Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior

Yang, Caiqin; Zhang, Lihe; Lu, Huchuan

doi:10.1109/lsp.2013.2260737

Cited by 242 publications

(50 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first analyze the design options in the Poisson diffusion system and then compare our method with 19 state-of-the-art saliency detectors, i.e., IT, 4 AC, 9 CA, 11 CB, 14 GB, 5 MZ, 7 SER, 8 SF, 15 SR, 6 SM, 19 SVO, 16 GS, 17 LC, 12 LR, 18 FT, 10 RC, 13 XIE, 20 MR, 25 and LESD. We first analyze the design options in the Poisson diffusion system and then compare our method with 19 state-of-the-art saliency detectors, i.e., IT, 4 AC, 9 CA, 11 CB, 14 GB, 5 MZ, 7 SER, 8 SF, 15 SR, 6 SM, 19 SVO, 16 GS, 17 LC, 12 LR, 18 FT, 10 RC, 13 XIE, 20 MR, 25 and LESD.…”

Section: Resultsmentioning

confidence: 99%

“…27 As a specific case of heat diffusion equation, the Poisson equation has been used extensively in computer vision, especially in the field of image editing and shape processing (please refer to Ref. We also plot saliency maps of eight other state-of-the-art methods [e.g., CA, 11 CB, 14 LR, 18 RC, 13 XIE, 20 SM, 19 MR, 25 and LESD (Ref. This arises naturally as a necessary condition in the solution of certain variational problems and the resulting partial differential equation can be easily solved by standard numerical solvers.…”

Section: Brief Review For Heat Diffusion In Imagementioning

confidence: 99%

“…To provide a consistent visual comparison, here we plot the qualitative results of the eight most representative saliency object detection type methods [i.e., RC, 13 CA, 11 CB, 14 XIE, 20 LR, 18 SM, 19 MR, 25 and LESD (Ref. 26)] on images with either single or multiple object(s).…”

Section: Qualitative Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

Diffuse visual attention for saliency detection

Liu

Zhong

Cao

et al. 2015

J. Electron. Imaging

View full text Add to dashboard Cite

This paper presents a physical perspective to understand visual saliency on the scene and develops an anisotropic heat diffusion based formulation, named visual attention diffusion (VAD), to detect salient regions in natural images. Our idea is based on the assumption that the visual attention can be diffused from a part of the most representative salient elements to other salient regions for a given image. In particular, we first design a corner-points-driven technique to simultaneously identify candidate foreground and background regions on the image. Then both the local object location and the nonlocal background structure can be estimated accordingly. Finally, we design a geometry-driven anisotropic Poisson system with Dirichlet boundary for saliency detection which uses the representative salient elements in the candidate foreground as heat sources and both local and nonlocal priors as guidance. After heat diffusion reaches a stable state, salient regions can be easily detected based on the temperatures (i.e., score value) of the image elements. Experiments show that the proposed system can produce more precise and reliable results compared to state-of-the-art saliency detectors. © 2015 SPIE and IS&T [Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 05/15/2015 Terms of Use: http://spiedl.org/terms Risheng Liu received his BSc and PhD degrees in mathematics from Dalian University of Technology in 2007 and 2012. He was a visiting scholar at Carnegie Mellon University from 2010 to 2012. He is currently a lecturer in the School of Software Technology at Dalian University of Technology. His research interests include machine learning and computer vision. He is a member of IEEE. Guangyu Zhong received her BSc in mathematics from Dalian Liu et al.: Diffuse visual attention for saliency detection Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 05/15/2015 Terms of Use: http://spiedl.org/terms Technology. Her research interests include machine learning, computer vision, and pattern recognition. Junjie Cao received his BSc and PhD degrees in mathematics from Dalian University of Technology in 2007 and 2012. He is currently a lecturer at Dalian Liu et al.: Diffuse visual attention for saliency detection Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 05/15/2015 Terms of Use: http://spiedl.org/terms

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Brief Review For Heat Diffusion In Imagementioning

confidence: 99%

See 1 more Smart Citation

Diffuse visual attention for saliency detection

Liu

Zhong

Cao

et al. 2015

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…To mimic this property, the saliency detection algorithms are designed to identify the most informative regions of an image by using the priors and characteristics of the HVS. [17][18][19][20][21][22][23][24][25][26] Because this saliency information is useful for many applications of computer vision as stated in the introduction, many researchers proposed various kinds of prior to detect salient region such as center prior, local and global contrast prior, background characteristics, boundary prior, and so on. In this section, we introduce just a few methods among numerous works, which are quite fast and easily exploited for our saliency-based backlight control application: Yang et al 22 adopted a semi-supervised learning scheme, but their algorithm is based on simple node ranking considering whether a node belongs to either background or saliency.…”

Section: Saliency Detection Algorithmmentioning

confidence: 99%

“…In this section, we introduce just a few methods among numerous works, which are quite fast and easily exploited for our saliency-based backlight control application: Yang et al 22 adopted a semi-supervised learning scheme, but their algorithm is based on simple node ranking considering whether a node belongs to either background or saliency. Yang et al 23 improved the center prior by introducing a convex-hull based center prior that estimates the location of salient objects as the interior of convex-hull. Also, contrast prior is used as one of the most powerful priors, because humans generally pay attention to high contrast regions.…”

Section: Saliency Detection Algorithmmentioning

confidence: 99%

Human visual perception‐based localized backlight scaling method for high dynamic range LCDs

2016

View full text Add to dashboard Cite

This paper presents a backlight control algorithm for liquid crystal display devices, which considers the human visual properties that we are usually attracted to the saliencies in a scene. The saliency means regions or objects that have different contrast or color from the surrounding, and thus attract our attention, which can be measured in various ways from each pixel value and its relation with the surrounding ones. Hence, by keeping or boosting the backlight of salient regions while suppressing in others, the quality of salient regions and overall contrast are enhanced. In addition, power can be saved by backlight dimming in non‐salient regions, without loss of overall quality in terms of human visual perception. In this backlight control process, the amount of energy consumption is regulated so that the proposed method consumes less than or equal energy as before, by developing a power management algorithm based on the bit rate control strategies of MPEG2 video encoders. Precisely, the energy consumption in each backlight unit is controlled by a parameter, so that the sum of energies of overall backlight units is kept within a limit.

show abstract

P-71: Encoding Saliency Information in Video Sequences and Its Application to Backlight Scaling of High Dynamic Range (HDR) LCDs

Park

Lee

Hwang

et al. 2016

SID Symposium Digest of Technical Papers

View full text Add to dashboard Cite

This paper presents a framework that encodes saliency information in a video sequence at the encoder and uses this information for backlight scaling at the decoder. The saliency region in a scene is extracted and encoded as a supplementary information of H.264/AVC codec in our scheme. The saliency information decoded at the receiver is used to highlight the saliencies in the scene, which enhances the dynamic range of output images.

show abstract

Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior

Cited by 242 publications

References 11 publications

Diffuse visual attention for saliency detection

Diffuse visual attention for saliency detection

Human visual perception‐based localized backlight scaling method for high dynamic range LCDs

P-71: Encoding Saliency Information in Video Sequences and Its Application to Backlight Scaling of High Dynamic Range (HDR) LCDs

Contact Info

Product

Resources

About