一種基于圖的流形排序的顯著性目標(biāo)檢測(cè)改進(jìn)方法

呂建勇; 唐振民

doi:10.11999/JEIT150619

一種基于圖的流形排序的顯著性目標(biāo)檢測(cè)改進(jìn)方法

doi: 10.11999/JEIT150619 cstr: 32379.14.JEIT150619

呂建勇¹,
唐振民¹

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61473154)

計(jì)量
- 文章訪問數(shù): 1763
- HTML全文瀏覽量: 177
- PDF下載量: 1271
- 被引次數(shù): 0
出版歷程
- 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: 該文針對(duì)現(xiàn)有的基于圖的流形排序的顯著性目標(biāo)檢測(cè)方法中僅使用k-正則圖刻畫各個(gè)節(jié)點(diǎn)的空間連接性的不足以及先驗(yàn)背景假設(shè)過于理想化的缺陷，提出一種改進(jìn)的方法，旨在保持高查全率的同時(shí)，提高準(zhǔn)確率。在構(gòu)造圖模型時(shí)，先采用仿射傳播聚類將各超像素(節(jié)點(diǎn))自適應(yīng)地劃分為不同的顏色類，在傳統(tǒng)的k-正則圖的基礎(chǔ)上，將屬于同一顏色類且空間上位于同一連通區(qū)域的各個(gè)節(jié)點(diǎn)也連接在一起；而在選取背景種子點(diǎn)時(shí)，根據(jù)邊界連接性賦予位于圖像邊界的超像素不同的背景權(quán)重，采用圖割方法篩選出真正的背景種子點(diǎn)；最后，采用經(jīng)典的流形排序算法計(jì)算顯著性。在常用的MSRA-1000和復(fù)雜的SOD數(shù)據(jù)庫(kù)上同7種流行算法的4種量化評(píng)價(jià)指標(biāo)的實(shí)驗(yàn)對(duì)比證明了所提改進(jìn)算法的有效性和優(yōu)越性。
- 顯著性目標(biāo)檢測(cè) /
- 改進(jìn)的圖模型 /
- 流形排序 /
- 邊界連接性 /
- 連通區(qū)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

參考文獻(xiàn)(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.

姜維, 盧朝陽(yáng), 李靜, 等. 基于視覺顯著性和提升框架的場(chǎng)景文字背景抑制方法[J]. 電子與信息學(xué)報(bào), 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.

錢生, 陳宗海, 林名強(qiáng), 等. 基于條件隨機(jī)場(chǎng)和圖像分割的顯著性檢測(cè)[J]. 自動(dòng)化學(xué)報(bào), 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.

蔣寓文, 譚樂怡, 王守覺. 選擇性背景優(yōu)先的顯著性檢測(cè)模型[J]. 電子與信息學(xué)報(bào), 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. 利用層次先驗(yàn)估計(jì)的顯著性目標(biāo)檢測(cè)[J]. 自動(dòng)化學(xué)報(bào), 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.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)