融合连续区域特性和背景学习模型的显著计算

doi:10.16451/j.cnki.issn1003-6059.201804002

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1203 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To enhance the computational efficiency of saliency model, a continuous region feature and background learning based model is proposed and the salient regions of images are extracted and fused. Firstly, the distance from the target pixel to the pixels of the region around is calculated, and a method for measuring the comparison of saliency based on Bayesian is proposed. The continuity of regions are merged. The void regions are merged with the most similar regions to themselves. Then, three typical saliency algorithms are employed to deal with the same image, and consequently different saliency maps are obtained. The background of each significant feature map is acquired in the contrast way, and the mixed Gauss background model is established. The background maps are obtained by learning weight coefficient, and then the saliency regions are acquired through subtracting background map from the image. Finally, the saliency regions are fused with the cell regulation. The proposed algorithm is validated on public SED1 and ASD datasets. The F-Measure and MAE of the proposed algorithm are superior to those of the current popular algorithms.

Key words： Machine Vision Saliency Detection Gaussian Mixture Model(GMM) Feature Fusion

Received: 21 November 2017

ZTFLH:

TP 391.4

Fund:Supported by National Natural Science Foundation of China(No.51177115), Natural Science Basis Research Plan in Shaanxi Province of China(2017JQ6054), Key Technology Innovation Team Project of Shaanxi Province(No.2014KCT-16), Science & Technology Research and Development Program of Shaanxi Province(No.2014XT-07), Project of Industrial Technology Research of Shaanxi Province(No.2015GY-075), Ph.D Start-up Fund of Xi′an Polytechnic University(No.BS1505)

Corresponding Authors: JI Chao(Corresponding author), Ph.D., lecturer. His research interests include online monitoring of smart grid, machine vision and artificial intelligence.

About author:: HUANG Xinbo, Ph.D., professor. His research interests include online monitoring technology and image processing;LIU Huiying, Ph.D., professor. Her research interests include machine vision and artificial intelligence;ZHANG Huiying, master student. Her research interests include computer vision and target tracking;XING Xiaoqaing, master student. His research interests include intelligent information processing and pattern recognition.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	JI Chao
	HUANG Xinbo
	LIU Huiying
	ZHANG Huiying
	XING Xiaoqiang

Cite this article:

JI Chao,HUANG Xinbo,LIU Huiying等. Fusing Continuous Region Characteristics and Background Learning Model for Saliency Computation[J]. , 2018, 31(4): 300-309.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201804002 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2018/V31/I4/300

[1] HOU X D, ZHANG L Q, Saliency Detection: A Spectral Residual Approach // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2007: 10.1109/CVPR.2007.383267.
[2] CHENG M M, ZHANG G X, MITRA N J, et al. Global Contrast Based Salient Region Detection // Proc of the 24th IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 409-416.
[3] ZHANG K, ZUO W M, GU S H, et al. Learning Deep CNN Denoiser Prior for Image Restoration // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2808-2817.
[4] HOU Q B, CHENG M M, HU X W, et al. Deeply Supervised Salient Object Detection with Short Connections // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 5300-5309.
[5] FILALI I, ALLILI M S, BENBLIDIA N. Multi-scale Salient Object Detection Using Graph Ranking and Global-Local Saliency Refinement. Signal Processing: Image Communication, 2016, 47: 380-401.
[6] LI X, ZHAO L M, WEI L N, et al. DeepSaliency: Multi-task Deep Neural Network Model for Salient Object Detection. IEEE Transactions on Image Processing, 2016, 25(8): 3919-3930.
[7] HUANG F, QI J Q, LU H C, et al. Salient Object Detection via Multiple Instance Learning. IEEE Transactions on Image Proce-ssing, 2017, 26(4): 1911-1922.
[8] DAVIS A, BOUMAN K L, CHEN J G, et al. Visual Vibrometry: Estimating Material Properties from Small Motions in Video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 732-745.
[9] LI X H, LU H C, ZHANG L H, et al. Saliency Detection via Dense and Sparse Reconstruction // Proc of the IEEE International Confe-rence on Computer Vision. Washington, USA: IEEE, 2013: 2976-2983.
[10] POHLEN T, HERMANS A, MATHIAS M, et al. Full Resolution Residual Networks for Semantic Segmentation in Street Scenes // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2017: 3309-3318.
[11] WU H S, WU Y L, ZHANG S L, et al. Cartoon Image Segmentation Based on Improved SLIC Superpixels and Adaptive Region Propagation Merging // Proc of the IEEE International Conference on Signal and Image Processing. Washington, USA: IEEE, 2016: 277-281.
[12] MA Y F, ZHANG H J. Contrast-Based Image Attention Analysis by Using Fuzzy Growing // Proc of the 11th ACM International Conference on Multimedia. New York, USA: ACM, 2003: 374-381.
[13] WANG X, MA H M, CHEN X Z, et al. Edge Preserving and Multi-scale Contextual Neural Network for Salient Object Detection. IEEE Transactions on Image Processing, 2018, 27(1): 121-134.
[14] TONG N, LU H C, RUAN X, et al. Salient Object Detection via Bootstrap Learning // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 1882-1892.
[15] GOFERMAN S, ZELNIK-MANOR L, TAL A. Context-Aware Saliency Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10): 1915-1926.
[16] CHEN X Z, MA H M, WANG X, et al. Improving Object Propo-sals with Multi-thresholding Straddling Expansion // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 2587-2595.
[17] 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.
[18] ACHANTA R, ESTRADA F, WILS P, et al. Salient Region Detection and Segmentation // Proc of the 6th International Confe-rence on Computer Vision Systems. New York, USA: Springer, 2008: 66-75.
[19] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-Tuned Salient Region Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2009: 1597-1604.