自適應(yīng)閾值分割與局部背景線索結(jié)合的顯著性檢測

唐紅梅; 吳士婧; 郭迎春; 裴亞男

doi:10.11999/JEIT160984

自適應(yīng)閾值分割與局部背景線索結(jié)合的顯著性檢測

doi: 10.11999/JEIT160984

1.
(河北工業(yè)大學(xué)電子信息工程學(xué)院天津 300401) ②(河北工業(yè)大學(xué)計(jì)算機(jī)科學(xué)與軟件學(xué)院天津 300401)

基金項(xiàng)目:

天津市科技計(jì)劃項(xiàng)目(14RCGFGX00846, 15ZCZDNC 00130)，河北省自然科學(xué)基金面上項(xiàng)目(F2015202239)

計(jì)量
- 文章訪問數(shù): 1300
- HTML全文瀏覽量: 178
- PDF下載量: 432
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-09-29
- 修回日期: 2017-02-16
- 刊出日期: 2017-07-19

Saliency Detection Based on Adaptive Threshold Segmentation and Local Background Clues

1.
(School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China)
2.
(School of Computer Science and Engineering, Hebei University of Technology, Tianjin 300401, China)

Funds:

Tianjin Science and Technology Project (14RCGFGX00846, 15ZCZDNC00130), Project of Natural Science Foundation of Hebei Province (F2015202239)

摘要

摘要: 為了提高顯著性算法對不同類圖像的適用性以及結(jié)果的完整性，該文提出一種基于自適應(yīng)閾值合并的分割過程與新的背景選擇方法相結(jié)合的顯著性檢測算法。在分割過程中，生成相鄰區(qū)塊的RGB以及LAB共六通道融合的顏色差值序列，采用區(qū)塊面積參數(shù)的反比例模型生成自適應(yīng)閾值與顏色差值序列進(jìn)行對比合并。在背景選擇過程中，根據(jù)局部區(qū)域背景-主體-背景的相對位置關(guān)系線索，得到背景區(qū)域，再對結(jié)果進(jìn)行邊緣優(yōu)化。該算法與其它算法相比得到的顯著圖不需要外接其他閾值算法即生成二值圖，自適應(yīng)閾值合并能排除復(fù)雜環(huán)境中的物體細(xì)節(jié)，專注于同等級大小物體的顯著性對比。
- 顯著性檢測 /
- 自適應(yīng)閾值 /
- 相鄰顏色差值 /
- 局部背景線索 /
- 邊緣優(yōu)化
Abstract: In order to improve the applicability for different types of image and integrity of the results, a saliency detection algorithm is proposed. It combines the adaptive threshold merging with a new background selection strategy. In the segmentation process, the color difference sequence is obtained by the selective fusion of RGB and LAB of adjacent blocks. Adaptive threshold is generated by inverse proportion model of block area parameter. Merging progress is done after the adaptive threshold comparison with the color difference sequence. In the background selection process, background regions are obtained by the local relative position of background-subject-background in the local area. The experimental results are optimized for edge. Compared with other algorithms, the saliency map of two values obtained does not need external threshold algorithm in this paper. Adaptive threshold merging can eliminate the details of objects in complex environments and can focus on the saliency comparison of the same level size objects.
- Saliency detection /
- Adaptive threshold /
- Adjacent color difference /
- Local background clues /
- Edge optimization

HTML全文

參考文獻(xiàn)(20)

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.

羅會蘭, 萬成濤, 孔繁勝. 基于 KL散度及多尺度融合的顯著性區(qū)域檢測算法[J]. 電子與信息學(xué)報(bào), 2016, 38(7): 1594-1601. doi: 10.11999/JEIT151145.

LUO Huilan, WAN Chengtao, and KONG Fansheng. Salient region detection algorithm via KL divergence and multi-scale merging[J]. Journal of Electronics Information Technology, 2016, 38(7): 1594-1601. doi: 10.11999/JEIT151145.

WU Pohung, CHEN Chienchi, DING Jianjiun, et al. Salient region detection improved by principle component analysis and boundary information[J]. IEEE Transactions on Image Processing, 2013, 22(9): 3614-3624. doi: 10.1109/TIP.2013. 2266099.

SHETH C and VENKATESH R. Object saliency using a background prior[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Shanghai, China, 2016: 1931-1935. doi: 10.1109/ICASSP.2016.7472013.

LI G B and YU Y Z. Visual saliency based on multiscale deep features[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 5455-5463. doi: 10.1109/CVPR.2015.7299184.

ZHANG Wei, BORJI A, WANG Zhou, et al. The application of visual saliency models in objective image quality assessment: A statistical evaluation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(6): 1266-1278. doi: 10.1109/TNNLS.2015.2461603.

畢篤彥, 庫濤, 查宇飛, 等. 基于顏色屬性直方圖的尺度目標(biāo)跟蹤算法研究[J]. 電子與信息學(xué)報(bào), 2016, 38(5): 1099-1106. doi: 10.11999/JEIT150921.

BI Duyan, KU Tao, ZHA Yufei, et al. Scale-adaptive object tracking based on color names histogram[J].Journal of Electronics Information Technology, 2016, 38(5): 1099-1106. doi: 10.11999/JEIT150921.

XIANG D and ZHONG B J. Scale-space saliency detection in combined color space[C]. Chinese Automation Congress, Wuhan, China, 2015: 726-731. doi: 10.1109/CAC.2015. 7382593.

ACHANTA R, APPU S, 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): 2274-2281. doi: 10.1109/TPAMI.2012.120.

TONG Na, LU Huchuan, ZHANG Lihe, et al. Saliency detection with multi-scale superpixels[J]. IEEE Signal Processing Letters, 2014, 21(9): 1035-1039. doi: 10.1109/LSP. 2014.2323407.

鄭瑞連, 鐘寶江, 徐東升. 基于L曲率的尺度空間形狀分析技術(shù)[J]. 南京大學(xué)學(xué)報(bào), 2012, 48(2): 172-181. doi: 10.13232 /j.cnki.jnju.2012.02.007.

ZHENG Ruilian, ZHONG Baojiang, and XU Dongsheng. Scale space shape analysis technique based on L curvature[J]. Journal of Nanjing University, 2012, 48(2): 172-181. doi: 10.13232/j.cnki.jnju.2012.02.007.

NGUYEN H T, WORRING M, and BOOMGAARD R V D. Watersnakes: Energy-driven watershed segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(3): 330-342. doi: 10.1109/TPAMI.2003. 1182096.

朱玉琨. 結(jié)合局部特征與空間關(guān)系的多物體檢測算法研究[D]. [碩士論文], 上海交通大學(xué), 2014: 3-76.

ZHU Yukun. Research on multi object detection algorithm based on local feature and spatial relation[D]. [Master dissertation], Shanghai Jiao Tong University, 2014: 3-76.

CHENG M M, ZHANG G X, MITRAN J, et al. Global contrast based salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011: 409-416. doi: 10.1109/TPAMI.2014. 2345401.

ZELNIK-MANOR L, TAL A, and MARGOLIN R. What makes a patch distinct?[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013: 1139-1146. doi: 10.1109/CVPR.2013.151.

CHENG M M, WARRELL L, LIN W Y, et al. Efficient salient region detection with soft image abstraction[C]. IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 1529-1536. doi: 10.1109/ICCV.2013.193.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)