[1]高 群,朱 均,王芊芊,等. 基于鱼眼图像的目标检测算法研究[J].控制与信息技术(原大功率变流技术),2019,(03):1.[doi:10.13889/j.issn.2096-5427.2019.03.100]
 GAO Qun,ZHU Jun,WANG Qianqian,et al.Research on the Object Detection Algorithm Based on Fisheye Image[J].High Power Converter Technology,2019,(03):1.[doi:10.13889/j.issn.2096-5427.2019.03.100]
点击复制

 基于鱼眼图像的目标检测算法研究()
分享到:

《控制与信息技术》(原《大功率变流技术》)[ISSN:2095-3631/CN:43-1486/U]

卷:
期数:
2019年03期
页码:
1
栏目:
出版日期:
2019-06-30

文章信息/Info

Title:
Research on the Object Detection Algorithm Based on Fisheye Image
作者:
 高 群1朱 均2王芊芊1曹 杰3许 超2
 (1.国网浙江温岭市供电有限公司,浙江 温岭 317500;2.浙江大学 控制科学与工程学院,浙江 杭州 310000;
3.温岭市非普电气有限公司,浙江 温岭 317500)
Author(s):
GAO Qun1 ZHU Jun2 WANG Qianqian1 CAO Jie3 XU Chao2
 ( 1. State Grid Zhejiang Wenling Power Supply Co., Ltd., Wenling, Zhejiang 317500, China; 2. College of Control Science and
Engineering, Zhejiang University, Hangzhou, Zhejiang 310000, China; 3. Wenling Feipu Electric Co., Ltd., Wenling, Zhejiang 317500, China )
关键词:
 目标检测鱼眼图像深度学习畸变矫正嵌入式特征提取
Keywords:
 object detection fisheye image deep learningdistortion correction embedded system feature extraction
分类号:
TN911.73
DOI:
10.13889/j.issn.2096-5427.2019.03.100
文献标志码:
A
摘要:
 鱼眼图像在使用前一般会先进行畸变矫正,但畸变严重的图像矫正会降低图像质量。为了提高目标检测精度与速度,文章提出了一种利用单个下视鱼眼摄像头代替多个普通摄像头的目标检测方案。其采用特征金字塔结构检测多尺度物体,并结合下视鱼眼的旋转与畸变特性进行算法优化,直接在原始鱼眼图像上进行目标检测。通过构建下视鱼眼数据集并进行实验,结果显示,所提出的鱼眼目标检测模型不仅精度较高,而且还能在嵌入式设备上快速运行。
Abstract:
 Fisheye image is usually corrected before it is used, but image correction with serious distortion will reduce image quality. In order to improve the accuracy and speed of object detection, this paper adopts a single bottom-view fisheye camera instead of multiple common cameras. It uses the feature pyramid structure to detect multi-scale objects, and combines the rotation and distortion characteristics of the fisheye to optimize the algorithm and directly detects the objects from the original fisheye image. In this paper, a downside fisheye dataset is constructed and experimented. The experimental results show that the fisheye detection model has high accuracy and can run fast on embedded devices.

参考文献/References:

 [1] 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 & Machine Intelligence, 2015, 39(6):1137-1149.
[2] DAI J , LI Y , HE K , et al. R-FCN: Object Detection via Region-based Fully Convolutional Networks[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain,2016:379-387 .
[3] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas, USA,2016:770-778.
[4] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot MultiBox Detector[J]. Proceedings of European Conference on Computer Vision ,2016:21-37.
[5] REDMON J, DIVVALA S , GIRSHICK R, et al. You Only Look Once: Unified, Real-Time Object Detection[C]// Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015:779-788.
[6] REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger[C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu, USA, 2017:6517-6525.
[7] REDMON J, FARHADI A. YOLOv3: An Incremental Improvement[J/oL]. arXiv,2018:1-8[2018-12-01]. https: //arxiv. org/pdf/1804.02767.pdf.
[8] HUANG J, RATHOD V, SUN C, et al. Speed/accuracy trade-offs for modern convolutional object detectors[C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA,2017:3296-3297.
[9] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// International Conference on International Conference on Machine Learning. Lille, France, 2015:448-456.
[10] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the Inception Architecture for Computer Vision[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA,2016:2818-2826.
[11] SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence .California ,USA, 2016:4278-4284.
[12] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[J/oL]. arXiv, 2017: 1-9[2018-12-01]. https://arxiv. org/pdf/1704.04861.pdf.
[13] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017(1):2999-3007.
[14] GIRSHICK R. Fast R-CNN[C]//IEEE International Conference on Computer Vision (ICCV).Santiago, Chile, 2015:1440-1448.
[15] TIELEMAN T,HINTON G. Double Sarsa and Double Expected Sarsa with Shallow and Deep Learning[J]. Journal of Data Analysis and Information Processing,2016,4(4):26-31.

