基于魯棒前景選擇的顯著性檢測

王晨; 樊養(yǎng)余; 李波

doi:10.11999/JEIT170390

基于魯棒前景選擇的顯著性檢測

doi: 10.11999/JEIT170390

2.
(西北工業(yè)大學(xué)電子信息學(xué)院西安 710072) ②(空軍工程大學(xué)航空航天工程學(xué)院西安 710038)

基金項目:

國家自然科學(xué)基金(61379104)

計量
- 文章訪問數(shù): 1129
- HTML全文瀏覽量: 133
- PDF下載量: 292
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-04-26
- 修回日期: 2017-07-17
- 刊出日期: 2017-11-19

Saliency Detection Based on Robust Foreground Selection

2.
(School of Electronics &

Funds:

The National Natural Science Foundation of China (61379104)

摘要

摘要: 顯著性檢測是指自動提取未知場景中符合人類視覺習(xí)慣的興趣目標(biāo)的方法。為了進一步提高檢測的準(zhǔn)確性，該文提出了利用魯棒前景種子的流形排序進行顯著性檢測的算法。首先利用角點檢測和邊緣連接算法得到兩個不同的凸包，用它們的交集初步確立目標(biāo)區(qū)域的大致位置；然后利用凸包外邊緣作為標(biāo)準(zhǔn)對凸包內(nèi)的超像素進行相似度檢測，將與大部分外邊緣相似的超像素去除，得到更準(zhǔn)確的目標(biāo)樣本作為前景種子；利用錨點圖構(gòu)建新的圖結(jié)構(gòu)表示數(shù)據(jù)節(jié)點之間的關(guān)系；接著通過基于前景和背景種子的流形排序算法對圖像所有區(qū)域進行排序，并得到兩種不同的顯著性檢測圖；最后借助代價函數(shù)對顯著性圖進行優(yōu)化，得到最終的顯著性檢測結(jié)果。經(jīng)實驗表明，與幾種經(jīng)典算法對比，該文方法可以進一步提高顯著性算法的精確度和召回率。
- 顯著性檢測 /
- 凸包 /
- 錨點圖 /
- 流形排序
Abstract: Saliency detection is to find the most important object automatically according to the human visual in the unknown scene. For improving the precision of saliency detection, the saliency detection based on robust foreground seeds via manifold ranking is proposed in this paper. Firstly, the two different convex hulls are got by the Harris corner and boundary connectivity algorithm. And the original object region is defined by the intersection about the above convex hulls. Secondly, the superpixels in convex hull are done the similarity detection with the outer edge of the convex hull. The superpixels are removed when they are similar to most of the outer edge, and the more precision foreground seeds are got. Using the anchor graph, a novel graph construction is built to express the relationship between data nodes. And then, two different kinds of salient results will be got based on ranking on manifolds using foreground and background seeds respectively. Finally, the saliency map is got through optimizing a novel cost function. Experimental results prove that the proposed algorithm improves the performance evaluation of precision and recall rate further.
- Saliency detection /
- Convex hull /
- Anchor graph /
- Manifold ranking

HTML全文

參考文獻(31)

GUO Chuanxin, LI Zhenbo, QIAO Xi, et al. Image segmentation of underwater sea cucumber using grabcut with saliency map[J]. Transaction of the Chinese Society for Agricultural Machinery, 2015, 46(1): 147-152. doi: 10.6041/ j.issn.1000-1298. 2015. S0.025.

郭傳鑫, 李振波, 喬曦, 等. 基于融合顯著圖與GrabCut算法的水下海參圖像分割[J]. 農(nóng)業(yè)機械學(xué)報, 2015, 46(1): 147-152. doi: 10.6041/j.issn.1000-1298.2015.S0.025.

薛夢霞, 彭暉, 劉士榮, 等. 基于視覺顯著性的場景目標(biāo)識別[J]. 控制工程, 2106, 23(5): 687-692. doi: 1671-7848(2016) 05-0687-06.

XUE Mengxia, PENG Hui, LIU Shirong, et al. Scene object recognition based on visual saliency[J]. Control Engineering of China, 2106, 23(5): 687-692. doi: 1671-7848(2016)05-0687- 06.

李然, 李艷靈, 崔子冠, 等. 視覺顯著性導(dǎo)向的圖像壓縮感知測量與重建[J]. 華中科技大學(xué)學(xué)報(自然科學(xué)版), 2016, 44(5): 13-18. doi: 10.13245/j.hust.160503.

LI Ran, LI Yanling, CUI Ziguang, et al. Visual saliency oriented compressive sensing measurement and reconstruction of images[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2016, 44(5): 13-18. doi: 10.13245/j.hust.160503.

趙宏偉, 李清亮, 劉萍萍, 等. 特征點顯著性約束的圖像檢索方法[J]. 吉林大學(xué)學(xué)報(工學(xué)版), 2016, 46(2): 542-548. doi: 10.13229/j.cnki.jdxbgxb20160232.

