《计算机应用研究》|Application Research of Computers

一种基于边缘图像的快速物体检测方法

Fast object detection method based on edge image

免费全文下载 (已被下载 次)  
获取PDF全文
作者 买桂英,林娜,魏霖静
机构 1.甘肃民族师范学院 计算机科学系,甘肃 合作 747000;2.河南工业贸易职业学院 信息工程学院,郑州 451191;3.甘肃农业大学 信息科学技术学院,兰州 730070
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2525-03
DOI 10.3969/j.issn.1001-3695.2017.08.064
摘要 为提高物体检测速度,提出一种利用边缘快速检测物体的方法。首先,求取图像中每一个像素的边缘模值和方向,依据模值定位边缘位置,依据位置和方向进行边缘分组;然后,通过计算边缘组的相似度来对候选的包围盒进行投票;最后,统计多尺度滑动窗口上各候选包围盒的投票得分,依据包围盒得分对包围盒进行过滤,再依据包围盒重合度对包围盒进行合并,并依据合并的包围盒数量判断其是否为物体,最终得到图像中各物体的包围盒。实验结果表明,相对于目前最新的物体检测算法,该方法的运算效率较高,且检索率和精确度高。
关键词 物体检测;边缘模值;边缘方向;包围盒;得分;滑动窗
基金项目 国家自然科学基金资助项目(U1404602)
甘肃省教育厅资助项目(2014A-115)
本文URL http://www.arocmag.com/article/01-2017-08-064.html
英文标题 Fast object detection method based on edge image
作者英文名 Mai Guiying, Lin Na, Wei Linjing
机构英文名 1.Dept.ofComputerScience,GansuNomalUniversityforNationalities,HezuoGansu747000,China;2.Dept.ofInformationEngineering,HenanIndustry&TradeVocationalCollege,Zhengzhou451191,China;3.SchoolofInformationScience&Technology,GansuAgricultureUniversity,Lanzhou730070,China
英文摘要 For improving the speed of object detection, this paper proposed an object detection method by using edge. First, it computed the edge magnitude and orientation for every pixel in the image, located the edge position according to magnitude, and divided the edges into different groups according to edge position and orientation. Second, it voted for candidate bounding box by computing the similarity among edge groups. Finally, it calculated the voting scores of each candidate bounding box among multi-scale sliding windows, filterd the bounding boxes according to their scores, combined them according to their overlap ratio, distinguished an object according the number of combined bounding boxes, and obtained each object’s bounding box in the image. Experimental results show that, comparing with main methods based on bounding box, this method has the higher computation efficiency, and the recall ratio and precision are high.
英文关键词 object detection; edge magnitude; edge orientation; bounding box; scoring; sliding windows
参考文献 查看稿件参考文献
  [1] 黄凯奇, 任伟强, 谭铁牛. 图像物体分类与检测算法综述[J] . 计算机学报, 2014, 6(6):1225-1240.
[2] Mehmood S, Cagnoni S, Mordonini M, et al. An embedded architecture for real-time object detection in digital images based on niching particle swarm optimization[J] . Journal of Real-Time Image Proces-sing, 2015, 10(1):75-89.
[3] Rani P I, Muneeswaran K. Robust real time face detection automatically from video sequence based on Haar features[C] //Proc of International Conference on Communication and Network Technologies. 2014:276-280.
[4] Hsu R L, Abdel-Mottaleb M, Jain A K. Face detection in color images[J] . IEEE Trans on Pattern Analysis & Machine Intelligence, 2002, 1(5):696-706.
[5] Li Haoxiang, Lin Zhe, Brandt J, et al. Efficient boosted exemplar-based face detection[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. 2014:1843-1850.
[6] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. 2005:886-893.
[7] Ko B C, Kim D Y, Jung J H, et al. Three-level cascade of random fo-rests for rapid human detection[J] . Optical Engineering, 2013, 52(2):027204-027204.
[8] Paul M, Haque S M E, Chakraborty S. Human detection in surveillance videos and its applications:a review[J] . Eurasip Journal on Advances in Signal Processing, 2013, 2013(1):1-16.
[9] 张晖, 董育宁. 基于视频的车辆检测算法综述[J] . 南京邮电大学学报:自然科学版, 2007, 27(3):88-94.
[10] Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J] . IEEE Trans on Pattern Analysis & Machine Intelligence, 2012, 34(11):2189-2202.
[11] Uijlings J R R, Sande K E A V D, Gevers T, et al. Selective search for object recognition[J] . International Journal of Computer Vision, 2013, 104(2):154-171.
[12] Manen S, Guillaumin M, Van Gool L. Prime object proposals with randomized prim′s algorithm[C] //Proc of IEEE International Conference on Computer Vision. 2013:2536-2543.
[13] 章毓晋. 图像分割[M] . 北京:科学出版社, 2001.
[14] Kumar G V S R. Review on image segmentation techniques[J] . Pattern Recognition, 2014, 47(3):992-997.
[15] Perrinet L. Feature detection using spikes:the greedy approach[J] . Journal of Physiology-Paris, 2006, 98(4-6):530-539.
[16] Roth D B G. Adaptive thresholding using the integral image[J] . Journal of Graphics GPU & Game Tools, 2007, 12(2):13-21.
[17] The PASCAL visual object classes challenge[EB/OL] . (2007). http://host. robots. ox. ac. uk/pascal/VOC/voc2007/.
收稿日期 2016/6/6
修回日期 2016/7/11
页码 2525-2527,2532
中图分类号 TP391.41
文献标志码 A