A Deep Supervised Edge Optimization Algorithm for Salt Body Segmentation

Guo, Jiangtao; Xu, Linfeng; Ding, Jisheng; He, Bin; Dai, Shengxuan; Liu, Fangyu

doi:10.1109/lgrs.2020.3007258

Cited by 17 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, many studies put edge features into the network as a branch to optimize the loss function and further enhance the edge information of the segmentation results. Guo et al [4] designed an edge prediction branch to predict the boundary of the salt body, which guides feature learning through the supervision of boundary loss so that the network can distinguish the features on both sides of the semantic boundary. Although these methods can improve the edge blur of classification results to a certain extent, they cannot retard the misclassification phenomenon within the boundary.…”

Section: Introductionmentioning

confidence: 99%

BIBED-Seg: Block-in-Block Edge Detection Network for Guiding Semantic Segmentation Task of High-Resolution Remote Sensing Images

Sui

Bai

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Edge optimization of semantic segmentation results is a challenging issue in remote sensing image processing. This article proposes a semantic segmentation model guided by a blockin-block edge detection network named BIBED-Seg. This is a twostage semantic segmentation model, where edges are extracted first and then segmented. We do two key works: The first work is edge detection, and we present BIBED, a block-in-block edge detection network, to extract the accurate boundary features. Here, the edge detection of multiscale feature fusion is first realized by creating the block-in-block residual network structure and devising the multilevel loss function. Second, we add the channel and spatial attention module into the residual structure to improve high-resolution remote sensing images' boundary positioning and detection accuracy by focusing on their channel and spatial dimensions. Finally, we evaluate our method on International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam and Vaihingen data sets and obtain ODS F-measure of 0.6671 and 0.7432, higher than other excellent edge detection methods. The second work is two-stage segmentation. First, the proposed BIBED is individually pretrained, and subsequently, the pretrained model is introduced into the entire segmentation network to extract boundary features. In the second segmentation stage, the edge detection network is used to constrain semantic segmentation results by loss cycles and feature bootstrapping. Our best model obtains the OA of 90.2%, 87.7%, and 81.5%, the IOU of 76.0%, 69.6%, and 61.3% on the ISPRS and WHDLD datasets, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

BIBED-Seg: Block-in-Block Edge Detection Network for Guiding Semantic Segmentation Task of High-Resolution Remote Sensing Images

Sui

Bai

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Shi et al [35] propose a 3D CNN model to achieve salt interpretation in 3D seismic data that can capture salt features without manual input. Guo et al [36] propose a supervised deep learning method for effectively segmenting salt bodies. The method designs an edge-prediction branch to predict salt boundaries, which guides feature learning by supervising the loss function, thus distinguishing the features on both sides of the salt boundaries.…”

Section: Introductionmentioning

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

“…In an era where visual intelligence products are so widespread today, images occupy a dominant position in the traffic carrier.Image based applications can be found everywhere in our daily life.Image dehazing/deraining proposed by [79,27,80,25,88,26,87,40,86] can be important in autopilot of smart cars, object detection methods proposed by [30,6,7,53,10,31,32,54,55,33,74] can be used in monitoring of transportation hubs and image segmentation methods [98,62,15,97,66,91,94,93,65,43,41] can be applied in medical imaging.However images are transmitted with varying degrees of degradation in the quality of the images eventually received by the observers -mostly humansat the receiving end due to the hardware and software conditions of the transmission channel or the receiving device, as well as lossy compression, e.g. image JPEG compression can cause blurring and ringing effects.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Survey on Image Aesthetic Quality Assessment

Yang

Shi

et al. 2019

2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)

View full text Add to dashboard Cite

Image quality assessment(IQA) is of increasing importance for image-based applications. Its purpose is to establish a model that can replace humans for accurately evaluating image quality. According to whether the reference image is complete and available, image quality evaluation can be divided into three categories: full-reference(FR), reduced-reference(RR), and non-reference(NR) image quality assessment. Due to the vigorous development of deep learning and the widespread attention of researchers, several non-reference image quality assessment methods based on deep learning have been proposed in recent years, and some have exceeded the performance of reduced -reference or even full-reference image quality assessment models. This article will review the concepts and metrics of image quality assessment and also video quality assessment, briefly introduce some methods of full-reference and semi-reference image quality assessment, and focus on the non-reference image quality assessment methods based on deep learning. Then introduce the commonly used synthetic database and real-world database. Finally, summarize and present challenges.Preprint. Under review.

show abstract

A Deep Supervised Edge Optimization Algorithm for Salt Body Segmentation

Cited by 17 publications

References 29 publications

BIBED-Seg: Block-in-Block Edge Detection Network for Guiding Semantic Segmentation Task of High-Resolution Remote Sensing Images

BIBED-Seg: Block-in-Block Edge Detection Network for Guiding Semantic Segmentation Task of High-Resolution Remote Sensing Images

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

A Comprehensive Survey on Image Aesthetic Quality Assessment

Contact Info

Product

Resources

About