基于流形排序和联合连通性先验的显著性目标检测
|
摘要
为了进一步提高显著性目标检测的准确性,提出基于不同特征流形排序和联合连通性先验的显著性检测算法.针对现有基于流形排序的算法在图的构建中存在的边权重计算和顶点的连接问题,使用不同种特征计算顶点间边的权重,并且改进顶点的连接方式,得到流形排序显著图.同时结合边界连通性先验和前景连通性先验得到联合连通性先验显著图.在不同尺度下进一步融合两种显著性结果,得到最终的显著图.通过与16种算法在4种数据集上的对比表明,文中算法可以得到更清晰、准确的检测结果.
To improve the performance of saliency detection,a bottom-up saliency object detection model is proposed by integrating different features based manifold ranking and co-connectivity. Aiming at the calculation on edge and connection bewteen nodes of the graph in most manifold ranking based models,a manifold ranking based salient map is produced via different features to calculate the weight of edges and modified connection to construct the graph. Simultaneously,the co-connectivity based salient map is obtained by incorporating boundary connectivity and foreground connectivity. The final saliency map is achieved through fusing these two salient results with different scales. Compared with 16 state-ofthe-art methods on four public benchmark datasets,the proposed algorithm performs better.
To improve the performance of saliency detection,a bottom-up saliency object detection model is proposed by integrating different features based manifold ranking and co-connectivity. Aiming at the calculation on edge and connection bewteen nodes of the graph in most manifold ranking based models,a manifold ranking based salient map is produced via different features to calculate the weight of edges and modified connection to construct the graph. Simultaneously,the co-connectivity based salient map is obtained by incorporating boundary connectivity and foreground connectivity. The final saliency map is achieved through fusing these two salient results with different scales. Compared with 16 state-ofthe-art methods on four public benchmark datasets,the proposed algorithm performs better.
引文
[1]ITTI L,KOCH C,NIEBUR E. A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259.
[2] JUDD T,EHINGER K,DURAND F,et al. Learning to Predict Where Humans Look//Proc of the 12th IEEE International Conference on Computer Vision. Washington,USA:IEEE,2009:2106-2113.
[3]CHANG K Y,LIU T L,CHEN H T,et al. Fusing Generic Objectness and Visual Saliency for Salient Object Detection//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:914-921.
[4]PRADEEP A,SUBASH N. Saliency Tree:Saliency Detection Method Integrating Diffusion-Based Compactness and Local Contrast. International Journal of Innovative Research in Computer and Communication Engineering,2015,3(10):9778-9784.
[5]WANG L,XUE J R,ZHENG N N,et al. Automatic Salient Object Extraction with Contextual Cue//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:105-112.
[6]LU Y,ZHANG W,LU H,et al. Salient Object Detection Using Concavity Context//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:233-240.
[7]LIU T,SUN J,ZHENG N N,et al. Learning to Detect a Salient Object//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE, 2017. DOI:10. 1109/CVPR.2007.383047.
[8]CHENG M M,MITRA N J,HUANG X L,et al. Global Contrast Based Salient Region Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,37(3):569-582.
[9]YANG J M,YANG M. Top-Down Visual Saliency via Joint CRF and Dictionary Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(3):576-588.
[10]GOFERMAN S,ZELNIK-MANOR L,TAL A. Context-Aware Saliency Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):1915-1926.
[11]ACHANTA R,SSSTRUNK S. Saliency Detection Using Maximum Symmetric Surround//Proc of the IEEE International Conference on Image Processing. Washington,USA:IEEE,2010:2653-2656.
[12]JIANG H Z,WANG J D,YUAN Z J,et al. Automatic Salient Object Segmentation Based on Context and Shape Prior[C/OL].[2018-08-20]. https://people. cs. umass. edu/~hzjiang/pubs/saliency_cbs_bmvc2011.pdf.
[13]DUAN L J,WU C P,MIAO J,et al. Visual Saliency Detection by Spatially Weighted Dissimilarity//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2011:473-480.
[14]KIM J,HAN D,TAI Y,et al. Salient Region Detection via HighDimensional Color Transform//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2014:883-890.
[15]JIANG P,LING H B,YU J Y,et al. Salient Region Detection by UFO:Uniqueness,Focusness and Objectness//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2013:1976-1983.
