元胞自动机多尺度优化的显著性细微区域检测

针对由于待检测目标局部区域显著性差异过大造成的细微区域检测失败问题, 在贝叶斯理论框架下, 提出一种基于元胞自动机多尺度优化的显著性检测方法。首先结合暗通道先验信息和区域对比度在同一张图片的5个超像素尺度空间内分别构建原始显著性图; 接着, 利用元胞自动机建立动态更新机制, 通过影响因子矩阵和置信度矩阵优化每个元胞下一状态的影响力, 获得对应5个优化显著性图; 最后在基于贝叶斯理论的融合算法框架下得到最终的显著性图。在两个复杂度不同的标准图像数据库上将本文方法与10种主流显著性提取方法进行视觉效果和客观定量数据对比, 结果显示, 本文算法效果优于现有10种显著性提取方法, 其中在公认最具挑战的DUT-OMRON数据库的综合指标F-measure 值为0.631 4, 平均绝对误差(MAE)为0.132 5, ROC曲线下面积(AUC)为0.892 8, 表明本文算法具有较高的准确性和鲁棒性。

Abstract

Aiming at failure detection problems on subtle region caused by saliency differences of detected target in local region, under the framework of Bayesian theory, the author proposed a novel salient region detection method based on cellular automata multi-scale optimization. Firstly, the prior information about dark channel was integrated with regional contrast to separately construct original salient maps in five superpixel scale spaces on the same picture; and then the cellular automata was used to establish a dynamic updating mechanism and impact factor matrix and confidence matrix were applied to optimize influences of each cellular in next state. As a result, the saliency values of all cells will be renovated simultaneously according to the proposed updating rule, and five optimized salient maps were obtained; finally, under the framework of fusion algorithm in Bayesian theory, the final saliency map was obtained. The experiment on two standard image datasets with different complexity was conducted, and experimental result indicates that the performance of proposed algorithm is superior to other ten existing salient region detection algorithms both in visual effect and in objective quantitative comparison. Especially on the most challenging DUT-OMRON data base, the aggregative indicator F-measure value of proposed algorithm is 0.631 4, and mean absolute error (MAE) is 0.132 5 and ROC area under the curve (AUC) is 0.892 8, indicating that the algorithm has higher accuracy and robustness.

参考文献

[1] LI X, ZHAO L M, WEI L, et al.. DeepSaliency: Multi-task deep neural network model for salient object detection ［J］. IEEE Transactions on Image Processing, 2016, 25(8): 3919-3930.

[2] 郭少军, 娄树理, 刘峰. 应用颜色聚类图像块的多舰船显著性检测［J］. 光学精密工程, 2016, 24(7): 1807-1817.

GUO SH J, LOU SH L, LIU F, et al.. Multi-ship saliency detection via patch fusion by color clustering ［J］. Opt. Precision Eng., 2016, 24(7): 1807-1817. (in Chinese)

[3] GUO C L, ZHANG L M. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression ［J］. IEEE Transactions on Image Processing, 2010, 19(1): 185-198.

[4] RAHTU E, KANNALA J, SALO M, et al.. Segmenting salient objects from images and videos ［C］. 2010 European Conference on Computer Vision, Crete, Greece, ECCV, 2010: 366-379.

[5] 张迪飞, 张金锁, 姚克明, 等. 基于SVM分类的红外舰船目标识别［J］. 红外与激光工程, 2016, 45(1): 179-184.

ZHANG D F, ZHANG J S, YAO K M, et al.. Infrared ship-target recognition based on SVM classification ［J］. Infrared and Laser Engineering, 2016, 45(1) 179-184. (in Chinese)

[6] TONG N, LU H C, RUAN X, et al.. Salient object detection via bootstrap learning ［C］. 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, United states, CVPR, 2015: 179-184.

[7] ITTI L, KOCH C, 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.

[8] HAREL J, KOCH C, PERONA P. Graph-based visual saliency ［C］. Advances in Neural Information Processing Systems, Vancouver, Canada, 2006: 545-552.

