基于视觉显著性和超像素融合的物体定位方法

doi:10.11772/j.issn.1001-9081.2015.01.0215

计算机应用 ›› 2015, Vol. 35 ›› Issue (1): 215-219.DOI: 10.11772/j.issn.1001-9081.2015.01.0215

基于视觉显著性和超像素融合的物体定位方法

邵明正, 齐剑锋, 王希武, 王路

军械工程学院信息工程系, 石家庄050003

收稿日期:2014-07-31 修回日期:2014-09-19 出版日期:2015-01-01 发布日期:2015-01-26
通讯作者: 邵明正
作者简介:邵明正(1986-),男,山东济宁人,硕士研究生,主要研究方向:计算机视觉、图像处理;齐剑锋(1969-),男,河北石家庄人,副教授,博士,主要研究方向:机器学习、计算机视觉;王希武(1966-),男,河北衡水人,副教授,博士,主要研究方向:数据挖掘.

Object localization method based on fusion of visual saliency and superpixels

SHAO Mingzheng, QI Jianfeng, WANG Xiwu, WANG Lu

Information Engineering Department, Ordnance Engineering College, Shijiazhuang Hebei 050003, China

Received:2014-07-31 Revised:2014-09-19 Online:2015-01-01 Published:2015-01-26

摘要/Abstract

摘要：

针对选择性搜索算法所需定位窗口数量过多的问题,提出了一种基于视觉显著性和超像素融合的改进方法.首先,利用视觉显著性图像粗略估计物体的位置;然后,从这些初始位置开始,根据图像的表观特征融合相邻超像素,并引入一种背景分析方法以避免过度融合;最后,利用贪心算法将融合后的区域再进行组合,并生成最终的定位窗口.在Pascal VOC 2007数据集上的实验结果表明,与选择性搜索方法相比,在同样的检测标准下(查全率为0.91),改进后的方法所使用的窗口数量减少了20%,而重叠率达到了0.77.该方法由粗到细地进行物体定位,在定位窗口数量较少的情况下仍能保持较高的重叠率和查全率.

关键词: 物体定位, 视觉显著性, 超像素, 滑动窗口, 物体识别

Abstract:

Considering the weakness of the selective search method that needs a large number of windows to localize objects, a novel object localization method based on fusion of visual saliency and superpixels was proposed in this paper. Firstly, the visual saliency map was used to coarsely localize the objects, and then the adjacent superpixels could be merged according to the appearance features of image, starting from the above coarse positions. Furthermore, the method employed a simple background detector to avoid the over-merge. Finally, a greedy algorithm was used to iteratively combine the merged regions and generate the final bounding boxes. The experimental results on Pascal VOC 2007 show that the proposed method leads to a 20% reduction in the number of the bounding boxes on the same detection rate (recall of 0.91) compared to the selective search algorithm, and its overlap rate reaches 0.77. The presented method can keep higher overlap rate and recall scores with fewer windows because of its coarse-to-fine process.

Key words: object localization, visual saliency, superpixel, sliding window, object recognition

中图分类号:

TP391.413

邵明正, 齐剑锋, 王希武, 王路. 基于视觉显著性和超像素融合的物体定位方法[J]. 计算机应用, 2015, 35(1): 215-219.

SHAO Mingzheng, QI Jianfeng, WANG Xiwu, WANG Lu. Object localization method based on fusion of visual saliency and superpixels[J]. Journal of Computer Applications, 2015, 35(1): 215-219.

