A high-resolution feature difference attention network for the application of building change detection

Wang, Xue; Du, Junhan; Tan, Kun; Ding, Jianwei; Liu, Zhaoxian; Pan, Chen; Han, Bo

doi:10.1016/j.jag.2022.102950

Cited by 27 publications

(16 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction is divided into pixel-based [27], [28], object-based [29], [30], [31] and feature-based [32], [33] based on the basic unit of processing. Pixel-level-based methods are similar to traditional image-transformation-based methods [34].…”

Section: B Deep Learning CD Methodsmentioning

confidence: 99%

Enhanced Self-Attention Network for Remote Sensing Building Change Detection

Liang

Hua

2023

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

View full text Add to dashboard Cite

The self-attention mechanism can break the limitation of the receptive field, model in a global scope, and extract global information efficiently. In this work, we propose a lightweight remote sensing building change detection model (ESACD). In the encoder, we use the enhanced self-attention layer, CoT layer, instead of the normal convolution operation. The CoT layer fuses the dynamic context with the static context. Compared with the ordinary convolutional layer, this strategy can fully mine the local features between the input keys to dynamically enhance the feature representation. Subsequently, we use dual attention to further mine the low-frequency information and high-frequency information of the images and the semantic features of interest to the model. Dual attention consists of the HiLo attention mechanism and the Tokenizer attention mechanism. HiLo extracts high-frequency information and low-frequency information through two branches. In the high-frequency branch, nonoverlapping windows are applied to the features for self-attention. In the low-frequency branch, average pooling is first performed on features before self-attention. After Tokenizer attention extracts the feature tokens that the model is interested in, it encodes its information and, then, converts the tokens into pixel-level features. Tokenizer attention realizes the efficient extraction of features and enhances the representation ability of the model. Finally, we fuse feature information to enhance the fluidity of information and improve accuracy. Through our experiments on two change detection datasets, ESACD has better performance than other state-of-the-art methods while maintaining fewer parameters.

show abstract

Section: B Deep Learning CD Methodsmentioning

confidence: 99%

Enhanced Self-Attention Network for Remote Sensing Building Change Detection

Liang

Hua

2023

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

View full text Add to dashboard Cite

show abstract

“…In order to better optimize the accuracy of adaptive threshold generation, we propose an adaptive threshold binary cross entropy loss function. The prediction value generated by the adaptive threshold is applied to the binary cross entropy loss function, as shown in formula (18).…”

Section: Adaptive Threshold Binary Cross-entropy Loss Functionmentioning

confidence: 99%

“…In order to deeply mine multi-scale and multi-level features and improve detection accuracy, LI [17] et al designed a pyramid attention layer by using the spatial attention mechanism. Wang et al [18] proposed a high-resolution feature differential attention network for change detection. The network introduces a multiresolution parallel structure, comprehensively utilizes image information of different resolutions, reduces the loss of spatial information, proposes a differential attention module, improves the sensitivity to differential information, and maintains the change information of buildings.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Change Detection Based on Multi-Level Diversity Feature Fusion

Xie,

2024

IEEE Access

View full text Add to dashboard Cite

Urban topographic changes have a crucial impact on the environment, which serves as the foundation for human survival. However, due to the different spectral response characteristics of various remote sensing satellite sensors and the presence of aging issues, the captured remote sensing images exhibit color imbalance under different seasons and lighting conditions. Existing change detection methods fail to establish the correlation between changed and unchanged information in color-imbalanced urban topographic remote sensing images, thereby reducing the utilization of feature extraction information. Additionally, using fixed thresholds for region determination may inaccurately and incompletely generate change areas. Therefore, this paper proposes a remote sensing image change detection method based on multi-level and multi-diversity feature fusion. Firstly, a ResNet-18 network is employed to extract dual-temporal features. Secondly, to enhance the discrimination between change and unchanged regions during feature extraction and improve the utilization of feature extraction information, a Diversity Feature Fusion Module (DFFM) is designed to reduce false alarms and omissions in the detection results. Furthermore, to effectively address the problem of boundary misjudgment in change areas caused by fixed thresholds, an Adaptive Threshold Module is devised to adaptively learn the texture features of change and unchanged regions, enabling the generation of more accurate thresholds for boundary determination, thereby improving the robustness of the algorithm model and alleviating false alarms. Finally, experimental tests demonstrate that our method achieves excellent performance in two public change detection datasets.

show abstract

“…Literature [4] proposes a fusion method of CRF and Deeplab networks, which provides a new idea for building change detection, but its feature localization is not accurate. Literature [5] proposed the Siamese_AUNet network, which combined Siamese and U-Net, and adopted double-branch U-Net coding in the encoder part, which improved the detection performance. However, the network structure was complex and the calculation efficiency was low.…”

Section: Introductionmentioning

confidence: 99%

Remote sensing image small target and moving target change detection method

Du,

Liu,

Zhang

et al. 2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

Multi-temporal remote sensing image change detection is an important research direction in the field of remote sensing, which has a wide range of applications in environmental monitoring, urban change, agricultural investigation, war symptoms prediction, military force deployment, military strike damage assessment and so on. In order to solve the difficult problem of change detection of some moving objects and small objects in remote sensing images, it is necessary to mine the global complex semantic information in the feature extraction stage, and the current research on this aspect is not in-depth. In this paper, a 3-branch TSPNet network based on Transformer structure and SKAttention mechanism is proposed. This model has advantages of high detection accuracy, full mining of global semantic information and high degree of refinement, which can realize fine detection and moving target detection. The model was tested on the CDD and Levi-CD datasets, and parameters such as F1 scores and mIoU outperformed other mainstream networks.

show abstract

A high-resolution feature difference attention network for the application of building change detection

Cited by 27 publications

References 33 publications

Enhanced Self-Attention Network for Remote Sensing Building Change Detection

Enhanced Self-Attention Network for Remote Sensing Building Change Detection

Remote Sensing Image Change Detection Based on Multi-Level Diversity Feature Fusion

Remote sensing image small target and moving target change detection method

Contact Info

Product

Resources

About