习的图像拼接篡改检测[J]. 北京航空航天大学学报, 2020, 46(5): 1039-1044.
[6]	陈映雪, 丁文锐, 李红光, 王蒙, 王旭. 基于视频帧间运动估计的无人机图像车辆检测[J]. 北京航空航天大学学报, 2020, 46(3): 634-642.
[7]	杨思晨, 王华锋, 王月海, 李锦涛, 王赟豪. 深度学习机制与小波融合的超分辨率重建算法[J]. 北京航空航天大学学报, 2020, 46(1): 189-197.
[8]	张克明, 蔡远文, 任元. 基于生成对抗网络的航天异常事件检测方法[J]. 北京航空航天大学学报, 2019, 45(7): 1329-1336.
[9]	张鹏, 张嘉峰, 刘涛. 基于相干度优化的极化顺轨干涉SAR慢小目标CFAR检测[J]. 北京航空航天大学学报, 2019, 45(3): 575-587.
[10]	魏宏喜, 张越. 基于生成对抗网络的零样本图像分类[J]. 北京航空航天大学学报, 2019, 45(12): 2345-2350.
[11]	张新峰, 郭宇桐, 蔡轶珩, 孙萌. 基于DCNN和全连接CRF的舌图像分割算法[J]. 北京航空航天大学学报, 2019, 45(12): 2364-2374.
[12]	赵国, 秦世引. PMMWI与VI优势互补的人体隐蔽违禁物检测与定位[J]. 北京航空航天大学学报, 2019, 45(10): 2011-2025.
[13]	赵蓬辉, 孟春宁, 常胜江. 基于异步卷积分解与分流结构的单阶段检测器[J]. 北京航空航天大学学报, 2019, 45(10): 2089-2098.
[14]	郭琳, 秦世引. 遥感图像飞机目标高效搜检深度学习优化算法[J]. 北京航空航天大学学报, 2019, 45(1): 159-173.
[15]	韩京冶, 许福, 陈志泊, 刘辉. 一种基于深度学习的交互式电话号码识别方法[J]. 北京航空航天大学学报, 2018, 44(5): 1074-1080.