-
Advanced Search

Citation: Ye ZHANG, Ting XU, Dingzhong FENG, Meixian JIANG, Guanghua WU. Research on Faster RCNN Object Detection Based on Hard Example Mining[J]. Journal of Electronics and Information Technology, ;2019, 41(6): 1496-1502. doi: 10.11999/JEIT180702 shu

Research on Faster RCNN Object Detection Based on Hard Example Mining

  • Corresponding author: Meixian JIANG, 1056294025@qq.com
  • Received Date: 2018-07-13
    Accepted Date: 2019-01-28
    Available Online: 2019-06-01

Figures(4) / Tables(4)

  • Because of the classic Faster RCNN training proccess with too many difficult training samples and low recall rate problem, a method which combines the techniques of Online Hard Example Mining (OHEM) and Hard Negative Example Mining (HNEM) is adopted, which carries out the error transfer for the difficult samples using its corresponding maximum loss value from real-time filtering. It solves the problem of low detection of hard example and improves the efficiency of the model training. To improve the recall rate and generalization of the model, an improved Non-Maximum Suppression (NMS) algorithm is proposed by setting confidence thresholds penalty function; In addition, multi-scale training and data augmentation are also introduced. Finally, the results before and after improvement are compared: Sensibility experiments show that the algorithm achieves good results in VOC2007 data set and VOC2012 data set, with the mean Average Percision (mAP) increasing from 69.9% to 74.40%, and 70.4% to 79.3% respectively, which demonstrates strongly the superiority of the algorithm.
  • 加载中
    1. [1]

      吕博云. 数字图像处理技术及应用研究[J]. 科技与创新, 2018(2): 146–147. doi: 10.15913/j.cnki.kjycx.2018.02.146
      LÜ Boyun. Research on the technology and application of digital image processing[J]. Science and Technology &Innovation, 2018(2): 146–147. doi: 10.15913/j.cnki.kjycx.2018.02.146

    2. [2]

      王湘新, 时洋, 文梅. CNN卷积计算在移动GPU上的加速研究[J]. 计算机工程与科学, 2018, 40(1): 34–39. doi: 10.3969/j.issn.1007-130X.2018.01.005
      WANG Xiangxin, SHI Yang, and WEN Mei. Accelerating CNN on mobile GPU[J]. Computer Engineering &Science, 2018, 40(1): 34–39. doi: 10.3969/j.issn.1007-130X.2018.01.005

    3. [3]

      胡炎, 单子力, 高峰. 基于Faster-RCNN和多分辨率SAR的海上舰船目标检测[J]. 无线电工程, 2018, 48(2): 96–100. doi: 10.3969/j.issn.1003-3106.2018.02.04
      HU Yan, SHAN Zili, and GAO Feng. Ship detection based on faster-RCNN and multiresolution SAR[J]. Radio Engineering, 2018, 48(2): 96–100. doi: 10.3969/j.issn.1003-3106.2018.02.04

    4. [4]

      GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 580–587. doi: 10.1109/CVPR.2014.81.

    5. [5]

      REN Shaoqing, HE Kaiming, 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. doi: 10.1109/TPAMI.2016.2577031

    6. [6]

      FELZENSZWALB P, MCALLESTER D, and RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]. Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008: 1–8. doi: 10.1109/CVPR.2008.4587597.

    7. [7]

      YAN Junjie, LEI Zhen, WEN Longyin, et al. The fastest deformable part model for object detection[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2497–2504.

    8. [8]

      FORSYTH D. Object detection with discriminatively trained part-based models[J]. Computer, 2014, 47(2): 6–7. doi: 10.1109/MC.2014.42

    9. [9]

      DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005: 886–893. doi: 10.1109/CVPR.2005.177.

    10. [10]

      WANG Xiaoyu, HAN T X, and YAN Shuicheng. An HOG-LBP human detector with partial occlusion handling[C]. Proceedings of 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 2009: 32–39. doi: 10.1109/ICCV.2009.5459207.

    11. [11]

      ERHAN D, SZEGEDY C, TOSHEV A, et al. Scalable object detection using deep neural networks[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2155–2162. doi: 10.1109/CVPR.2014.276.

    12. [12]

      NEUBECK A and VAN GOOL L. Efficient non-maximum suppression[C]. Proceedings of the 18th International Conference on Pattern Recognition, Hongkong, China, 2006: 850–855. doi: 10.1109/ICPR.2006.479.

    13. [13]

      李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012: 18–23.
      LI Hang. Statistical Learning Method[M]. Beijing: Tsinghua University Press, 2012: 18–23.

    14. [14]

      周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 23–35.
      ZHOU Zhihua. Machine Learning[M]. Beijing: Tsinghua University Press, 2016: 23–35.

