Depth saliency based on anisotropic center-surround difference

Ju, Ran; Ge, Ling; Geng, Wenjing; Ren, Tongwei; Wu, Guorong

doi:10.1109/icip.2014.7025222

Cited by 408 publications

(365 citation statements)

References 18 publications

Supporting

Mentioning

362

Contrasting

Unclassified

Order By: Relevance

“…Borji et al [7] showed that most of the existing image datasets for saliency detection had center-bias. Some salient object detection methods also used this characteristic to improve their performance [24]. However, these works didn't provide further quantitative evaluation of the effect of location information in saliency detection.…”

Section: Introductionmentioning

confidence: 97%

How important is location information in saliency detection of natural images

Ren

Liu

et al. 2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Location information, i.e., the position of content in image plane, is considered as an important supplement in saliency detection. The effect of location information is usually evaluated by integrating it with the selected saliency detection methods and measuring the improvement, which is highly influenced by the selection of saliency methods. In this paper, we provide direct and quantitative analysis of the importance of location information for saliency detection in natural images. We firstly analyze the relationship between content location and saliency distribution on four public image datasets, and validate the distribution by simply treating location based Gaussian distribution as saliency map. To further validate the effectiveness of location information, we propose a location based saliency detection approach, which completely initializes saliency maps with location information and propagate saliency among patches based on color similarity, and discuss the robustness Multimed Tools Appl (2016) 75:2543-2564 of location information's effect. The experimental results show that location information plays a positive role in saliency detection, and the proposed method can outperform most state-of-the-art saliency detection methods and handle natural images with different object positions and multiple salient objects.

show abstract

Section: Introductionmentioning

confidence: 97%

How important is location information in saliency detection of natural images

Ren

Liu

et al. 2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Let us compare our saliency model (BFSD) with a number of existing state-of-the-art methods, including graphbased manifold ranking (GMR) [7]; multi-context deep learning (MC) [27]; multiscale deep CNN (MDF) [28]; anisotropic centre-surround difference (ACSD) [10]; saliency detection at low-level, mid-level, and high-level stages (LMH) [19]; and exploiting global priors (GP) [20], among which GMR, MC and MDF are developed for RGB images, LMH and GP for RGB-D images, and ACSD for depth images. All of the results are produced using the public codes that are offered by the authors of the previously mentioned literature reports.…”

Section: Compared Methodsmentioning

confidence: 99%

“…To test how well the performance of our proposed method generalizes to a different dataset for detecting salient object in RGB-D images, we evaluate it on the NJU-DS400 [10]. As discussed in experiment setting, the images of the NJU-DS400 are collected in different scenarios.…”

Section: Cross-dataset Generalizationmentioning

confidence: 99%

“…the salient regions were marked by hand. The NJU-DS400 dataset [10] includes We will analyse the 3D saliency situation in RGB-D images based on human judgement. In terms of the NLPR dataset [19], the 3D saliency is decided jointly by RGB images and depth images, as shown in Fig.…”

Section: Evaluation Datasetsmentioning

confidence: 99%

“…In addition to RGB information, depth has been shown to be one of the practical cues for extracting saliency. Furthermore, Ju et al proposed a novel saliency method that worked on depth images based on the anisotropic centre-surround difference [10]. In contrast to saliency detection for 2D images, the depth factor must be considered when performing saliency detection for RGB-D images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual saliency detection for RGB-D images under a Bayesian framework

Wang

Zhou

Jin

et al. 2018

IPSJ T Comput Vis Appl

View full text Add to dashboard Cite

In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes' theorem. By assuming that deep features are Gaussian distributions, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map. The Gaussian distribution parameters can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on RGB-D images from the NLPR dataset and NJU-DS400 dataset show that the proposed model performs better than other existing models.

show abstract

Learning based versus heuristic based: A comparative analysis of visual saliency prediction in immersive virtual reality

Aşkın

Çelikcan

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

While visual saliency has been used for various purposes in virtual reality (VR), the efforts to properly understand the saliency mechanism in VR remain insufficient. In this paper, we present an extensive comparative analysis of learning-based and heuristic-based approaches to visual saliency prediction in immersive VR experienced using head-mounted-displays with a particular focus on the contribution of the depth cue. To this end, we use three learning-based RGB-D image saliency detection methods and two heuristic-based RGB-D image saliency detection methods on a VR dataset curated from three distinct virtual environments under two-dimensional and three-dimensional viewing conditions. Additionally, we extend the analysis by including a heuristic-based RGB video saliency detection method and its depth-infused version. The results acquired using these seven methods reveal the superiority of the learning-based RGB-D image saliency prediction methods in VR and validate the importance of the depth cue in the saliency prediction of virtual environments.

show abstract

Depth saliency based on anisotropic center-surround difference

Cited by 408 publications

References 18 publications

How important is location information in saliency detection of natural images

How important is location information in saliency detection of natural images

Visual saliency detection for RGB-D images under a Bayesian framework

Learning based versus heuristic based: A comparative analysis of visual saliency prediction in immersive virtual reality

Contact Info

Product

Resources

About