2020
DOI: 10.1016/j.patcog.2020.107532
|View full text |Cite
|
Sign up to set email alerts
|

Image segmentation using dense and sparse hierarchies of superpixels

Abstract: We investigate the intersection between hierarchical and superpixel image segmentation. Two strategies are considered: (i) the classical region merging, that creates a dense hierarchy with a higher number of levels, and (ii) the recursive execution of some superpixel algorithm, which generates a sparse hierarchy with fewer levels. We show that, while dense methods can capture more intermediate or higher-level object information, sparse methods are considerably faster and usually with higher boundary adherence … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
10
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 23 publications
(11 citation statements)
references
References 44 publications
(96 reference statements)
0
10
0
Order By: Relevance
“…In order to analyze the effectiveness of the proposed method, the Boundary Recall (BR) and Achievement Segmentation Accuracy (ASA) of ours and the state-of-the-art superpixel segmentation methods are shown in Figure 12. CSGBA [20], ISF [21], RISF [22] and SNIC [23] are the examples of the state-of-the-art methods.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…In order to analyze the effectiveness of the proposed method, the Boundary Recall (BR) and Achievement Segmentation Accuracy (ASA) of ours and the state-of-the-art superpixel segmentation methods are shown in Figure 12. CSGBA [20], ISF [21], RISF [22] and SNIC [23] are the examples of the state-of-the-art methods.…”
Section: Discussionmentioning
confidence: 99%
“…The SEEDS, SLIC, ERS and LSC are examples of the classical methods. CSGBA [ 20 ], ISF [ 21 ], RISF [ 22 ] and SNIC [ 23 ] are the examples of the state-of-the-art methods.…”
Section: Figurementioning
confidence: 99%
See 1 more Smart Citation
“…As mentioned in various superpixel studies [14,38], boundary adherence is the primary property in the superpixel evaluation system. To quantitatively evaluate the performance of the superpixel segmentation algorithms, two commonly used evaluation metrics were taken into account: boundary recall (BR) and under-segmentation error (USE).…”
Section: Benchmarkmentioning
confidence: 99%
“…Automatic superpixel segmentation has received widespread attention in the last decade, and can be broadly divided into two processing strategies [11,12]: graph-based algorithms, and gradient-based algorithms. Graph-based algorithms [9,13,14] aim to construct an undirected graph and minimize a defined cost function to generate superpixels. These methods treat pixels as nodes in the graph, and the edge weights between adjacent nodes are proportional to the similarity between the two nodes.…”
mentioning
confidence: 99%