ZHAO Hongwei, LI Qingliang, LIU Pingping, et al. Feature saliency constraint based image retrieval method[J]. Journal of Jinlin University (Engineering and Technology Edition), 2016, 46(2): 542-548. doi: 10.13229/j.cnki.jdxbgxb20160232.

PERAZZI F, KRAHENBUHUL P, PRITCH Y, et al. Saliency filters: Contrast based filtering for salient region detection[C]. Computer Vision and Pattern Recognition 2012, Providence, USA, 2012: 733-740. doi: 10.1109 /CVPR.2012. 6247743.

WEI Yichen, WEN Fang, ZHU Wangjing, et al. Geodesic saliency using background priors[C]. European Conference on Computer Vision 2012, Firenze, Italy, 2012: 29-42. doi: 10.1007/978-3-642-33712-3_3.

YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking[C]. Computer Vision and Pattern Recognition 2013, Portland, USA, 2013: 3166-3173. doi: 10.1109/CVPR.2013.407.

ZHU Wangjiang, LIANG Shuang, WEI Yiche, et al. Saliency optimization from robust background detection[C]. Computer Vision and Pattern Recognition 2014, Columbus, USA, 2014: 2814-2821. doi: 10.1109/CVPR.2014.360.

LIU Tie, SUN Jian, ZHENG Nanning, et al. Learning to detect a salient object[C]. Computer Vision and Pattern Recognition, 2007, Minneapolis, USA, 2007: 353-367. doi: 10.1109/CVPR.2007.383047.

YANG Jimei and YANG Minghsuan. Top-down visual saliency via joint CRF and dictionary learning[C]. Computer Vision and Pattern Recognition 2012, Providence, USA, 2012: 2296-2303. doi: 10.1109/CVPR.2012.6247940.

GOPALAKRISHNAN V, HU Y, and RAJAN D. Random walks on graphs for salient object detection in images[J]. IEEE Transactions on Image Processing, 2010, 19(12): 3232-3242. doi: 10.1109/TIP.2010.2053940.

呂建勇, 唐振民. 一種基于圖的流形排序的顯著性目標(biāo)檢測改進方法[J]. 電子與信息學(xué)報, 2015, 37(11): 2555-2563. doi: 10.11999/JEIT150619.

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

QI Wei, CHENG Mingming, BORJI Ali, et al. Saliency-Rank: Two-stage manifold ranking for salient object detection[J]. Computational Visual Media, 2015, 1(4): 309-320. doi: 10. 1007/s41095-015-0028y.

XIE Yulin, LU Huchuan, and YANG Minghsuan. Bayesian saliency via low and mid level cues[J]. IEEE Transactions on Image Processing, 2013, 22(5): 1689-1698. doi: 10.1109/TIP. 2012.2216276.

LIU Risheng, CAO Junjie, LIN Zhouchen, et al. Adaptive differential equation learning for visual saliency detection[C]. Computer Vision and Pattern Recognition 2014, Columbus, USA, 2014: 3862-3869. doi: 10.1109/CVPR.2014.494.

林曉, 王燕玲, 朱恒亮, 等. 改進凸包的貝葉斯模型顯著性檢測算法[J]. 計算機輔助設(shè)計與圖形學(xué)學(xué)報, 2017, 29(2): 221-228.

LIN Xiao, WANG Yanling, ZHU Henliang, et al. Saliency detection based on the Bayesian model of improved convex hull[J]. Journal of computer-Aided Design and Computer Graphics, 2017, 29(2): 221-228.

ZHOU D, WESTON J, GRETTON A, et al. Ranking on data manifolds[C]. Neural Information Processing Systems 2003, Vancouver, Canada, 2003: 169-176.

WEIJER J, GEVERS T, and BAGDANOV A. Boosting color saliency in image feature detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(1): 150-156. doi: 10.1109/ TPAMI.2006.3.

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. doi: 10.1109/ TPAMI.2012.120.

LIU Wei, HE Junfeng, and CHANG Shihfu. Large graph construction for scalable semi-supervised learning[C]. The 27th International Conference on Machine Learning, Haifa, 2010: 679-686.

YANG Y, NIE F, XU D, et al. A multimedia retrieval framework basd on semi-supervised ranking and relevance feedback[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 723-742. doi: 10.1109/ TPAMI.2011.170.

YAN Qiong, SHI Jianping, XU Li, et al. Hierarchical image saliency detection on extended CSSD[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(4): 717-729. doi: 10.1109/ TPAMI.2015.2465960.

ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]. Computer Vision and Pattern Recognition 2009, Miami, USA, 2009: 1597-1604. doi: 10.1109 /CVPR.2009.5206596.

CHENG M, ZHANG G X, MITRA N J, et al. Global contrast based salient region detection[C]. Computer Vision and Pattern Recognition 2011, Colorado, 2011: 409-416. doi: 10.1109/CVPR.2011.5995344.

YAN Q, XU L, SHI J, et al. Hierarchical saliency detection[C]. Computer Vision and Pattern Recognition 2013, Portland, USA, 2013: 1155-1162. doi: 10.1109 /CVPR.2013.153.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計