语义信息引导下的显著目标检测算法
|
摘要
针对现有显著性检测方法在凸显目标完整性和背景噪声抑制方面性能较差的问题,提出一种显著目标检测算法。构建改进的全卷积神经网络,捕获图像中的语义信息,生成高层语义初步显著图。利用语义知识引导流形排序进行优化,实现显著目标的边缘传播。融合不同尺度下的显著图,完成显著目标检测。在ECSSD、DUT-OMRON、SED2数据集上进行实验,结果表明,与最大对称环绕、主成分分析等算法相比,该算法检测出的显著目标更加完整,在复杂场景下检测结果鲁棒性更好。
In view of the poor performance of the existing saliency detection method in object highlighting and background noise suppression,a salient object detection algorithm is proposed.An improved Fully Convolutional Neural Network(FCNN) is constructed to capture the semantic information in the image,which can generate the high-level semantic preliminary saliency maps.The semantic knowledge is used to optimize the Manifold Ranking(MR),and then achieve the edge propagation of salient object.The saliency maps under different scales are fused to realize salient object detection.Experiments are carried out on ECSSD,DUT-OMRON and SED2 datasets,the results show that compared with algorithms such as Maximum Symmetric Surround(MSS)and Principal Component Analysis(PCA),the salient objects detected by the algorithm in this paper are more complete and the detection results are more robust in complex scenes.
In view of the poor performance of the existing saliency detection method in object highlighting and background noise suppression,a salient object detection algorithm is proposed.An improved Fully Convolutional Neural Network(FCNN) is constructed to capture the semantic information in the image,which can generate the high-level semantic preliminary saliency maps.The semantic knowledge is used to optimize the Manifold Ranking(MR),and then achieve the edge propagation of salient object.The saliency maps under different scales are fused to realize salient object detection.Experiments are carried out on ECSSD,DUT-OMRON and SED2 datasets,the results show that compared with algorithms such as Maximum Symmetric Surround(MSS)and Principal Component Analysis(PCA),the salient objects detected by the algorithm in this paper are more complete and the detection results are more robust in complex scenes.
引文
[1] SHEHNAZ M,NAVEEN N.An object recognition algorithm with structure-guided saliency detection and SVM classifier[C]//Proceedings of 2015 International Conference on Power,Instrumentation,Control and Computing.Washington D.C.,USA:IEEE Press,2015:1-4.
[2] ZHANG F,DU B,ZHANG L.Saliency-guided unsupervised feature learning for scene classification[J].IEEE Tran-sactions on Geoscience and Remote Sensing,2015,53(4):2175-2184.
[3] ZHAO R,OUYANG W,WANG X.Unsupervised salience learning for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3586-3593.
[4] GUO D,TANG J,CUI Y,et al.Saliency-based content-aware lifestyle image mosaics[J].Journal of Visual Communication and Image Representation,2015,26:192-199.
[5] 冯松鹤,郎丛妍,须德.一种融合图学习与区域显著性分析的图像检索算法[J].电子学报,2011,39(10):2288-2294.
[6] SHEN X,WU Y.A unified approach to salient object detection via low rank matrix recovery[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:853-860.
[7] ZHU W,LIANG S,WEI Y,et al.Saliency optimization from robust background detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:2814-2821.
[8] 袁巧,程艳芬,陈先桥.多先验特征与综合对比度的图像显著性检测[J].中国图象图形学报,2018,23(2):239-248.
[9] WANG L,LU H,RUAN X,et al.Deep networks for saliency detection via local estimation and global search[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3183-3192.
[10] 高东东,张新生.基于空间卷积神经网络模型的图像显著性检测[J].计算机工程,2018,44(5):246-251.
[11] KIM J,PAVLOVIC V.A shape preserving approach for salient object detection using convolutional neural networks[C]//Proceedings of the 23rd International Con-ference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:609-614.
[12] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[13] LIU T,SUN J,ZHENG N N,et al.Learning to detect a salient object[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2007:1-8.
[14] YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3166-3173.
[15] YAN Q,XU L,SHI J,et al.Hierarchical saliency detec-tion[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1155-1162.
[16] ALPERT S,GALUN M,BASRI R,et al.Image segmentation by probabilistic bottom-up aggregation and cue integration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):315-327.
[17] ACHANTA R,SüSSTRUNK S.Saliency detection using maximum symmetric surround[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2010:2653-2656.
[18] MARGOLIN R,TAL A,ZELNIK-MANOR L.What makes a patch distinct[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1139-1146.
[19] YANG C,ZHANG L,LU H.Graph-regularized saliency detection with convex-hull-based center prior [J].IEEE Signal Processing Letters,2013,20(7):637-640.
[20] JIANG B,ZHANG L,LU H,et al.Saliency detection via absorbing markov chain[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:1665-1672.
[21] JIANG H,WANG J,YUAN Z,et al.Salient object detection:a discriminative regional feature integration approach [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2083-2090.
[2] ZHANG F,DU B,ZHANG L.Saliency-guided unsupervised feature learning for scene classification[J].IEEE Tran-sactions on Geoscience and Remote Sensing,2015,53(4):2175-2184.
[3] ZHAO R,OUYANG W,WANG X.Unsupervised salience learning for person re-identification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3586-3593.
[4] GUO D,TANG J,CUI Y,et al.Saliency-based content-aware lifestyle image mosaics[J].Journal of Visual Communication and Image Representation,2015,26:192-199.
[5] 冯松鹤,郎丛妍,须德.一种融合图学习与区域显著性分析的图像检索算法[J].电子学报,2011,39(10):2288-2294.
[6] SHEN X,WU Y.A unified approach to salient object detection via low rank matrix recovery[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:853-860.
[7] ZHU W,LIANG S,WEI Y,et al.Saliency optimization from robust background detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:2814-2821.
[8] 袁巧,程艳芬,陈先桥.多先验特征与综合对比度的图像显著性检测[J].中国图象图形学报,2018,23(2):239-248.
[9] WANG L,LU H,RUAN X,et al.Deep networks for saliency detection via local estimation and global search[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3183-3192.
[10] 高东东,张新生.基于空间卷积神经网络模型的图像显著性检测[J].计算机工程,2018,44(5):246-251.
[11] KIM J,PAVLOVIC V.A shape preserving approach for salient object detection using convolutional neural networks[C]//Proceedings of the 23rd International Con-ference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:609-614.
[12] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[13] LIU T,SUN J,ZHENG N N,et al.Learning to detect a salient object[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2007:1-8.
[14] YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3166-3173.
[15] YAN Q,XU L,SHI J,et al.Hierarchical saliency detec-tion[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1155-1162.
[16] ALPERT S,GALUN M,BASRI R,et al.Image segmentation by probabilistic bottom-up aggregation and cue integration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):315-327.
[17] ACHANTA R,SüSSTRUNK S.Saliency detection using maximum symmetric surround[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2010:2653-2656.
[18] MARGOLIN R,TAL A,ZELNIK-MANOR L.What makes a patch distinct[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1139-1146.
[19] YANG C,ZHANG L,LU H.Graph-regularized saliency detection with convex-hull-based center prior [J].IEEE Signal Processing Letters,2013,20(7):637-640.
[20] JIANG B,ZHANG L,LU H,et al.Saliency detection via absorbing markov chain[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:1665-1672.
[21] JIANG H,WANG J,YUAN Z,et al.Salient object detection:a discriminative regional feature integration approach [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2083-2090.