Multi-object Graph-based Segmentation with Non-overlapping Surfaces

Jensen, Patrick M.; Dahl, Anders Bjorholm; Dahl, Vedrana Andersen

doi:10.1109/cvprw50498.2020.00496

Cited by 4 publications

(6 citation statements)

References 26 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We contribute 8 problems. ( 7) New problems performing multi-object image segmentation via surface fitting from two recent papers [53,57]. We contribute 9 problems using [53] and 8 using [57].…”

Section: Datasetsmentioning

confidence: 99%

“…( 7) New problems performing multi-object image segmentation via surface fitting from two recent papers [53,57]. We contribute 9 problems using [53] and 8 using [57]. (8) New problems performing graph matching from the recent paper [48].…”

Section: Datasetsmentioning

confidence: 99%

“…For the block-based algorithms, we split the graph into blocks in one of the following ways: For graphs based on an underlying image grid, we define blocks by recursively splitting the image grid along its longest axis. For the surface-based segmentation methods [53,57], we define blocks such that nodes associated with a surface are in their own block. For mesh segmentation, we compute the geodesic distance between face centers and then use agglomerative clustering to divide the nodes associated with each face into blocks.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Jensen

Jeppesen

Dahl

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Minimum cut/maximum flow (min-cut/max-flow) algorithms solve a variety of problems in computer vision and thus significant effort has been put into developing fast min-cut/max-flow algorithms. As a result, it is difficult to choose an ideal algorithm for a given problem. Furthermore, parallel algorithms have not been thoroughly compared. In this paper, we evaluate the state-of-the-art serial and parallel min-cut/max-flow algorithms on the largest set of computer vision problems yet. We focus on generic algorithms, i.e., for unstructured graphs, but also compare with the specialized GridCut implementation. When applicable, GridCut performs best. Otherwise, the two pseudoflow algorithms, Hochbaum pseudoflow and excesses incremental breadth first search, achieves the overall best performance. The most memory efficient implementation tested is the Boykov-Kolmogorov algorithm. Amongst generic parallel algorithms, we find the bottom-up merging approach by Liu and Sun to be best, but no method is dominant. Of the generic parallel methods, only the parallel preflow push-relabel algorithm is able to efficiently scale with many processors across problem sizes, and no generic parallel method consistently outperforms serial algorithms. Finally, we provide and evaluate strategies for algorithm selection to obtain good expected performance. We make our dataset and implementations publicly available for further research.

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Jensen

Jeppesen

Dahl

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, our experiments include the super resolution, texture restoration, deconvolution, decision tree field (DTF), and automatic labelling environment (ALE) datasets from [62]. Finally, we include problems from two recent papers [37,39] which perform multiobject image segmentation via surface fitting. Note that some datasets consist of many small problem instances which must be run in sequence.…”

Section: Datasetsmentioning

confidence: 99%

“…1) For graphs based on an underlying image grid, we define blocks by recursively splitting the image grid along its longest axis until we have the required number of blocks. 2) For the surface based segmentation methods [37,39],…”

Section: Datasetsmentioning

confidence: 99%

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Jensen¹,

Jeppesen²,

Dahl³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Minimum cut / maximum flow (min-cut/max-flow) algorithms are used to solve a variety of problems in computer vision and thus significant effort has been put into developing fast min-cut/max-flow algorithms. This makes it difficult to choose an optimal algorithm for a given problem -especially for parallel algorithms, which have not been thoroughly compared. In this paper, we review the state-of-the-art min-cut/max-flow algorithms for unstructured graphs in computer vision. We evaluate run time performance and memory use of various implementations of both serial and parallel algorithms on a set of graph cut problems. Our results show that the Hochbaum pseudoflow algorithm is the fastest serial algorithm closely followed by the Excesses Incremental Breadth First Search algorithm, while the Boykov-Kolmogorov algorithm is the most memory efficient. The best parallel algorithm is the adaptive bottom-up merging approach by Liu and Sun. Additionally, we show significant variations in performance between different implementations the same algorithms highlighting the importance of low-level implementation details. Finally, we note that existing parallel min-cut/max-flow algorithms can significantly outperform serial algorithms on large problems but suffers from added overhead on small to medium problems. Implementations of all algorithms are available at: github.com/patmjen/maxflow algorithms.

show abstract

Performance evaluation of salient object detection techniques

Ahmed

Gad

Aboutabl

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Recently, the detection and segmentation of salient objects that attract the attention of human visual in images is determined by using salient object detection (SOD) techniques. As an essential computer vision problem, SOD has increasingly attracted the researchers’ interest over the years. While a lot of SOD models and applications have been proposed, there is still a lack of deep understanding of the issues and achievements. A comprehensive study on the recent techniques of SOD is provided in this paper. Precisely, this paper presents a review of SOD techniques from various perspectives. Various image segmentation techniques are presented such as segmentation based on machine learning or deep learning, the second perspective concentrates on classifying them into supervised and unsupervised learning techniques and the last one based on manual approach, semi-automatic approach, and fully automatic approach and so on. Then, the paper presents a summarization of datasets used for SOD. Finally, analyses of SOD models and comparison results are presented.

show abstract

Multi-object Graph-based Segmentation with Non-overlapping Surfaces

Cited by 4 publications

References 26 publications

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

Performance evaluation of salient object detection techniques

Contact Info

Product

Resources

About