参考文献

[1] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]// Proceedings of the 18th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005: 886-893.
[2] FELZENSZWALB P F, GIRSHICK R B, McALLESTER D, et al. Object detection with discriminatively trained part based models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[3] ZHU L, CHEN Y, YUILLE A, et al. Latent hierarchical structural learning for object detection [C]// Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 1062-1069.
[4] van de SANDE K E A, UIJLINGS J R R, GEVERS T, et al. Segmentation as selective search for object recognition [C]// Proceedings of the 13rd IEEE International Conference on Computer Vision. Piscataway: IEEE, 2011: 1879-1886.
[5] WANG X, YANG M, ZHU S, et al. Regionlets for generic object detection [C]// Proceedings of the 14th IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 17-24.
[6] LAMPERT C H, BLASCHKO M B, HOFMANN T. Efficient subwindow search: a branch and bound framework for object localization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2129-2142.
[7] ALEXE B, DESELAERS T, FERRARI V. Measuring the object-ness of image windows [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2189-2202.
[8] VEDALDI A, GULSHAN V, VARMA M, et al. Multiple kernels for object detection [C]// Proceedings of the 12nd IEEE International Conference on Computer Vision. Piscataway: IEEE, 2009: 606-613.
[9] ENDRES I, HOIEM D. Category independent object proposals [C]// Proceeding of the 11st European Conference on Computer Vision, LNCS 6315. Berlin: Springer, 2010: 575-588.
[10] ARBELAEZ P, MAIRE M, FOWLKES C, et al. Contour detection and hierarchical image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898-916.
[11] CARREIRA J, SMINCHISESCU C. Constrained parametric min-cuts for automatic object segmentation [C]// Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 3241-3248.
[12] YAN Q, XU L, SHI J, et al. Hierarchical saliency detection [C]// Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2013: 1155-1162.
[13] ZHANG J, SCLAROFF S. Saliency detection: a boolean map approach [C]// Proceedings of the 14th IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 153-160.
[14] FULKERSON B, VEDALDI A, SOATTO S. Class segmentation and object localization with superpixel neighborhoods [C]// Proceedings of the 12nd IEEE International Conference on Computer Vision. Piscataway: IEEE, 2009: 670-677.
[15] WANG C, CHEN J, LI W. Superpixel segmentation algorithms review [J]. Application Research of Computers, 2014, 31(1): 6-12.(王春瑶,陈俊周,李炜.超像素分割算法研究综述[J].计算机应用研究,2014,31(1):6-12.)
[16] FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation [J]. International Journal of Computer Vision, 2004, 59(2): 167-181.
[17] SHI J, MALIK J. Normalized cuts and image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.
[18] ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[19] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

基于视觉显著性和超像素融合的物体定位方法

Object localization method based on fusion of visual saliency and superpixels

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	景兴红, 孙国栋, 何世彪, 廖勇. 基于滑窗滤波和多项式拟合的时变信道估计方法[J]. 计算机应用, 2021, 41(9): 2699-2704.
[2]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[3]	刘双元, 郑王里, 林云汉. 面向三维特征描述子的自适应二进制简化方法[J]. 计算机应用, 2021, 41(7): 2062-2069.
[4]	韩艳茹, 尹梦晓, 覃子轩, 苏鹏, 杨锋. 图像和视频的低多边形渲染[J]. 计算机应用, 2021, 41(2): 504-510.
[5]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[6]	仇媛, 常相茂, 仇倩, 彭程, 苏善婷. 基于长短期记忆网络和滑动窗口的流数据异常检测方法[J]. 计算机应用, 2020, 40(5): 1335-1339.
[7]	王一婷, 张柯, 李捷, 郝宗波, 段昶, 朱策. 同一场景下超大尺度差异物体的识别和定位方法[J]. 计算机应用, 2020, 40(12): 3520-3525.
[8]	王书朋, 赵瑶. 基于自适应分割的多曝光图像融合算法[J]. 计算机应用, 2020, 40(1): 252-257.
[9]	杨世强, 罗晓宇, 乔丹, 柳培蕾, 李德信. 基于滑动窗口和动态规划的连续动作分割与识别[J]. 计算机应用, 2019, 39(2): 348-353.
[10]	李登刚, 陈香香, 李华丽, 王忠美. 基于超像素的流形正则化稀疏约束NMF混合像元分解算法[J]. 计算机应用, 2019, 39(10): 3100-3106.
[11]	刘张虎, 程春玲. 面向大规模数据主题建模的方差减小的随机变分推理算法[J]. 计算机应用, 2018, 38(6): 1675-1681.
[12]	王家润, 任菲, 荣明, 罗童心. 拟合复杂形状主骨架的颜色渐变填充[J]. 计算机应用, 2018, 38(3): 829-835.
[13]	丁飞飞, 杨文元. 信息熵约束下的视频目标分割[J]. 计算机应用, 2018, 38(10): 2782-2787.
[14]	刘宇, 金伟正, 范赐恩, 邹炼. 使用超像素分割与图割的网状遮挡物检测算法[J]. 计算机应用, 2018, 38(1): 238-245.
[15]	李雪君, 张开华, 宋慧慧. 融合时空多特征表示的无监督视频分割算法[J]. 计算机应用, 2017, 37(11): 3134-3138.