-
In order to solve the problems of video saliency detection and poor fusion effect, a video saliency detection model and a fusion model are proposed. Video saliency detection is divided into spatial saliency detection and temporal saliency detection. In the spatial domain, inspired by the properties of visual cortex hierarchical perception and the Gestalt visual psychology, we propose a hierarchical saliency detection model with three-layer architecture for single frame image. The video single frame is simplified layer by layer, then the results are combined to form a whole consciousness vision object and become easier to deal with. At the bottom of the model, candidate saliency regions are formed by nonlinear simplification model of the characteristic image (dual color characteristic and luminance characteristic image), which is in accordance with the biological visual characteristic. In the middle of the model, the candidate regions with the strongest competitiveness are selected as the local salient regions according to the property of matrix minimum Fresenius- norm (F- norm). At the top level of the model, the local salient regions are integrated by the core theory of Gestalt visual psychology, and the spatial saliency map is obtained. In the time domain, based on the consistency assumption of a moving object in target location, motion range and direction, the optical flow points detected by Lucas-Kanade method are classified to eliminate the noise interference, then the motion saliency of moving object is measured by the motion amplitude. Finally, based on the difference between the visual sensitivity of dynamic and static information and the difference in visual sensitivity between color information and gray information, a general fusion model of time and spatial domain salient region is proposed. The saliency detection results of single frame image and video sequence frame image are represented by the gray color model and the Munsell color system respectively. Experimental results show that the proposed saliency detection method can suppress the background noise, solve the sparse pixels problem of a moving object, and can effectively detect the salient regions from the video. The proposed fusion model can display two kinds of saliency results simultaneously in a single picture of a complex scene. This model ensures that the detection results of images are so complicated that a chaotic situation will not appear.
-
Keywords:
- saliency detection /
- nonlinear simplification /
- Gestalt visual psychology /
- Lucas-Kanade method
[1] Borji A, Sihite D N, Itti L 2015 IEEE Trans. Image Process. 24 5706
[2] Cichy R M, Pantazis D, Oliva A 2016 Cerebral Cortex 26 3563
[3] Li Z C, Qin S Y, Itti L 2011 Image Vision Comput. 29 1
[4] Wu G L, Fu Y J, Huang S C, Chen S Y 2013 IEEE Trans. Image Process. 22 2247
[5] Franke U, Pfeiffer D, Rabe C, Knoeppel C, Enzweiler M, Stein F, Herrtwich R 2013 Proceedings of IEEE Conference on Computer Vision Sydney, Australia, December 1-8, 2013 p214
[6] Ma Y F, Hua X S, Lu L, Zhang H J 2005 IEEE Trans. Multimed. 7 907
[7] Ejaz N, Mehmood I, Baik S W 2014 Comput. Elec. Engr. 40 993
[8] Evangelopoulos G, Zlatintsi A, Potamianos A, Maragos P 2013 IEEE Trans. Multimed. 15 1553
[9] Itti L, Koch C, Niebur E 1998 IEEE Trans. Pattern Anal. Mach. Intell. 20 1254
[10] Itti L, Koch C 2001 Nat. Rev. Neurosci. 2 194
[11] Cheng M M, Zhang G X, Mitra N J, Huang X, Hu S M 2011 Proceedings of Computer Vision and Pattern Recognition Colorado Springs, November 15-18, 2011 p409
[12] Liu J, Wang S 2015 Neurocomputing 147 435
[13] Guo C, Ma Q, Zhang L 2008 Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Anchorage, Alaska, January 17-18, 2008 p1
[14] Hou X D, Zhang L Q 2007 Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Minneapolis, Minnesota, June 19-21, 2007 p18
[15] Zhu Z, Wang M 2016 J. Comput. Appl. 36 2560
[16] Tao D, Cheng J, Song M 2016 IEEE Trans. Neur. Netw. Lear. Syst. 27 1122
[17] Xue Y W, Guo X J, Cao X C 2012 Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing Kyoto, Japan, March 25-30, 2012 p1485
[18] Ma Z M, Tao C K 1999 Acta Phys. Sin. 48 2202 (in Chinese) [马兆勉, 陶纯堪 1999 物理学报 48 2202]
[19] Jin Z L, Han J, Zhang Y, Bo L F 2014 Acta Phys. Sin. 63 069501 (in Chinese) [金左轮, 韩静, 张毅, 柏连发 2014 物理学报 63 069501]
[20] Wu Y Q, Zhang J K 2010 Acta Phys. Sin. 59 5487 (in Chinese) [吴一全, 张金矿 2010 物理学报 59 5487]
[21] Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 物理学报 59 980]
[22] Wang X, Ma H, Chen X 2016 Proceedings of International Conference on Image Processing the Phoenix Convention Centre, Phoenix, Arizona, USA, September, 2016 p25