相似文献/References:

[1]冯江华,胡 惇,罗凌波. 交直交中压大功率变频技术在冶金轧机上的应用[J].控制与信息技术(原大功率变流技术),2015,(05):1.[doi:10.13889/j.issn.2095-3631.2015.05.001]
 FENG Jianghua,HU Dun,LUO Lingbo. Application of AC-DC-AC High -power Medium-voltage Converter on Metallurgical Mill[J].High Power Converter Technology,2015,(03):1.[doi:10.13889/j.issn.2095-3631.2015.05.001]
[2]张 明. 现代电力电子集成技术综述[J].控制与信息技术(原大功率变流技术),2016,(01):1.[doi:10.13889/j.issn.2095-3631.2016.01.001]
 ZHANG Ming. Overview of Modern Power Electronics Integration Technology[J].High Power Converter Technology,2016,(03):1.[doi:10.13889/j.issn.2095-3631.2016.01.001]
[3]窦泽春,刘国友,陈 俊,等. 大功率压接式IGBT 器件设计与关键技术[J].控制与信息技术(原大功率变流技术),2016,(02):21.[doi:10.13889/j.issn.2095-3631.2016.02.005]
 DOU Zechun,LIU Guoyou,CHEN Jun,et al. Design and Key Technologies of High-power Press-pack IGBT Device[J].High Power Converter Technology,2016,(03):21.[doi:10.13889/j.issn.2095-3631.2016.02.005]
[4]熊 辉,袁 勇,黄 南,等. 风电功率组件电热特性分析[J].控制与信息技术(原大功率变流技术),2016,(02):47.[doi:10.13889/j.issn.2095-3631.2016.02.010]
 XIONG Hui,YUAN Yong,HUANG Nan,et al. Analysis of Electrical & Thermal Performances for Power Assembly of Wind Power[J].High Power Converter Technology,2016,(03):47.[doi:10.13889/j.issn.2095-3631.2016.02.010]
[5]邓云川,高 宏,陈建君. 基于拓展Carson 理论的单线隧道内牵引网电气参数计算研究[J].控制与信息技术(原大功率变流技术),2016,(03):1.[doi:10.13889/j.issn.2095-3631.2016.03.100]
 DENG Yunchuan,GAO Hong,CHEN Jianjun. Study of Electrical Parameter Calculation for Traction Network in Single-line Tunnel Based on the Extend of Carson Theory[J].High Power Converter Technology,2016,(03):1.[doi:10.13889/j.issn.2095-3631.2016.03.100]
[6]章志兵,张志学,陈志博. 交流传动列车谐波性能优化策略[J].控制与信息技术(原大功率变流技术),2016,(04):0.[doi:10.13889/j.issn.2095-3631.2016.04.001]
 ZHANG Zhibing,ZHANG Zhixue,CHEN Zhibo. Optimization of the Harmonic in AC Drive Locomotive and EMUs[J].High Power Converter Technology,2016,(03):0.[doi:10.13889/j.issn.2095-3631.2016.04.001]
[7]王 俊,张 渊,李宗鉴,等. SiC GTO 晶闸管技术现状及发展[J].控制与信息技术(原大功率变流技术),2016,(05):7.[doi:10.13889/j.issn.2095-3631.2016.05.100]
 WANG Jun,ZHANG Yuan,LI Zongjian,et al. Technology Status and Development of SiC GTO Thyristor[J].High Power Converter Technology,2016,(03):7.[doi:10.13889/j.issn.2095-3631.2016.05.100]
[8]彭朝阳,白 云,申华军,等. 3 300 V 高压4H-SiC 结势垒肖特基二极管器件的研制[J].控制与信息技术(原大功率变流技术),2016,(05):46.[doi:10.13889/j.issn.2095-3631.2016.05.200]
 PENG Zhaoyang,BAI Yun,SHEN Huajun,et al. Development of High voltage 4H-SiC Junction Barrier Schottky Diode with 3 300 V Blocking Voltage[J].High Power Converter Technology,2016,(03):46.[doi:10.13889/j.issn.2095-3631.2016.05.200]
[9]臧晓笛,田德文. 低开关频率下永磁同步电机弱磁区电流谐波抑制[J].控制与信息技术(原大功率变流技术),2016,(06):1.[doi:10.13889/j.issn.2095-3631.2016.06.200]
 ZANG Xiaodi,TIAN Dewen. Current Harmonic Suppression of Permanent Magnet Synchronous Motor in Weak Magnetic Field under Low Switching Frequency[J].High Power Converter Technology,2016,(03):1.[doi:10.13889/j.issn.2095-3631.2016.06.200]
[10]孟乐轩,赵 鑫,Mehdi Savaghebi,等. 微电网电能质量分层控制及其关键技术[J].控制与信息技术(原大功率变流技术),2017,(02):1.[doi:10.13889/j.issn.2095-3631.2017.02.100]
 MENG Lexuan,ZHAO Xin,SAVAGHEBI Mehdi,et al. Hierarchical Control and its Key Technologies for Power Quality Enhancement in Micro-grids[J].High Power Converter Technology,2017,(03):1.[doi:10.13889/j.issn.2095-3631.2017.02.100]

备注/Memo

备注/Memo:
 收稿日期:2018-12-13
作者简介:高群(1979—),男,高级工程师,主要从事信息、通信和电力传输研究工作。
基金项目:国家自然科学基金面上项目(61473253)
更新日期/Last Update: 2019-05-28