Object localization method based on fusion of visual saliency and superpixels

doi:10.11772/j.issn.1001-9081.2015.01.0215

Abstract

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

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

CLC Number:

TP391.413

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.

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.

References

[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.