Object-based change detection for VHR remote sensing images based on a Trisiamese-LSTM

Ran, Jing; Liu, Shuang; Gong, Zhaoning; Wang, Zhiheng; Guan, Hao; Gautam, Atul; Zhao, Wenji

doi:10.1080/01431161.2020.1734253

Cited by 22 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the FCM algorithm only sets the normalization constraint on the membership degree of a single sample, the noise data far away from the center of each subcategory still has a large membership degree, which makes the algorithm sensitive to noise and outliers [17][18][19][20]. In contrast, IFP-FCM and Graphics Interchange Format (GIFP) FCM, which are based on affiliation correction, introduce different affiliation penalty terms in the clustering objective function to achieve the correction of affiliation of a single sample to different subclasses, which improves the clustering performance of the algorithm to some extent, but both algorithms are still constrained by the affiliation normalization condition in the Complexity clustering iteration process [21][22][23].…”

Section: Algorithm False Identification Modelmentioning

confidence: 99%

[Retracted] False Financial Statement Identification Based on Fuzzy C‐Means Algorithm

2021

Complexity

View full text Add to dashboard Cite

Financial accountants falsify financial statements by means of financial techniques such as financial practices and financial standards, and when compared with conventional financial data, it is found that the falsified financial data often lack correlation or even contradict each other in terms of financial data indicators. At the same time, there are also inherent differences in reporting patterns from conventional financial data, but these differences are difficult to test manually. In this paper, the fuzzy C-means (FCM) clustering method is used to amplify these differences and thus identify false financial statements. In the proposed algorithm, firstly, the normalization constraint of the FCM clustering algorithm on the sum of affiliation of individual samples is relaxed to the constraint on the sum of affiliation of all samples, thus reducing the sensitivity of the algorithm to noise and isolated points; secondly, a new affiliation correction method is proposed to address the problem that the difference in affiliation is too large after the relaxation of the constraint. In the discussion of this paper, most of the information comes from the annual reports of companies, administrative penalty decisions of the Securities Regulatory Commission, and some information comes from research reports made by securities institutions, which are limited sources of information. The proposed method can correct the affiliation to a reasonable range, effectively avoiding the problem that some samples have too much affiliation and become a class of their own and also avoiding the problem that it is difficult to choose the termination threshold of the algorithm iteration due to too little affiliation, and can ensure that the constraint on the sum of affiliation of all samples is always satisfied during the iteration of the algorithm. The method has the characteristics of high recognition accuracy and has the significance of theoretical method innovation.

show abstract

Section: Algorithm False Identification Modelmentioning

confidence: 99%

[Retracted] False Financial Statement Identification Based on Fuzzy C‐Means Algorithm

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…Jing, R et al [160] developed a unique DL architecture for a CD consisting of a subnetwork and an LSTM sub-network that used spatial, spectral, and multiphase information to increase the CD capability in VHR RS images. The experiments revealed that the multiphase information extracted by the LSTM sub-network was essential for improving the accuracy of CD results.…”

Section: Deep Learning Based Semi-supervised Methods In Hyperspectral...mentioning

confidence: 99%

Deep Learning-Based Change Detection in Remote Sensing Images: A Review

et al. 2022

View full text Add to dashboard Cite

Images gathered from different satellites are vastly available these days due to the fast development of remote sensing (RS) technology. These images significantly enhance the data sources of change detection (CD). CD is a technique of recognizing the dissimilarities in the images acquired at distinct intervals and are used for numerous applications, such as urban area development, disaster management, land cover object identification, etc. In recent years, deep learning (DL) techniques have been used tremendously in change detection processes, where it has achieved great success because of their practical applications. Some researchers have even claimed that DL approaches outperform traditional approaches and enhance change detection accuracy. Therefore, this review focuses on deep learning techniques, such as supervised, unsupervised, and semi-supervised for different change detection datasets, such as SAR, multispectral, hyperspectral, VHR, and heterogeneous images, and their advantages and disadvantages will be highlighted. In the end, some significant challenges are discussed to understand the context of improvements in change detection datasets and deep learning models. Overall, this review will be beneficial for the future development of CD methods.

show abstract

“…To explore this possible information complementarity, this paper proposed the use of the analysis of variance-F value (ANOVA F)-spectral embedding strategy to analyze the changes in the ANOVA F values for different fusion combinations. Spectral embedding [ 42 ] was then used for fusion mapping. The softmax classifier was used for classification.…”

Section: Methodsmentioning

confidence: 99%

AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features

Huang

Tan

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

Cervical cancer is the fourth most common cancer in the world. Whole-slide images (WSIs) are an important standard for the diagnosis of cervical cancer. Missed diagnoses and misdiagnoses often occur due to the high similarity in pathological cervical images, the large number of readings, the long reading time, and the insufficient experience levels of pathologists. Existing models have insufficient feature extraction and representation capabilities, and they suffer from insufficient pathological classification. Therefore, this work first designs an image processing algorithm for data augmentation. Second, the deep convolutional features are extracted by fine-tuning pre-trained deep network models, including ResNet50 v2, DenseNet121, Inception v3, VGGNet19, and Inception-ResNet, and then local binary patterns and a histogram of the oriented gradient to extract traditional image features are used. Third, the features extracted by the fine-tuned models are serially fused according to the feature representation ability parameters and the accuracy of multiple experiments proposed in this paper, and spectral embedding is used for dimension reduction. Finally, the fused features are inputted into the Analysis of Variance-F value-Spectral Embedding Net (AF-SENet) for classification. There are four different pathological images of the dataset: normal, low-grade squamous intraepithelial lesion (LSIL), high-grade squamous intraepithelial lesion (HSIL), and cancer. The dataset is divided into a training set (90%) and a test set (10%). The serial fusion effect of the deep features extracted by Resnet50v2 and DenseNet121 (C5) is the best, with average classification accuracy reaching 95.33%, which is 1.07% higher than ResNet50 v2 and 1.05% higher than DenseNet121. The recognition ability is significantly improved, especially in LSIL, reaching 90.89%, which is 2.88% higher than ResNet50 v2 and 2.1% higher than DenseNet121. Thus, this method significantly improves the accuracy and generalization ability of pathological cervical WSI recognition by fusing deep features.

show abstract

Object-based change detection for VHR remote sensing images based on a Trisiamese-LSTM

Cited by 22 publications

References 41 publications

[Retracted] False Financial Statement Identification Based on Fuzzy C‐Means Algorithm

[Retracted] False Financial Statement Identification Based on Fuzzy C‐Means Algorithm

Deep Learning-Based Change Detection in Remote Sensing Images: A Review

AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features

Contact Info

Product

Resources

About