[23] He S, Lau R W, Liu W 2015 Int. J. Comput. Vision 115 330
[24] Li H, Chen J, Lu H 2017 Neurocomputing 226 212
[25] Huang Y 2016 M. S. Thesis (Beijing: Institute of Optoelectronic Technology) [黄烨2016 硕士学位论文 (北京: 中国科学院)]
[26] Paragios N, Deriche R 2000 IEEE Trans. Pattern Anal. Mach. Intell. 22 266
[27] Tsai D M, Lai S C 2009 IEEE Trans. Image Process. 18 158
[28] Barron J L, Fleet D, Beauchemin S S 1994 Int. J. Comput. Vision 12 43
[29] Elazary L, Itti L 2008 J. Vision 8
[30] Lucas B D, Kanade T 1981 Proceedings of International Joint Conference on Artificial Intelligence Vancouver, BC, Canada, August, 1981 285
[31] Baker S, Scharstein D, Lewis J P, Roth S, Black M J, Szelisk R 2007 Proceedings of IEEE International Conference on Computer Vision Rio de Janeiro, Brazil, October 14-21, 2007 p92
[32] Koffka K 1935 Principles of Gestalt Psychology (London: Lund Humphries)
[33] Mullen K T 1985 J. Phys. 359 381
[34] Gary B, Adrian K 2008 Learning OpenCV (America: O'Reilly Media) pp356-370
[35] Shi J, Yan Q, Xu L, Jia J 2016 IEEE Trans. Pattern Anal. Mach. Intell. 38 1
[36] Li X, Li Y, Shen C H, Dick A, Hengel 2013 Proceedings of Computer Vision Sydney, NSW, Australia, December 8, 2013 p3328
-
[1] Borji A, Sihite D N, Itti L 2015 IEEE Trans. Image Process. 24 5706
[2] Cichy R M, Pantazis D, Oliva A 2016 Cerebral Cortex 26 3563
[3] Li Z C, Qin S Y, Itti L 2011 Image Vision Comput. 29 1
[4] Wu G L, Fu Y J, Huang S C, Chen S Y 2013 IEEE Trans. Image Process. 22 2247
[5] Franke U, Pfeiffer D, Rabe C, Knoeppel C, Enzweiler M, Stein F, Herrtwich R 2013 Proceedings of IEEE Conference on Computer Vision Sydney, Australia, December 1-8, 2013 p214
[6] Ma Y F, Hua X S, Lu L, Zhang H J 2005 IEEE Trans. Multimed. 7 907
[7] Ejaz N, Mehmood I, Baik S W 2014 Comput. Elec. Engr. 40 993
[8] Evangelopoulos G, Zlatintsi A, Potamianos A, Maragos P 2013 IEEE Trans. Multimed. 15 1553
[9] Itti L, Koch C, Niebur E 1998 IEEE Trans. Pattern Anal. Mach. Intell. 20 1254
[10] Itti L, Koch C 2001 Nat. Rev. Neurosci. 2 194
[11] Cheng M M, Zhang G X, Mitra N J, Huang X, Hu S M 2011 Proceedings of Computer Vision and Pattern Recognition Colorado Springs, November 15-18, 2011 p409
[12] Liu J, Wang S 2015 Neurocomputing 147 435
[13] Guo C, Ma Q, Zhang L 2008 Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Anchorage, Alaska, January 17-18, 2008 p1
[14] Hou X D, Zhang L Q 2007 Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Minneapolis, Minnesota, June 19-21, 2007 p18
[15] Zhu Z, Wang M 2016 J. Comput. Appl. 36 2560
[16] Tao D, Cheng J, Song M 2016 IEEE Trans. Neur. Netw. Lear. Syst. 27 1122
[17] Xue Y W, Guo X J, Cao X C 2012 Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing Kyoto, Japan, March 25-30, 2012 p1485
[18] Ma Z M, Tao C K 1999 Acta Phys. Sin. 48 2202 (in Chinese) [马兆勉, 陶纯堪 1999 物理学报 48 2202]
[19] Jin Z L, Han J, Zhang Y, Bo L F 2014 Acta Phys. Sin. 63 069501 (in Chinese) [金左轮, 韩静, 张毅, 柏连发 2014 物理学报 63 069501]
[20] Wu Y Q, Zhang J K 2010 Acta Phys. Sin. 59 5487 (in Chinese) [吴一全, 张金矿 2010 物理学报 59 5487]
[21] Xu Y N, Zhao Y, Liu L P, Zhang Y, Sun X D 2010 Acta Phys. Sin. 59 980 (in Chinese) [许元男, 赵远, 刘丽萍, 张宇, 孙秀冬 2010 物理学报 59 980]
[22] Wang X, Ma H, Chen X 2016 Proceedings of International Conference on Image Processing the Phoenix Convention Centre, Phoenix, Arizona, USA, September, 2016 p25
[23] He S, Lau R W, Liu W 2015 Int. J. Comput. Vision 115 330
[24] Li H, Chen J, Lu H 2017 Neurocomputing 226 212
[25] Huang Y 2016 M. S. Thesis (Beijing: Institute of Optoelectronic Technology) [黄烨2016 硕士学位论文 (北京: 中国科学院)]
[26] Paragios N, Deriche R 2000 IEEE Trans. Pattern Anal. Mach. Intell. 22 266
[27] Tsai D M, Lai S C 2009 IEEE Trans. Image Process. 18 158
[28] Barron J L, Fleet D, Beauchemin S S 1994 Int. J. Comput. Vision 12 43
[29] Elazary L, Itti L 2008 J. Vision 8
[30] Lucas B D, Kanade T 1981 Proceedings of International Joint Conference on Artificial Intelligence Vancouver, BC, Canada, August, 1981 285
[31] Baker S, Scharstein D, Lewis J P, Roth S, Black M J, Szelisk R 2007 Proceedings of IEEE International Conference on Computer Vision Rio de Janeiro, Brazil, October 14-21, 2007 p92
[32] Koffka K 1935 Principles of Gestalt Psychology (London: Lund Humphries)
[33] Mullen K T 1985 J. Phys. 359 381
[34] Gary B, Adrian K 2008 Learning OpenCV (America: O'Reilly Media) pp356-370
[35] Shi J, Yan Q, Xu L, Jia J 2016 IEEE Trans. Pattern Anal. Mach. Intell. 38 1
[36] Li X, Li Y, Shen C H, Dick A, Hengel 2013 Proceedings of Computer Vision Sydney, NSW, Australia, December 8, 2013 p3328
Catalog
Metrics
- Abstract views: 5753
- PDF Downloads: 302
- Cited By: 0
下载:
