Salient Object Detection with Complex Scene Based on Cognitive Neuroscience

Zhu, Changan; Li, Ge; Wang, Wenmin; Wang, Ronggang

doi:10.1109/bigmm.2017.22

Cited by 13 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RGB-D saliency computation is a rapidly growing field and offers object detection and attention prediction in a manner that is robust to appearance. Therefore, some algorithms [12,16,44,66,69] adopt depth cues to deal with the challenging scenarios. In [69], Zhu et al propose a framework based on the cognitive neuroscience and use depth cues to represent the depthes of real scenarios.…”

Section: Center Prior Based Methodsmentioning

confidence: 99%

“…In contrary, bottom-up models [35,46,50,67,68] do not require any prior knowledge, such as object categories, to obtain saliency maps by using low level features based on center-surround contrasts. They compute the feature distinctness of a target region, e.g., pixels, patches or superpixels and then compare to its surrounding regions locally or globally.…”

Section: Traditional Saliency Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection

Zhu¹,

Zhang²,

Li³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Saliency detection aims to detect the most attractive objects in images and is widely used as a foundation for various applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel priors. First, we generate an initial saliency map based on a color saliency map and a depth saliency map of a given RGB-D image. Then, we generate a center-dark channel map based on center saliency and dark channel priors. Finally, we fuse the initial saliency map with the center dark channel map to generate the final saliency map. Extensive evaluations over four benchmark datasets demonstrate that our proposed method performs favorably against most of the state-of-the-art approaches. Besides, we further discuss the application of the proposed algorithm in small target detection and demonstrate the universal value of center-dark channel priors in the field of object detection. CCS Concepts: • General and reference → Cross-computing tools and techniques; • Computer systems organization → Applications-Computer vision; • Image Processing and Computer → Scene Analysis-Object recognition;

show abstract

Section: Center Prior Based Methodsmentioning

confidence: 99%

Section: Traditional Saliency Algorithmmentioning

confidence: 99%

Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection

Zhu¹,

Zhang²,

Li³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Firstly, it is originally defined as a task of predicting eye-fixations on images [11]. Secondly, researchers use the term to refer to salient object estimation or salient region detection [6,35,65]. Here, the task is extended to identify the region, containing the salient object, which is a binary segmentation task for salient object extraction.…”

Section: Introductionmentioning

confidence: 99%

Saliency from High-Level Semantic Image Features

et al. 2020

View full text Add to dashboard Cite

Top-down semantic information is known to play an important role in assigning saliency. Recently, large strides have been made in improving state-of-the-art semantic image understanding in the fields of object detection and semantic segmentation. Therefore, since these methods have now reached a high-level of maturity, evaluation of the impact of high-level image understanding on saliency estimation is now feasible. We propose several saliency features which are computed from object detection and semantic segmentation results. We combine these features with a standard baseline method for saliency detection to evaluate their importance. Experiments demonstrate that the proposed features derived from object detection and semantic segmentation improve saliency estimation significantly. Moreover, they show that our method obtains state-of-theart results on (FT, ImgSal, and SOD datasets) and obtains competitive results on four other datasets (ECSSD, PASCAL-S, MSRA-B, and HKU-IS).

show abstract

“…Recently, advances in 3D data acquisition techniques have motivated the adoption of structural features, improving the discrimination between different objects with the similar appearance. some algorithms [19,15,5,6,44,40] adopt depth cue to deal with the challenging scenarios. In [19], Zhu et al propose a framework based on cognitive neuroscience, and use depth cue to represent the depth of real field.…”

mentioning

confidence: 99%

“…some algorithms [19,15,5,6,44,40] adopt depth cue to deal with the challenging scenarios. In [19], Zhu et al propose a framework based on cognitive neuroscience, and use depth cue to represent the depth of real field. In [5], Cheng et al compute salient stimuli in both color and depth spaces.…”

mentioning

confidence: 99%

A multilayer backpropagation saliency detection algorithm and its applications

Zhu

2018

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Saliency detection is an active topic in the multimedia field. Most previous works on saliency detection focus on 2D images. However, these methods are not robust against complex scenes which contain multiple objects or complex backgrounds. Recently, depth information supplies a powerful cue for saliency detection. In this paper, we propose a multilayer backpropagation saliency detection algorithm based on depth mining by which we exploit depth cue from three different layers of images. The proposed algorithm shows a good performance and maintains the robustness in complex situations. Experiments results show that the proposed framework is superior to other existing saliency approaches. Besides, we give two innovative applications by this algorithm, such as scene reconstruction from multiple images and small target object detection in video.

show abstract

Salient Object Detection with Complex Scene Based on Cognitive Neuroscience

Cited by 13 publications

References 14 publications

Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection

Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection

Saliency from High-Level Semantic Image Features

A multilayer backpropagation saliency detection algorithm and its applications

Contact Info

Product

Resources

About