Minimum Barrier Salient Object Detection at 80 FPS

Zhang, Jianming; Sclaroff, Stan; Lin, Zhe; Shen, Xiaohui; Price, Brian; Mĕch, Radomír

doi:10.1109/iccv.2015.165

Cited by 386 publications

(235 citation statements)

References 32 publications

Supporting

Mentioning

234

Contrasting

Unclassified

Order By: Relevance

“…We compare our method with 6 state-of-the-art methods including the GS [29],SF [30],CP [31],PCA [32],CA [28],MB [33]on the MSRA10K,ASD and SED1 datasets.…”

Section: Experiments Resultsmentioning

confidence: 99%

Saliency Detection Combining Multi-layer Integration Algorithm with Background Prior and Energy Function

Xia

Zhang

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…We compare our method with 6 state-of-the-art methods including the GS [29],SF [30],CP [31],PCA [32],CA [28],MB [33]on the MSRA10K,ASD and SED1 datasets.…”

Section: Experiments Resultsmentioning

confidence: 99%

Saliency Detection Combining Multi-layer Integration Algorithm with Background Prior and Energy Function

Xia

Zhang

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Our experiments have shown that the MBD is stable to noise, seed point position [3,10,22,23]. The MBD has many interesting theoretical properties, and has been shown to be a potentially useful tool in image processing [3,7,10,22,25]. This paper collects and compares published results on the MBD and presents them in a unified framework.…”

Section: Introductionmentioning

confidence: 99%

“…The minimum barrier distance based on ρ is not smooth in the sense of [2,6] and, as a result, the obtained distance transforms is not error-free [3,14,22,25] with this approach. However, Zhang et al [25] gave an error bound and also showed that for a very restricted class of 2D images, the approach gives exact minimum barrier distance transforms, see Theorem 3 which is here adapted to the Dijkstra approximation algorithm. points is an α-connected set, then the absolute error in the distance map obtained by the Dijkstra approximation algorithm on f is strictly less than .…”

Section: Distance Transform Computation Of Discretization I ρmentioning

confidence: 99%

See 1 more Smart Citation

The Minimum Barrier Distance: A Summary of Recent Advances

Strand

Ciesielski

Malmberg

et al. 2017

Discrete Geometry for Computer Imagery

View full text Add to dashboard Cite

Abstract. In this paper we present an overview and summary of recent results of the minimum barrier distance (MBD), a distance operator that is a promising tool in several image processing applications. The theory constitutes of the continuous MBD in R n , its discrete formulation in Z n (in two different natural formulations), and of the discussion of convergence of discrete MBDs to their continuous counterpart. We describe two algorithms that compute MBD, one very fast but returning only approximate MBD, the other a bit slower, but returning the exact MBD. Finally, some image processing applications of MBD are presented and the directions of potential future research in this area are indicated.

show abstract

“…This distance has been shown very efficient to proceed to salient object segmentation [177,195]. A continuous version of this distance, the Dahu pseudo-distance, has then been proposed in [64]; note that this is not a distance but a pseudo-distance in the sense that it does not satisfy the identity of indiscernibles.…”

Section: The Dahu Pseudo-distancementioning

confidence: 99%

A Tutorial on Well-Composedness

2017

View full text Add to dashboard Cite

Due to digitization, usual discrete signals generally present topological paradoxes, such as the connectivity paradoxes of Rosenfeld. To get rid of those paradoxes, and to restore some topological properties to the objects contained in the image, like manifoldness, Latecki proposed a new class of images, called wellcomposed images, with no topological issues. Furthermore, well-composed images have some other interesting properties: for example, the Euler number is locally computable, boundaries of objects separate background from foreground, the tree of shapes is well-defined, and so on. Last, but not the least, some recent works in mathematical morphology have shown that very nice practical results can be obtained thanks to well-composed images. Believing in its prime importance in digital topology, we then propose this state-of-the-art of well-composedness, summarizing its different flavours, the different methods existing to produce well-composed signals, and the various topics that are related to well-composedness.

show abstract

Minimum Barrier Salient Object Detection at 80 FPS

Cited by 386 publications

References 32 publications

Saliency Detection Combining Multi-layer Integration Algorithm with Background Prior and Energy Function

Saliency Detection Combining Multi-layer Integration Algorithm with Background Prior and Energy Function

The Minimum Barrier Distance: A Summary of Recent Advances

A Tutorial on Well-Composedness

Contact Info

Product

Resources

About