Multiple Kernel Graph Cut for SAR Image Change Detection

Jia, Lu; Zhang, Tiantian; Fang, Jing; Dong, Feibiao

doi:10.3390/rs13040725

Cited by 8 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph-cut is a popular energy optimization algorithm that has been widely used in medical image segmentation [45,46], hyperspectral image classification [47,48], SAR image classification [49,50], multi-view clustering [51][52][53], and so on. Because there are still some noise and wrong predictions in the 3D salt results predicted by the 3D U-net model, we utilize a graph-cut with improved edge weights to obtain more refined results.…”

Section: Three-dimensional Graph-cutmentioning

confidence: 99%

SaltISNet3D: Interactive Salt Segmentation from 3D Seismic Images Using Deep Learning

2023

View full text Add to dashboard Cite

Salt interpretation using seismic data is essential for structural interpretation and oil and gas exploration. Although deep learning has made great progress in automatic salt image segmentation, it is often difficult to obtain satisfactory results in complex situations. Thus, interactive segmentation with human intervention can effectively replace the fully automatic method. However, the current interactive segmentation cannot be directly applied to 3D seismic data and requires a lot of human interaction. Because it is difficult to collect 3D seismic data containing salt, we propose a workflow to simulate salt data and use a large amount of 3D synthetic salt data for training and testing. We use a 3D U-net model with skip connections to improve the accuracy and efficiency of salt interpretation. This model takes 3D seismic data volume with a specific size as an input and generates a salt probability volume of the same size as an output. To obtain more detailed salt results, we utilize a 3D graph-cut to ameliorate the results predicted by the 3D U-net model. The experimental results indicate that our method can achieve more efficient and accurate segmentation of 3D salt bodies than fully automatic methods.

show abstract

Section: Three-dimensional Graph-cutmentioning

confidence: 99%

SaltISNet3D: Interactive Salt Segmentation from 3D Seismic Images Using Deep Learning

2023

View full text Add to dashboard Cite

show abstract

“…In contrast to a valid metric, a generalized metric or a pseudometric (e.g. GED), does not strictly adhere to at least one of the following conditions: non-negativity, identity of indiscernibles, symmetry, positive definiteness, and triangle inequality [21]. For the sake of brevity, we use the term "metric" to denote "generalized metric" in this paper.…”

Section: Related Workmentioning

confidence: 99%

“…where Π(G 1 , G 2 ) denotes the set of all possible edit paths from G 1 to G 2 . The computation of the exact GED is a NP-hard problem [21]. In practice, a suboptimal approximation algorithm is often used and a cost matrix C is often defined for the edit operations.…”

Section: Graph Edit Distances and Edit Costsmentioning

confidence: 99%

“…By fixing the embedding space as a kernel space, we align the distances in it and graph space as proposed in Section 3.3. The pre-image problem can then be recast as a graph generation problem [21]. We first optimize edit cost constants according to the embedded kernel space, and then we use these optimized edit costs, and take advantage of recent advances where the proposed iterative alternate minimization procedure (IAM) allows generating new graphs [33].…”

Section: Graph Generations: a Pre-image Examplementioning

confidence: 99%

See 1 more Smart Citation

Bridging Distinct Spaces in Graph-Based Machine Learning

Jia,

Ning,

Gaüzère

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Graph-based machine learning, encompassing Graph Edit Distances (GEDs), Graph Kernels, and Graph Neural Networks (GNNs), offers extensive capabilities and exciting potential. While each model possesses unique strengths for graph challenges, interrelations between their underlying spaces remain under-explored. In this paper, we introduce a novel framework for bridging these distinct spaces via GED cost learning. A supervised metric learning approach serves as an instance of this framework, enabling space alignment through pairwise distances and the optimization of edit costs. Experiments reveal the framework's potential for enhancing varied tasks, including regression, classification, and graph generation, heralding new possibilities in these fields.

show abstract

“…In [27], a modified Markov random field (MRF) model, which combines the nonlocal means similarity weights, is proposed to preserve spatial details and reduce speckle effects in urban change detection. Moreover, researchers apply the multiple kernel graph cuts to extract the changed areas on high-dimensional feature space [28]. For purpose of establishing a broader context relation, the stereograph cuts algorithm is constructed between bi-temporal SAR to generate a smooth change map [29].…”

Section: Introductionmentioning

confidence: 99%

SAR Image Change Detection Based on Heterogeneous Graph With Multiattributes and Multirelationships

Jun

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

The performance of change detection between synthetic aperture radar (SAR) images mainly depends on the selection and utilization of image attributes. Nevertheless, most existing change detection approaches merely take the intensity attribute into consideration, constraining their capacities of detecting changes in complex situations. To solve this problem, this study develops an unsupervised SAR image change detection approach based on heterogeneous graph with multi-attributes and multi-relationships. First, the structural attribute, obtained by removing the complex texture, can be used to reflect the overall features of a SAR image. A heterogeneous graph is then constructed to encode the structural and intensity attributes as vertices, and two types of edges are hence connected to capture the intra-relationships and inter-relationships from these different attributes. With the support of this graph, the hyper-adjacency characteristics are proposed to quantify the multi-relationships and describe the global heterogeneous information. Constructing heterogeneous graphs respectively on bi-temporal SAR images, the changes of both intensity and structural attributes can be measured via comparing the hyper-adjacency characteristics of the bi-temporal graphs, thereby generating a difference image with good separability. Finally, the change map is obtained by cutting off the weakly related edges of heterogeneous graph on the difference image. Experiments on four real SAR datasets prove the effectiveness of the proposed graph-driven approach in improving the accuracy and robustness of change detection.

show abstract

Multiple Kernel Graph Cut for SAR Image Change Detection

Cited by 8 publications

References 22 publications

SaltISNet3D: Interactive Salt Segmentation from 3D Seismic Images Using Deep Learning

SaltISNet3D: Interactive Salt Segmentation from 3D Seismic Images Using Deep Learning

Bridging Distinct Spaces in Graph-Based Machine Learning

SAR Image Change Detection Based on Heterogeneous Graph With Multiattributes and Multirelationships

Contact Info

Product

Resources

About