[9] HOU X D, ZHANG L Q. Saliency detection: a spectral residual approach ［C］. 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Minneapolis, United states, CVPR, 2007: 1-8.

[10] 张颖颖, 张帅, 张萍, 等. 融合对比度和分布性的图像显著性区域检测［J］. 光学精密工程, 2014, 22(4): 1012-1019.

ZHANG Y Y, ZHANG SH, ZHANG P, et al.. Detection of salient maps by fusion of contrast and distribution ［J］. Opt. Precision Eng., 2014, 22(4): 1012-1019. (in Chinese)

[11] WEI Y C, WEN F, ZHU W J, et al.. Geodesic saliency using background priors ［C］. 2012 European Conference on Computer Vision, Florence, Italy, ECCV, 2012: 29-42.

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

[13] 贾松敏, 徐涛, 董政胤, 等. 采用脉冲耦合神经网络的改进显著性区域提取方法［J］. 光学精密工程, 2015, 23(3): 819-826.

JIA S M, XU T, DONG ZH Y, et al.. Improved salience region extraction algorithm with PCNN ［J］. Opt. Precision Eng., 2015, 23(3): 819-826. (in Chinese)

[14] 罗会兰, 万成涛, 孔繁胜. 基于KL散度及多尺度融合的显著性区域检测算法［J］. 电子与信息学报, 2016, 38(7): 1594-1601.

LUO H L, WAN CH T, KONG F SH, et al.. Salient region detection algorithm via KL divergence and multi-scale merging ［J］. Journal of Electronics & Information Technology, 2016, 38(7): 1594-1601. (in Chinese)

[15] ZHANG L Y, MARKS T K, TONG M H, et al.. SUN: a bayesian framework for saliency using natural statistics ［J］. Journal of Vision, 2008, 8(7): 1-20.

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

[17] JIANG H Z, WANG J D, YUAN Z J, et al.. Salient object detection: a discriminative regional feature integration approach ［C］. 2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Portland, United states, CVPR, 2013: 2083-2090.

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

[19] NEUMANN J V. The general and logical theory of automata ［J］. Cerebral Mechanisms in Behavior, 1951, 1(41): 1-21.

[20] QIN Y, LU H C, XU Y Q, et al.. Saliency detection via cellular automata ［C］. 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, United states, CVPR, 2015: 110-119.

[21] HE K M, SUN H, TANG X O, et al.. Single image haze removal using dark channel prior ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.

[22] 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): 2274-2281.

[23] BORJI A, CHENG M M, JIANG H, et al.. Salient object detection: a benchmark ［J］. IEEE Transactions on Image Processing, 2015, 24(12): 5706-5722.

[24] 宋颖超, 罗海波, 惠斌, 等. 尺度自适应暗通道先验去雾方法［J］. 红外与激光工程, 2016, 45(9): 286-297.

SONG Y CH, LUO H B, HUI B, et al.. Haze removal using scale adaptive dark channel prior ［J］. Infrared and Laser Engineering, 2016, 45(9): 286-297. (in Chinese)

[25] RADHAKRISHNA A, SHEILA H, FRANCISCO E, et al.. Frequency-tuned salient region detection［C］. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Miami, United states, CVPR, 2009: 1597-1604.

[26] PERAZZI F, KRAHENBUL P, PRITCH Y, et al.. Saliency filters: contrast based filtering for salient region detection［C］. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, United states, CVPR, 2012: 733-740.

徐涛, 贾松敏, 张国梁. 元胞自动机多尺度优化的显著性细微区域检测[J]. 光学精密工程, 2017, 25(5): 1312. XU Tao, JIA Song-min, ZHANG Guo-liang. Salient subtle region accurate detection via cellular automata multi-scale optimization[J]. Optics and Precision Engineering, 2017, 25(5): 1312.

元胞自动机多尺度优化的显著性细微区域检测

关于本站 Cookie 的使用提示

全站搜索

元胞自动机多尺度优化的显著性细微区域检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索