Stereo GrabCut: Interactive and Consistent Object Extraction for Stereo Images

Ju, Ran; Xu, Xiangyang; Yang, Yang; Wu, Guorong

doi:10.1007/978-3-319-03731-8_39

Cited by 11 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By saliency analysis, vision tasks are concentrated on a few regions of interests instead of entire images, which benefit many applications in both efficiency and effectiveness, e.g. image classification [1,2], object segmentation [3][4][5][6], image retargeting [7][8][9][10], adaptive image compression [11,12], content-based image retrieval [13,14] and quality assessment [15,16].…”

Section: Introductionmentioning

confidence: 99%

Depth-aware salient object detection using anisotropic center-surround difference

Liu

Ren

et al. 2015

Signal Processing: Image Communication

Self Cite

117

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Depth-aware salient object detection using anisotropic center-surround difference

Liu

Ren

et al. 2015

Signal Processing: Image Communication

Self Cite

117

View full text Add to dashboard Cite

“…Only a few methods completely ignore location information, such as calculating the distance between the color of each pixel and the mean color of the whole image as saliency value [1]. Most existing methods implicitly use location information, such as considering spatial relationships between regions [12], or explicitly use location information, such as combining center-bias to saliency detection results [23], to improve their performance. However, quantitative analysis and evaluation of the effectiveness of location information in saliency detection is still lacking.…”

Section: Related Workmentioning

confidence: 98%

“…Fixation prediction aims to simulate the attention mechanism of human visual system by highlighting a few salient points [8]. Different to fixation prediction, salient object detection aims to extract the entire salient objects [12], which is more suitable to multimedia applications, such as object segmentation [11,23], image classification [46,47], object tracking [40,49], image and video annotation [3,37,43], information retrieval [13,45,48] and content-aware editing [38,39,44].…”

Section: Introductionmentioning

confidence: 99%

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

“…In [24] Price et al proposed a framework to simultaneously segment both views by integrating dense stereo correspondence term into the graph cuts model. The model is adopted by [16] and [23]. In [33] it has been shown that sparse correspondence can achieve comparable result.…”

Section: Related Workmentioning

confidence: 99%

“…Contour Correspondence Input: = { 1 , 2 , ..., } Output: ′ = { 1 ′ , 2 ′ , ..., ′ } 1: // State transition matrix calculation 2: for each cell ( , 14: for = − 1 to 1 do 15:= index(min ( , +1 −1 , , +1 , , +1 +1 ))16:′ = − 17: end forin blue. Each node ( , ) in the path can be mapped to a pixel −…”

mentioning

confidence: 99%

StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images

Ren

2015

2015 IEEE International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Consistent object extraction plays an essential role for stereo image editing with the population of stereoscopic 3D media. Most previous methods perform segmentation on entire images for both views using dense stereo correspondence constraints. We find that for such kind of methods the computation is highly redundant since the two views are near-duplicate. Besides, the consistency may be violated due to the imperfectness of current stereo matching algorithms. In this paper, we propose a contour based method which searches for consistent object contours instead of regions. It integrates both stereo correspondence and object boundary constraints into an energy minimization framework. The proposed method has several advantages compared to previous works. First, the searching space is restricted in object boundaries thus the efficiency significantly improved. Second, the discriminative power of object contours results in a more consistent segmentation. Furthermore, the proposed method can effortlessly extend existing single-image segmentation methods to work in stereo scenarios. The experiment on the Adobe benchmark shows superior extraction accuracy and significant improvement of efficiency of our method to state-of-the-art. We also demonstrate in a few applications how our method can be used as a basic tool for stereo image editing.

show abstract

Stereo GrabCut: Interactive and Consistent Object Extraction for Stereo Images

Cited by 11 publications

References 12 publications

Depth-aware salient object detection using anisotropic center-surround difference

Depth-aware salient object detection using anisotropic center-surround difference

How important is location information in saliency detection of natural images

StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images

Contact Info

Product

Resources

About