一种基于图的流形排序的显著性目标检测改进方法

吕建勇; 唐振民

doi:10.11999/JEIT150619

一种基于图的流形排序的显著性目标检测改进方法

doi: 10.11999/JEIT150619

吕建勇¹,
唐振民¹

基金项目:

国家自然科学基金(61473154)

计量
- 文章访问数: 1700
- HTML全文浏览量: 159
- PDF下载量: 1268
- 被引次数: 0
出版历程
- 收稿日期: 2015-05-25
- 修回日期: 2015-08-13
- 刊出日期: 2015-11-19

An Improved Graph-based Manifold Ranking for Salient Object Detection

Lü Jian-yong¹,
Tang Zhen-min¹

Funds:

The National Natural Science Foundation of China (61473154)

摘要

摘要: 该文针对现有的基于图的流形排序的显著性目标检测方法中仅使用k-正则图刻画各个节点的空间连接性的不足以及先验背景假设过于理想化的缺陷，提出一种改进的方法，旨在保持高查全率的同时，提高准确率。在构造图模型时，先采用仿射传播聚类将各超像素(节点)自适应地划分为不同的颜色类，在传统的k-正则图的基础上，将属于同一颜色类且空间上位于同一连通区域的各个节点也连接在一起；而在选取背景种子点时，根据边界连接性赋予位于图像边界的超像素不同的背景权重，采用图割方法筛选出真正的背景种子点；最后，采用经典的流形排序算法计算显著性。在常用的MSRA-1000和复杂的SOD数据库上同7种流行算法的4种量化评价指标的实验对比证明了所提改进算法的有效性和优越性。
- 显著性目标检测 /
- 改进的图模型 /
- 流形排序 /
- 边界连接性 /
- 连通区域
Abstract: To overcome the shortage that the spatial connectivity of every node is modeled only via the k-regular graph and the idealistic prior background assumption is used in existing salient object detection method based on graph-based manifold ranking, an improved method is proposed to increase the precision while preserving the high recall. When constructing the graph model, the affinity propagation clustering is utilized to aggregate the superpixels (nodes) to different color clusters adaptively. Then, based on the traditional k-regular graph, the nodes belonging to the same cluster and located in the same spatial connected region are connected with edges. According to the boundary connectivity, the superpixels along the image boundaries are assigned with different background weights. Then, the real background seeds are selected by graph cuts method. Finally, the classical manifold ranking method is employed to compute saliency. The experimental comparison results of 4 quantitative evaluation indicators between the proposed and 7 state-of-the-art methods on MSRA-1000 and complex SOD datasets demonstrate the effectiveness and superiority of the proposed improved method.
- Salient object detection /
- Improved graph model /
- Manifold ranking /
- Boundary connectivity /
- Connected region

HTML全文

参考文献(29)

Li W T, Chang H S, Lien K C, et al.. Exploring visual and motion saliency for automatic video object extraction[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2600-2610.

Chen D Y and Luo Y S. Preserving motion-tolerant contextual visual saliency for video resizing[J]. IEEE Transactions on Multimedia, 2013, 15(7): 1616-1627.

姜维, 卢朝阳, 李静, 等. 基于视觉显著性和提升框架的场景文字背景抑制方法[J]. 电子与信息学报, 2014, 36(3): 617-623.

Jiang Wei, Lu Chao-yang, Li Jing, et al.. Visual saliency and boosting based background suppression for scene text[J]. Journal of Electronics Information Technology, 2014, 36(3): 617-623.

Borji A and Itti L. State-of-the-art in visual attention modeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 185-207.

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.

钱生, 陈宗海, 林名强, 等. 基于条件随机场和图像分割的显著性检测[J]. 自动化学报, 2015, 41(4): 711-724.

Qian Sheng, Chen Zong-hai, Lin Ming-qiang, et al.. Saliency detection based on conditional random field and image segmentation[J]. Acta Automatica Sinica, 2015, 41(4): 711-724.

Borji A, Sihite D N, and Itti L. Quantitative analysis of human-model agreement in visual saliency modeling: a comparative study[J]. IEEE Transactions on Image Processing, 2013, 22(1): 55-69.

Borji A, Sihite D N, and Itti L. Salient object detection: a benchmark[C]. Proceedings of the European Conference on Computer Vision, Florence, 2012: 414-429.

Achanta R, Estrada F, Wils P, et al.. Salient region detection and segmentation[C]. Proceedings of the International Conference on Computer Vision Systems, Heraklion, 2008: 66-75.

Achanta R, Hemami S, Estrada F, et al.. Frequency-tuned salient region detection[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Miami, 2009: 1597-1604.

Cheng M M, Zhang G X, Mitra N J, et al.. Global contrast based salient region detection[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Providence, 2011: 409-416.

Goferman S, Zelnik-Manor L, and Tal A. Context-aware saliency detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10): 1915-1926.

Jiang H, Wang J, Yuan Z, et al.. Automatic salient object segmentation based on context and shape prior[C]. Proceedings of the British Machine Vision Conference, Dundee, 2011: 110.1-110.12.

Cheng M M, Jonathan W, Lin W Y, et al.. Efficient salient region detection with soft image abstraction[C]. Proceedings of the IEEE International Conference on Computer Vision, Sydney, 2013: 1529-1536.

Xie Y L, Lu H C, and Yang M H. Bayesian saliency via low and mid level cues[J]. IEEE Transactions on Image Processing, 2013, 22(5): 1689-1698.

Wei Y C, Wen F, Zhu W J, et al.. Geodesic saliency using background priors[C]. Proceedings of the European Conference on Computer Vision, Florence, 2012: 29-42.

Zhu W J, Liang S, Wei Y C, et al.. Saliency optimization from robust background detection[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014: 2814-2821.

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.

Jiang Yu-wen, Tan Le-yi, and Wang Shou-jue. Saliency detected model based on selective edges prior[J]. Journal of Electronics Information Technology, 2015, 37(1): 130-136.

徐威, 唐振民. 利用层次先验估计的显著性目标检测[J]. 自动化学报, 2015, 41(4): 799-812.

Xu Wei and Tang Zhen-min. Exploiting hierarchical prior estimation for salient object detection[J]. Acta Automatica Sinica, 2015, 41(4): 799-812.

Jiang B W, Zhang L H, Lu H C, et al.. Saliency detection via absorbing markov chain[C]. Proceedings of the IEEE International Conference on Computer Vision, Sydney, 2013: 1665-1672.

Yang C, Zhang L H, Lu H C, et al.. Saliency detection via graph-based manifold ranking[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Portland, 2013: 3166-3173.

Cheng X, Du P, Guo J, et al.. Ranking on data manifold with sink points[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(1): 177-191.

Achanta R, Shaji A, Smith K, et al.. SLIC superpixles compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.

Frey B J and Dueck D. Clustering by passing message between data points[J]. Science, 2007, 315(5814): 972-976.

Boykov Y and Jolly M P. Interactive graph cuts for optimal boundary region segmentation of objects in N-D images[C]. Proceedings of the IEEE International Conference on Computer Vision, Vancouver, 2001: 105-112.

施引文献

资源附件(0)

访问统计