Detection of multi-ship targets at sea based on ObjectNess BING

被引：1
|
作者：
Guo S.-J. [1 ,3 ]
Shen T.-S. [2 ]
Xu J. [1 ]
Ma X.-X. [1 ]
机构：
[1] Department of Control Engineering, Navy Aeronautical Engineering University, Yantai
[2] China Defense Science and Technology Information Center, Beijing
[3] Unit 91868 of the PLA, Sanya
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2016年 / 38卷 / 01期
关键词：
Detection of corner points; Model training; Object detection; ObjectNess binarized normed gradients (BING); Ship target at sea;
D O I：
10.3969/j.issn.1001-506X.2016.01.03
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
It is found that generic objects with well-defined closed boundary can be discriminated by looking at the norm of gradients, with a suitable resizing of their corresponding image windows into a small fixes size, which can save a lot of time. Inspired by the high quality of ObjectNess binarized normed gradients (BING), it is used for the multi-ship target detection on the sea. Considering the characteristics of the ship targets and the artificial objects, a method of predicting the object candidate windows based on corner points and ObjectNess BING is proposed, which can also generates a small set of high quality ship target windows, yielding 96.2% object detection rate (DR) just like the former ObjectNess BING dose for the test of images downloaded from the internet, but with only 900+proposals. It reduces the time cost of ship targets detection and makes the ship detection more efficient than the former ObjectNess BING. © 2016, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码：14 / 20
页数：6
相关论文
共 33 条
  • [1] Shi P., Zhuang L.S., Ao H.H., Et al., Ship detection based on human vision perception, Journal of Atmospheric and Environmental Optics, 5, 5, pp. 373-379, (2010)
  • [2] Yang M.Y., Yang W.P., Automatic detection method of IR warship target in the complex sea-sky background, Infraed and Laser Engineering, 28, 10, pp. 580-584, (2006)
  • [3] Huang Y.D., Li J., Fan N.J., Algorithm for locating naval ship on the sea-sky-line, Transactions of Beijing Institute of Technology, 28, 4, pp. 302-305, (2008)
  • [4] Zhang D.X., He S.H., Yang S.Q., Ship targets detection method based on multi-scale fractal feature, Laser & Infrared, 39, 3, pp. 315-318, (2009)
  • [5] Ai S.F., Zhang G.H., Lv G.J., A local entrophy based algorithm for detecting IR target under sea background, Electronic Optics & Control, 15, 7, pp. 75-82, (2008)
  • [6] Zhang F., Wang Y.H., Fast IR ship segmentation guided by salient features detection, Infrared and Laser Engineering, 33, 6, pp. 603-606, (2004)
  • [7] Dalal N., Triggs B., Histograms of oriented gradients for human detection, Proc. of the the 18th IEEE Conference on Computer Vision and Pattern Recognition, pp. 886-893, (2005)
  • [8] Felzenszwalb P.F., Girshick R.B., McAllester D., Et al., Object detection with discriminatively trained part-based models, IEEE Trans. on Pattern Analysis & Machine Intelligence, 32, 9, pp. 1627-1645, (2010)
  • [9] Alexe B., Deselaers T., Ferrari V., Et al., What is an object?, Proc. of the 23th IEEE Conference on Computer Vision and Pattern Recognition, pp. 73-80, (2010)
  • [10] Alexe B., Deselaers T., Ferrari V., Et al., Measuring the objectness of image windows, IEEE Trans. on Pattern Analysis & Machine Intelligence, 34, 11, pp. 2189-2202, (2012)
1234