Salient Object Detection Based on Laplace Diffusion Models with Sink Points
WANG Baoyan① ZHANG Tie② WANG Xingang③
①(College of Information Science and Engineering, Northeastern University, Shenyang 110819, China) ②(College of Science, Northeastern University, Shenyang 110819, China) ③(College of Control Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China)
Based on Laplace similarity metrics, corresponding diffusion-based saliency models are proposed according to different clusters (sparse or dense) of salient seeds in the two-stage detection, a diffusion-based two-stage complementary method for salient object detection is therefore investigated. Especially for the introduction of sink points in the second stage, saliency maps obtained by this proposed method can well restrain background parts, as well as become more robust with the change of control factor α. Experiments show that different diffusion models will cause diversities of saliency diffusion degree when salient seeds are determined. In addition, the two-stage Laplace-based diffusion model with sink points is more effective and robust than other two-stage diffusion models. Meanwhile, the proposed algorithm is superior over the existing five state-of-the-art methods in terms of different metrics. This exactly shows that the similarity metrics method applied to image retrieval and classification is also available for salient objects detection.
SHEN Hao, LI Shuxiao, ZHU Chengfei, et al. Moving object detection in aerial video based on spatiotemporal saliency[J]. Chinese Journal of Aeronautics, 2013, 26(5): 1211-1217. doi: 10.1016/j.cja.2013.07.038.
[2]
WANG Tiantian, XIU Chunbo, and CHENG Yi. Vehicle recognition based on saliency detection and color histogram [C]. 54th IEEE Conference on Decision and Control, Osaka, Japan, 2015: 2532-2535. doi: 10.1109/CCDC.2015.7162347.
[3]
GUO Chenlei and ZHANG Liming. 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. doi: 10.1109/TIP. 2009.2030969.
[4]
ITTI L. Automatic foveation for video compression using a neurobiological model of visual attention[J]. IEEE Transactions on Image Processing, 2004, 13(10): 1304-1318. doi: 10.1109/TIP.2004.834657.
[5]
QIN Chanchan, ZHANG Guoping, ZHOU Yicong, et al. Integration of the saliency-based seed extraction and random walks for image segmentation[J]. Neurocomputing, 2014, 129(4): 378-391. doi: 10.1016/j.neucom.2013.09.021.
[6]
LI Ang, SHE Xiaochun, and SUN Qizhi. Color image quality assessment combining saliency and FSIM[C]. Fifth International Conference on Digital Image Processing, Beijing, China, 2013: 88780I-1-88780I-5. doi: 10.1117/12. 2030719.
[7]
LI Liang, JIANG Shuqiang, ZHA Zhengjun, et al. Partial- duplicate image retrieval via saliency-guided visual matching [J]. IEEE Multimedia, 2013, 20(3): 13-23. doi: 10.1109/ MMUL.2013.15.
[8]
NA I S, LE H, KIM S H, et al. Extraction of salient objects based on image clustering and saliency[J]. Pattern Analysis and Application, 2015, 18(3): 667-675. doi: 10.1007/s10044- 015-0459-1.
[9]
HAN Jie, GUO Baolong, and SUN Wei. Target tracking method in aerial video based on saliency fusion[C]. International Conference on Mechatronics, Electronic, Industrial and Control Engineering, Shanghai, China, 2015: 723-727. doi: 10.2991/meic-15.2015.165.
[10]
BORJI A, CHENG Mingming, JIANG Huaizu, et al. Salient object detection: A benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5706-5722. doi: 10.1007/ 978-3-642-33709-3_30.
[11]
WEI Yichen, WEN Fang, ZHU Wangjiang, et al. Geodesic saliency using background priors[C]. 12th European Conference on Computer Vision, Florence, Italy, 2012: 29-42. doi: 10.1007/978-3-642-33712-3_3.
[12]
FU Keren, GU I Y H, GONG Chen, et al. Robust manifold- preserving diffusion-based saliency detection by adaptive weight construction[J]. Neurocomputing, 2015, 175: 336-347. doi: 10.1016/j.neucom.2015.10.066.
[13]
SHEN Xiaohui and WU Ying. A unified approach to salient object detection via low rank matrix recovery[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 853-860. doi: 10.1109/CVPR.2012. 6247758.
[14]
LI Xiaohui, LU Huchuan, ZHANG Lihe, et al. Saliency detection via dense and sparse reconstruction[C]. IEEE Conference on Computer Vision, Sydney, Australia, 2013: 2976-2983. doi: 10.1109/ICCV.2013.370.
[15]
YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Oregon, USA, 2013: 3166-3173. doi: 10.1109/CVPR.2013. 407.
[16]
JIANG Bowen, ZHANG Lihe, LU Huchuan, et al. Saliency detection via absorbing markov chain[C]. IEEE Conference on Computer Vision, Oregon, USA, 2013: 1665-1672. doi: 10.1109/ICCV.2013.209.
[17]
ZHOU Li, YANG Zhaohui, YUAN Qing, et al. Salient region detection via integrating diffusion-based compactness and local contrast[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3308-3320. doi: 10.1109/TIP.2015.2438546.
[18]
HWANG I, LEE S H, PARK J S, et al. Saliency detection based on seed propagation in a multi-layer graph[J]. Multimedia Tools & Applications, 2017, 76(2): 2111-2129. doi: 10.1007 /s11042-015-3171-7.
[19]
GOPALAKRISHNAN V, HU Yiqun, and RAJAN D. Random walks on graphs to model saliency in images[C]. IEEE Conference on Computer Vision, Miami, USA, 2009: 1698-1705. doi: 10.1109/CVPR.2009.5206767.
[20]
FU Keren, GU I Y H, and YANG Jie. Learning full-range affinity for diffusion-based saliency detection[C]. 41st IEEE International Conference on Acoustics, Speech and Signal Processing, Shanghai, China, 2016: 1926-1930.
[21]
GONG Chen, TAO Dacheng, LIU Wei, et al. Saliency propagation from simple to difficult[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 2531-2539. doi: 10.1109/CVPR.2015.7298868.
[22]
WU Xiaoming, LI Zhenguo, and CHANG Shihfu. New insights into Laplacian similarity search[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 1949-1957. doi: 10.1109/CVPR.2015. 7298805.
[23]
ACHANTA R, HEMAMI S, ESTRADA F, et al. SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282. doi: 10.1109/TPAMI. 2012.120.
[24]
OTSU N. A threshold selection method from gray level histograms[J]. IEEE Transactions on System, Man, and Cybernetic, 1979, 9(1): 62-66. doi: 10.1109/TSMC.1979. 4310076.
[25]
CHEN Shuhan, ZHENG Ling, HU Xuelong, et al. Discriminative saliency propagation with sink points[J]. Pattern Recognition, 2016, 60: 2-12. doi: 10.1016/j.patcog. 2016.05.016.
BIRJI A. What is a salient object a dataset and a baseline model for salient object detection[J]. IEEE Transactions on Image Processing, 2015, 24(2): 742-756. doi: 10.1109/TIP. 2014.2383320.
[28]
ZHU Wangjiang, LIANG Shuang, WEI Yichen, et al. Saliency optimization from robust background detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2814-2821. doi: 10.1109/CVPR.2014.360.
[29]
ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency- tuned salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2009: 1597-1604. doi: 10.1109/CVPR.2009.5206596.