[16]TONG N,LU H C,ZHANG Y,et al. Salient Object Detection via Global and Local Cues. Pattern Recognition,2015,48(10):3258-3267.
[17]WEI Y C,WEN F,ZHU W J,et al. Geodesic Saliency Using Background Priors//Proc of the European Conference on Computer Vision. Berlin,Germany:Springer,2012:29-42.
[18]WANG J P,LU H C,LI X H,et al. Saliency Detection via Background and Foreground Seed Selection. Neurocomputing,2015,152:359-368.
[19]ZHU W J,LIANG S,WEI Y C,et al. Saliency Optimization from Robust Background Detection//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2014:2814-2821.
[20]WANG Y Z,PENG G H,ZHOU M. Saliency Detection by Hierarchically Integrating Compactness, Contrast and Boundary Connectivity. Multimedia Tools and Applications, 2018, 77(10):11883-11901.
[21]ACHANTA R,SHAJI A,SMITH K,et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[22]ZHOU D Y,WESTON J,GRETTON A,et al. Ranking on Data Manifolds//Proc of the 16th International Conference on Neural Information Processing Systems. Cambridge, USA:MIT Press,2003:169-176.
[23] YANG C,ZHANG L H,LU H C,et al. Saliency Detection via Graph-Based Manifold Ranking//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2013:3166-3173.
[24]ZHOU L,YANG Z H,ZHOU Z T,et al. Salient Region Detection using Diffusion Process on a 2-Layer Sparse Graph. IEEE Transactions on Image Processing,2017,26(12):5882-5894.
[25]ACHANTA R,HEMAMI S,ESTRADA F,et al. Frequency-Tuned Salient Region Detection//Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington,USA:IEEE,2009:1597-1604.
[26]YAN Q,XU L,SHI J P,et al. Hierarchical Saliency Detection//Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE, 2013:1155-1162.
[27]PERAZZI F,KRHENBUHL P,PRITCH Y,et al. Saliency Filters:Contrast Based Filtering for Salient Region Detection//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington,USA:IEEE,2012:733-740.
[28]ZHANG J M,SCLAROFF S,LIN Z,et al. Minimum Barrier Salient Object Detection at 80 FPS//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2015:1404-1412.
[29]LU H C,LI X H,ZHANG L H,et al. Dense and Sparse Reconstruction Error Based Saliency Descriptor. IEEE Transactions on Image Processing,2016,25(4):1592-1603.
[30]ZHOU L,YANG Z H,YUAN Q,et al. Salient Region Detection via Integrating Diffusion-Based Compactness and Local Contrast.IEEE Transactions on Image Processing,2015,24(11):3308-3320.
[31]PENG H W,LI B,LING H B,et al. Salient Object Detection via Structured Matrix Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):818-832.
[32]WANG Y Z,PENG G H. Salient Object Detection Based on Compactness and Foreground Connectivity. Machine Vision and Applications,2018,29(7):1143-1155.
[2] JUDD T,EHINGER K,DURAND F,et al. Learning to Predict Where Humans Look//Proc of the 12th IEEE International Conference on Computer Vision. Washington,USA:IEEE,2009:2106-2113.
[3]CHANG K Y,LIU T L,CHEN H T,et al. Fusing Generic Objectness and Visual Saliency for Salient Object Detection//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:914-921.
[4]PRADEEP A,SUBASH N. Saliency Tree:Saliency Detection Method Integrating Diffusion-Based Compactness and Local Contrast. International Journal of Innovative Research in Computer and Communication Engineering,2015,3(10):9778-9784.
[5]WANG L,XUE J R,ZHENG N N,et al. Automatic Salient Object Extraction with Contextual Cue//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:105-112.
[6]LU Y,ZHANG W,LU H,et al. Salient Object Detection Using Concavity Context//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2011:233-240.
[7]LIU T,SUN J,ZHENG N N,et al. Learning to Detect a Salient Object//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE, 2017. DOI:10. 1109/CVPR.2007.383047.
[8]CHENG M M,MITRA N J,HUANG X L,et al. Global Contrast Based Salient Region Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,37(3):569-582.
