Saliency detection via Cellular Automata

Qin, Yao; Lu, Huchuan; Xu, Yiqun; He, Wang

doi:10.1109/cvpr.2015.7298606

Cited by 165 publications

(40 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research on bottom-up visual attention model begins to shift to search salient object on the scene rather than predict the eye fixation, thus it is marked as the second wave called salient object detection model. The model is initiated by Liu et al [39] and continuous improvements [51]- [56] have been made. Recently, the rising of deep learning influences the bottomup salient object detection model into top-down or hybrid approach.…”

Section: Bottom-up Visual Saliencymentioning

confidence: 99%

See 1 more Smart Citation

Bottom-up visual attention model for still image: a preliminary study

Prahara

Murinto

Ismi

2020

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

The philosophy of human visual attention is scientifically explained in the field of cognitive psychology and neuroscience then computationally modeled in the field of computer science and engineering. Visual attention models have been applied in computer vision systems such as object detection, object recognition, image segmentation, image and video compression, action recognition, visual tracking, and so on. This work studies bottom-up visual attention, namely human fixation prediction and salient object detection models. The preliminary study briefly covers from the biological perspective of visual attention, including visual pathway, the theory of visual attention, to the computational model of bottom-up visual attention that generates saliency map. The study compares some models at each stage and observes whether the stage is inspired by biological architecture, concept, or behavior of human visual attention. From the study, the use of low-level features, center-surround mechanism, sparse representation, and higher-level guidance with intrinsic cues dominate the bottom-up visual attention approaches. The study also highlights the correlation between bottom-up visual attention and curiosity.

show abstract

Section: Bottom-up Visual Saliencymentioning

confidence: 99%

“…Qin et al (CA) [56] proposed a dynamic evolution model to detect saliency called cellular automata. Input image is segmented into small superpixels using SLIC.…”

Section: Liu Et Al (St)mentioning

confidence: 99%

Bottom-up visual attention model for still image: a preliminary study

Prahara

Murinto

Ismi

2020

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

show abstract

“…Considering that the evolution of a cell will produce extreme results when c i is too high or too low, we follow Ref. 46 to convert the value of c i to ½γ; γ þ η by E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 0 5 ; 3 2 6 ; 4 7 5…”

Section: Foreground Region Optimizationmentioning

confidence: 99%

Saliency-based foreground trajectory extraction using multiscale hybrid masks for action recognition

et al. 2018

View full text Add to dashboard Cite

Action recognition in realistic scenes is a challenging task in the field of computer vision. Although trajectory-based methods have demonstrated promising performance, background trajectories cannot be filtered out effectively, which leads to a reduction in the ratio of valid trajectories. To address this issue, we propose a saliency-based sampling strategy named foreground trajectories on multiscale hybrid masks (HM-FTs). First, the motion boundary images of each frame are calculated to derive the initial masks. According to the characteristics of action videos, image priors and the synchronous updating mechanism based on cellular automata are exploited to generate an optimized weak saliency map, which will be integrated with a strong saliency map obtained via the multiple kernels boosting algorithm. Then, multiscale hybrid masks are achieved through the collaborative optimization strategy and masks intersection. The compensation schemes are designed to extract a set of foreground trajectories that are closely related to human actions. Finally, a hybrid fusion framework for combining trajectory features and pose features is constructed to enhance the recognition performance. The experimental results on two benchmark datasets demonstrate that the proposed method is effective and improves upon most of the state-of-the-art algorithms.

show abstract

“…The weight

w_{i, j}^{k}

between two connecting superpixels

normals p_{i}

and

normals p_{j}

belonging to the same cluster

C_{k}

are determined by the dissimilarity using their features (i.e. the mean values in the CIE LAB colour space) as defined in [28]

w_{i, j}^{k} = ({, \begin{matrix} right leftthickmathspace.5em \\ \exp ()(, \frac{- d_{c} false(normals p_{i}, normals p_{j} false)}{σ_{c}^{2}}), j \in normalΩ false(i false) and i, j \in C_{k} \\ 0, otherwise \end{matrix})

where

normalΩ false(i false)

indicates the set of two‐layer neighbourhood [24] of superpixels

normals p_{i}

, which is the direct neighbouring nodes of superpixels

normals p_{i}

, as well as the direct neighbours of those neighbouring nodes. Meanwhile, in order to normalise the affinity matrix

bold-italicW = {false[w_{i, j}^{k} false]}_{N \times N}

, a degree matrix

D_{i, j}^{k}

is constructed

D_{i, j}^{k} = ({, \begin{matrix} right leftthickmathspace.5em \\ \sum_{j} w_{i, j}^{k}, i = j \\ 0 \end{matrix})

…”

Section: Scb: Salient Object Detection Modelmentioning

confidence: 99%

“…Li et al [8] proposed a saliency detection algorithm by combining dense and sparse appearance reconstructions errors model. Qin et al [24] presented a dynamic evolution model based on cellular automata to detect the saliency object. Sun et al [25] proposed a Markov absorption probability based saliency detection model within the random walk framework via image left and top sides as background cues.…”

Section: Related Workmentioning

confidence: 99%

Saliency detection using adaptive background template

Lin

Zhou

et al. 2017

IET Computer Vision

View full text Add to dashboard Cite

Since most existing saliency detection models are not suitable for the condition that the salient objects are near at the image border, the authors propose a saliency detection approach based on adaptive background template (SCB) despite of the position of the salient objects. First, a selection strategy is presented to establish the adaptive background template by removing the potential saliency superpixels from the image border regions, and the initial saliency map is obtained. Second, a propagation mechanism based on K-means algorithm is designed for maintaining the neighbourhood coherence of the above saliency map. Finally, a new spatial prior is presented to integrate the saliency detection results by aggregating two complementary measures such as image centre preference and the background template exclusion. Comprehensive evaluations on six benchmark datasets indicate that the authors' method outperforms other state-of-the-art approaches. In addition, a new dataset containing 300 challenging images is constructed for evaluating the performance of various salient object detection methods.

show abstract

Saliency detection via Cellular Automata

Cited by 165 publications

References 43 publications

Bottom-up visual attention model for still image: a preliminary study

Bottom-up visual attention model for still image: a preliminary study

Saliency-based foreground trajectory extraction using multiscale hybrid masks for action recognition

Saliency detection using adaptive background template

Contact Info

Product

Resources

About