    15. [15]

      SUN Changming and VALLOTTON P. Fast linear feature detection using multiple directional non-maximum suppression[J]. Journal of Microscopy, 2009, 234(2): 147–157. doi: 10.1111/jmi.2009.234.issue-2

  • 加载中
    1. [1]

      Hao FENGKun HUANGJing LIRong GAODonghua LIUChengfang SONG . Hybrid Point of Interest Recommendation Algorithm Based on Deep Learning. Journal of Electronics and Information Technology, 2019, 41(4): 880-887. doi: 10.11999/JEIT180458

    2. [2]

      Hongyun YANGFengyan WANG . Meteorological Radar Noise Image Semantic Segmentation Method Based on Deep Convolutional Neural Network. Journal of Electronics and Information Technology, 2019, 41(10): 2373-2381. doi: 10.11999/JEIT190098

    3. [3]

      Ye YUANKebin JIAPengyu LIU . Multi-context Autoencoders for Multivariate Medical Signals Based on Deep Convolutional Neural Networks. Journal of Electronics and Information Technology, 2019, 41(0): 1-8. doi: 10.11999/JEIT190135

    4. [4]

      Lun TANGPeipei ZHAOGuofan ZHAOQianbin CHEN . Virtual Network Function Migration Algorithm Based on Deep Belief Network Prediction of Resource Requirements. Journal of Electronics and Information Technology, 2019, 41(6): 1397-1404. doi: 10.11999/JEIT180666

    5. [5]

      Xiang XIELiqiang ZHANGJing WANG . Application of Residual Network to Infant Crying Recognition. Journal of Electronics and Information Technology, 2019, 41(1): 233-239. doi: 10.11999/JEIT180276

    6. [6]

      Haifeng SANGZizhen CHEN . 3D Human Motion Prediction Based on Bi-directionalGated Recurrent Unit. Journal of Electronics and Information Technology, 2019, 41(9): 2256-2263. doi: 10.11999/JEIT180978

    7. [7]

      Hongchang CHENYancheng WUShaomei LIChao GAO . Person Re-identification Based on Attribute Hierarchy Recognition. Journal of Electronics and Information Technology, 2019, 41(9): 2239-2246. doi: 10.11999/JEIT180740

    8. [8]

      Jianwei LIChangwen QUShujuan PENGYuan JIANG . Ship Detection in SAR images Based on Generative Adversarial Network and Online Hard Examples Mining. Journal of Electronics and Information Technology, 2019, 41(1): 143-149. doi: 10.11999/JEIT180050

    9. [9]

      Ronggui WANGMengya HANJuan YANGLixia XUEMin HU . Multi-Level Attention Feature Network for Few-shot Learning. Journal of Electronics and Information Technology, 2019, 41(0): 1-7. doi: 10.11999/JEIT190242

    10. [10]

      Zhengyi LIUTianze XU . RGB-D Saliency Detection Based on Optimized ELM and Depth Level. Journal of Electronics and Information Technology, 2019, 41(9): 2224-2230. doi: 10.11999/JEIT180826

    11. [11]

      Fei WANGShichao WUShaolin LIUYahui ZHANGYing WEI . Driver Fatigue Detection Through Deep Transfer Learning in an Electroencephalogram-based System. Journal of Electronics and Information Technology, 2019, 41(9): 2264-2272. doi: 10.11999/JEIT180900

    12. [12]

      Pengcheng GUOZheng LIUDingli LUOJianpu LI . Range Spread Target Detection Based on OnlineEstimation of Strong Scattering Points. Journal of Electronics and Information Technology, 2019, 41(0): 1-7. doi: 10.11999/JEIT190417

    13. [13]

      Ming YINWenjie WANGXuanyu ZHANGJijiao JIANG . A Maximal Frequent Itemsets Mining Algorithm Based on Adjacency Table. Journal of Electronics and Information Technology, 2019, 41(8): 2009-2016. doi: 10.11999/JEIT180692

    14. [14]

      Zhiqiang HOUShuai WANGXiufeng LIAOWangsheng YUJiaoyao WANGChuanhua CHEN . Adaptive Regularized Correlation Filters for Visual Tracking Based on Sample Quality Estimation. Journal of Electronics and Information Technology, 2019, 41(8): 1983-1991. doi: 10.11999/JEIT180921

    15. [15]

      Juan WANGTong WANGJianxin WU . Iterative Multiple Signal Classification Algorithm with Small Sample Size. Journal of Electronics and Information Technology, 2019, 41(0): 1-7. doi: 10.11999/JEIT190160

    16. [16]

      Yaguan QIANHongbo LUShouling JIWujie ZHOUShuhui WUBensheng YUNXiangxing TAOJingsheng LEI . Adversarial Example Generation Based on Particle Swarm Optimization. Journal of Electronics and Information Technology, 2019, 41(7): 1658-1665. doi: 10.11999/JEIT180777

    17. [17]

      Julong LANChanghe YUYuxiang HUZiyong LI . A SDN Routing Optimization Mechanism Based on Deep Reinforcement Learning. Journal of Electronics and Information Technology, 2019, 41(0): 1-6. doi: 10.11999/JEIT180870

    18. [18]

      Xin WANGKe LIChen NINGFengchen HUANG . Remote Sensing Image Classification Method Based on Deep Convolution Neural Network and Multi-kernel Learning. Journal of Electronics and Information Technology, 2019, 41(5): 1098-1105. doi: 10.11999/JEIT180628

    19. [19]

      Jiaqi WEILei ZHANGHongwei LIUJialian SHENG . A Novel Micro-motion Multi-target Wideband Resolution Algorithm Based on Curve Overlap Extrapolation. Journal of Electronics and Information Technology, 2019, 41(0): 1-7. doi: 10.11999/JEIT190033

    20. [20]

      Zengwei LÜZhenchun WEIJianghong HANRenhao SUNChengkai XIA . A Mobile Charging and Data Collecting Algorithm Based on Multi-objective Optimization. Journal of Electronics and Information Technology, 2019, 41(8): 1877-1884. doi: 10.11999/JEIT180897

Metrics
  • PDF Downloads(25)
  • Abstract views(373)
  • HTML views(161)
  • Cited By(0)

通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

/

DownLoad:  Full-Size Img  PowerPoint
Return