[9]YANG J M,YANG M. Top-Down Visual Saliency via Joint CRF and Dictionary Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(3):576-588.
[10]GOFERMAN S,ZELNIK-MANOR L,TAL A. Context-Aware Saliency Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):1915-1926.
[11]ACHANTA R,SSSTRUNK S. Saliency Detection Using Maximum Symmetric Surround//Proc of the IEEE International Conference on Image Processing. Washington,USA:IEEE,2010:2653-2656.
[12]JIANG H Z,WANG J D,YUAN Z J,et al. Automatic Salient Object Segmentation Based on Context and Shape Prior[C/OL].[2018-08-20]. https://people. cs. umass. edu/~hzjiang/pubs/saliency_cbs_bmvc2011.pdf.
[13]DUAN L J,WU C P,MIAO J,et al. Visual Saliency Detection by Spatially Weighted Dissimilarity//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2011:473-480.
[14]KIM J,HAN D,TAI Y,et al. Salient Region Detection via HighDimensional Color Transform//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2014:883-890.
[15]JIANG P,LING H B,YU J Y,et al. Salient Region Detection by UFO:Uniqueness,Focusness and Objectness//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2013:1976-1983.
[16]TONG N,LU H C,ZHANG Y,et al. Salient Object Detection via Global and Local Cues. Pattern Recognition,2015,48(10):3258-3267.
[17]WEI Y C,WEN F,ZHU W J,et al. Geodesic Saliency Using Background Priors//Proc of the European Conference on Computer Vision. Berlin,Germany:Springer,2012:29-42.
[18]WANG J P,LU H C,LI X H,et al. Saliency Detection via Background and Foreground Seed Selection. Neurocomputing,2015,152:359-368.
[19]ZHU W J,LIANG S,WEI Y C,et al. Saliency Optimization from Robust Background Detection//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2014:2814-2821.
[20]WANG Y Z,PENG G H,ZHOU M. Saliency Detection by Hierarchically Integrating Compactness, Contrast and Boundary Connectivity. Multimedia Tools and Applications, 2018, 77(10):11883-11901.
[21]ACHANTA R,SHAJI A,SMITH K,et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[22]ZHOU D Y,WESTON J,GRETTON A,et al. Ranking on Data Manifolds//Proc of the 16th International Conference on Neural Information Processing Systems. Cambridge, USA:MIT Press,2003:169-176.
[23] YANG C,ZHANG L H,LU H C,et al. Saliency Detection via Graph-Based Manifold Ranking//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE,2013:3166-3173.
[24]ZHOU L,YANG Z H,ZHOU Z T,et al. Salient Region Detection using Diffusion Process on a 2-Layer Sparse Graph. IEEE Transactions on Image Processing,2017,26(12):5882-5894.
[25]ACHANTA R,HEMAMI S,ESTRADA F,et al. Frequency-Tuned Salient Region Detection//Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington,USA:IEEE,2009:1597-1604.
[26]YAN Q,XU L,SHI J P,et al. Hierarchical Saliency Detection//Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington, USA:IEEE, 2013:1155-1162.
[27]PERAZZI F,KRHENBUHL P,PRITCH Y,et al. Saliency Filters:Contrast Based Filtering for Salient Region Detection//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington,USA:IEEE,2012:733-740.
[28]ZHANG J M,SCLAROFF S,LIN Z,et al. Minimum Barrier Salient Object Detection at 80 FPS//Proc of the IEEE International Conference on Computer Vision. Washington,USA:IEEE,2015:1404-1412.
[29]LU H C,LI X H,ZHANG L H,et al. Dense and Sparse Reconstruction Error Based Saliency Descriptor. IEEE Transactions on Image Processing,2016,25(4):1592-1603.
[30]ZHOU L,YANG Z H,YUAN Q,et al. Salient Region Detection via Integrating Diffusion-Based Compactness and Local Contrast.IEEE Transactions on Image Processing,2015,24(11):3308-3320.
[31]PENG H W,LI B,LING H B,et al. Salient Object Detection via Structured Matrix Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):818-832.
[32]WANG Y Z,PENG G H. Salient Object Detection Based on Compactness and Foreground Connectivity. Machine Vision and Applications,2018,29(7):1143-1155.