首页 > 论文 > 光学学报 > 38卷 > 9期(pp:915005--1)

基于GN分裂的小目标检测区域推荐搜索算法

An Algorithm of Small Object Detection Region Proposal Search Based on GN Splitting

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

区域推荐搜索是机器视觉研究热点之一,针对传统目标检测使用穷举式搜索效率低下的问题,通过优化搜索的准确率可提高检测效率。引入复杂网络中用于社区发现的Girvan-Newman(GN)分裂算法,结合小目标区域特征,提出一种基于图像网络结构的小目标检测区域推荐搜索算法。该算法根据区域间多样性颜色直方图相似性构建图像与图的映射关系,通过图中连通子图的生成获取小目标可能区域。能在生成较少候选区的情况下满足较高的召回率,进一步优化小目标检测的时间消耗。

Abstract

The region proposal search is one of the most active research topics of machine vision. The low efficiency of object detection using the traditional exhaustive search can be improved by optimizing the accuracy of search algorithm. The Girvan-Newman (GN) splitting for community discovery in complex networks is introduced as well as the features of small object regions. A novel method to generate small object regions is proposed by using the network structure of image. The algorithm constructs the relationship between the images and the graphs based on the similarity of color histograms between regions. It can obtain possible regions through the generation of connected subgraphs. This algorithm can meet the higher recall rate in the case of generating fewer candidate regions and further optimize the time consumption of small object detection.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201838.0915005

所属栏目:机器视觉

基金项目:国家自然科学基金(61671202,61573128)、国家重点研发计划(2016YFC0401606)

收稿日期:2018-04-09

修改稿日期:2018-04-25

网络出版日期:2018-05-02

作者单位    点击查看

赵沛然:河海大学物联网工程学院,江苏 常州 213022
吴新元:河海大学物联网工程学院,江苏 常州 213022
汤新雨:河海大学物联网工程学院,江苏 常州 213022
沈晓海:河海大学物联网工程学院,江苏 常州 213022
许海燕:河海大学物联网工程学院,江苏 常州 213022
李敏:河海大学物联网工程学院,江苏 常州 213022
张学武:河海大学物联网工程学院,江苏 常州 213022

联系人作者:张学武(lab_112@126.com); 赵沛然(zhaopeiran1994@126.com);

【1】Mo S W, Deng X P, Wang S, et al. Moving object detection algorithm based on improved visual background extractor[J]. Acta Optica Sinica, 2016, 36(6): 0615001.
莫邵文, 邓新蒲, 王帅, 等. 基于改进视觉背景提取的运动目标检测算法[J]. 光学学报, 2016, 36(6): 0615001.

【2】Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444.

【3】Xin P, Xu Y L, Tang H, et al. Fast airplane detection based on multi-layer feature fusion of fully convolutional networks[J]. Acta Optica Sinica, 2018, 38(3): 0315003.
辛鹏, 许悦雷, 唐红, 等. 全卷积网络多层特征融合的飞机快速检测[J]. 光学学报, 2018, 38(3): 0315003.

【4】Hosang J, Benenson R, Dollár P, et al. What makes for effective detection proposals?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(4): 814-830.

【5】Viola P, Jones M J, Snow D. Detecting pedestrians using patterns of motion and appearance[C]// IEEE International Conference on Computer Vision, 2003: 734.

【6】Papageorgiou C P, Oren M, Poggio T. A general framework for object detection[C]// IEEE International Conference on Computer Vision, 2002: 555-562.

【7】Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2189-2202.

【8】Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[J]. Computer Science, 2013:580-587.

【9】Sande K E A V D, Uijlings J R R, Gevers T, et al. Segmentation as selective search for object recognition[C]∥IEEE International Conference on Computer Vision, 2012: 1879-1886.

【10】Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]∥International Conference on Neural Information Processing Systems, 2015: 91-99.

【11】Qin J, Wang M H. Fast pedestrian proposal generation algorithm using online Gaussian model[J]. Acta Optica Sinica, 2016, 36(11): 1115001.
覃剑, 王美华. 采用在线高斯模型的行人检测候选框快速生成方法[J]. 光学学报, 2016, 36(11): 1115001.

【12】Cheng M M, Zhang Z M, Lin W Y, et al. BING: binarized normed gradients for objectness estimation at 300 fps[C]// IEEE Computer Vision and Pattern Recognition, 2014: 3286-3293.

【13】Zitnick C L, Dollár P. Edge boxes: locating object proposals from edges[M]. Chambridge: Springer International Publishing, 2014, 8693: 391-405.

【14】Ellis W D. A source book of gestalt psychology[M].Michigan: Humanities Press, Psychological Bulletin, 1939, 36(1): 40-43.

【15】Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004, 59(2): 167-181.

【16】He Q Y, Li Z L, Wang X Z, et al. Automated retinal layer segmentation based on optical coherence tomographic images[J]. Acta Optica Sinica, 2016, 36(10): 1011003.
贺琪欲,李中梁,王向朝,等. 基于光学相干层析成像的视网膜图像自动分层方法[J]. 光学学报, 2016, 36(10): 1011003.

【17】Newman M E J, Girvan M. Finding and evaluating community structure in networks[J]. Physical Review E, 2004, 69(2): 026113.

【18】Wang X F. Complex network theory application[M]. Beijing: Tsinghua University Press, 2006.
汪小帆. 复杂网络理论及其应用[M]. 北京:清华大学出版社,2006.

【19】Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking[C]// DBLP Computer Vision – ECCV 2008, 2008: 705-718.

【20】Cheng Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.

【21】Sheikh Y A, Khan E A, Kanade T. Mode-seeking by medoidshifts[C]// IEEE International Conference on Computer Vision, 2007: 1-8.

【22】Wang Q W. Study on image histogram feature and application[D]. Hefei: University of Science and Technology of China, 2014.
汪启伟. 图像直方图特征及其应用研究[D]. 合肥:中国科学技术大学,2014.

引用该论文

Zhao Peiran,Wu Xinyuan,Tang Xinyu,Shen Xiaohai,Xu Haiyan,Li Min,Zhang Xuewu. An Algorithm of Small Object Detection Region Proposal Search Based on GN Splitting[J]. Acta Optica Sinica, 2018, 38(9): 0915005

赵沛然,吴新元,汤新雨,沈晓海,许海燕,李敏,张学武. 基于GN分裂的小目标检测区域推荐搜索算法[J]. 光学学报, 2018, 38(9): 0915005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF