基于KL散度及多尺度融合的显著性区域检测算法

罗会兰; 万成涛; 孔繁胜

doi:10.11999/JEIT151145

基于KL散度及多尺度融合的显著性区域检测算法

doi: 10.11999/JEIT151145

1.
(江西理工大学信息工程学院赣州 341000) ②(浙江大学计算机科学技术学院杭州 310027)

基金项目:

国家自然科学基金(61105042, 61462035)，江西省青年科学家培养项目(20153BCB23010)

计量
- 文章访问数: 1545
- HTML全文浏览量: 209
- PDF下载量: 513
- 被引次数: 0
出版历程
- 收稿日期: 2015-10-13
- 修回日期: 2016-03-15
- 刊出日期: 2016-07-19

Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging

1.
(School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China)
2.
(College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China)

Funds:

The National Natural Science Foundation of China (61105042, 61462035), The Young Scientist Training Project of Jiangxi Province (20153BCB23010)

摘要

摘要: 基于对超像素颜色概率分布间KL散度的计算，以及对多尺度显著图的融合处理，该文提出一种新的显著性区域检测算法。首先，采用超像素算法多尺度分割图像，在各尺度下用分割产生的超像素为节点，并依据超像素分割数量对各超像素进行适当邻接连通扩展，构建无向扩展闭环连通图。其次，依据颜色判别力聚类量化各超像素内颜色，统计颜色聚类标签的概率分布，用概率分布间KL散度的调和平均值为扩展闭环连通图的边加权，再依据区域对比度并结合边界连通性，获取各尺度下的显著图。最后，平均融合各尺度下显著图，并进行优化处理，得到最终的显著图。在一些大型参考数据集上进行大量实验表明，所提算法优于当前一些先进算法，具有较高精确度和召回率，并且可以产生平滑显著图。
- 显著性区域检测 /
- 多尺度融合 /
- KL散度 /
- 闭环连通图
Abstract: A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop connected graph is constructed, in which nodes are the super-pixels and the adjacent regions are expanded reasonably relying on the total number of super-pixels. Then, all the color values in each super-pixel are clustered in terms of their discriminative power to get the statistical probability distribution of the cluster labels for each super-pixel. Next, the edges between all adjacent super-pixel pairs are weighted with the harmonic-mean of KL divergence of their probability distributions, and then the multi-scale saliency maps are calculated according to boundary connectivity and region contrast. The final saliency map is obtained by calculating and optimizing the mean map of all the saliency maps with different scales. Experimental results on some large benchmark datasets demonstrate that the proposed algorithm outperforms some state-of-the-art methods, and has higher precision and recall rates. The proposed algorithm can also produce smooth saliency maps.
- Salient region detection /
- Multi-scale merging /
- KL divergence /
- Close-loop connected graph

HTML全文

参考文献(25)

ITTI L, KOCH C, and NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

YANG J and YANG M H. Top-down visual saliency via joint CRF and dictionary learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2012: 2296-2303.

TONG N, LU H, RUAN X, et al. Salient object detection via bootstrap learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015: 1884-1892.

ZHAO R, OUYANG W, LI H, et al. Saliency detection by multi-context deep learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015: 1265-1274.

YAN Q, XU L, SHI J, et al. Hierarchical saliency detection [C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013: 1155-1162.

ZHU W, LIANG S, WEI Y, et al. Saliency optimization from robust background detection[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014: 2814-2821.

YANG C, ZHANG L, LU H, et al. Saliency detection via graph-based manifold ranking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 3166-3173.

TONG N, LU H, ZHANG Y, et al. Salient object detection via global and local cues[J]. Pattern Recognition, 2015, 48(10): 3258-3267.

KIM J, HAN D, TAI Y W, et al. Salient region detection via high-dimensional color transform[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014: 883-890.

ACHANTA R, ESTRADA F, WILS P, et al. Salient region detection and segmentation[C]. International Conference on Computer Vision Systems, Heraklion, 2008: 66-75.

CHENG M M, ZHANG G X, MITRA N J, et al. Global contrast based salient region detection[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Colorado Springs, 2011: 409-416.

PERAZZI F, KRAHENBUHL P, PRITCH Y, et al. Saliency filters: Contrast based filtering for salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 733-740.

HOU X and ZHANG L. Saliency detection: A spectral residual approach[C]. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, 2007: 1-8.

ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency- tuned salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009: 1597-1604.

吕建勇, 唐振民. 一种基于图的流形排序的显著性目标检测改进方法[J]. 电子与信息学报, 2015, 37(11): 2555-2563. doi: 10.11999/JEIT150619.

Jianyong and TANG Zhenmin. An improved graph-based manifold ranking for salient object detection[J]. Journal of Electronics Information Technology, 2015, 37(11): 2555-2563. doi: 10.11999/JEIT150619.

WEI Y, WEN F, ZHU W, et al. Geodesic saliency using background priors[C]. Proceedings of the 12th European Conference on Computer Vision, Firenze, Italy, 2012: 29-42.

蒋寓文, 谭乐怡, 王守觉. 选择性背景优先的显著性检测模型 [J]. 电子与信息学报, 2015, 37(1): 130-136. doi: 10.11999/ JEIT140119.

JIANG Yuwen, TAN Leyi, and WANG Shoujue. Saliency detected model based on selective edges prior[J]. Journal of Electronics Information Technology, 2015, 37(1): 130-136. doi: 10.11999/JEIT140119.

WANG J, LU H, LI X, et al. Saliency detection via background and foreground seed selection[J]. Neurocomputing, 2015, 152(C): 359-368.

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.

KHAN R, VAN DE WEIJER J, KHAN F S, et al. Discriminative color descriptors[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 2866-2873.

JOHNSON D B. Efficient algorithms for shortest paths in sparse networks[J]. Journal of the ACM (JACM), 1977, 24(1): 1-13.

OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems Man Cybernetics, 1979, 9(1): 62-66.

HE K, SUN J, and TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.

施引文献

资源附件(0)

访问统计