Building change detection using the parallel spatial-channel attention block and edge-guided deep network

Eftekhari, A.; Samadzadegan, Farhad; Javan, Farzaneh Dadrass

doi:10.1016/j.jag.2023.103180

Cited by 17 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [36] constructed an end-to-end hybrid detection network of Transformer and UNet to aggregate local-global features, which fully combines the local extraction capability of CNN with the long-range feature-dependent capture capability of ViT. In parallel, Eftekhari et al [37] combined spatial attention to distinguish irrelevant backgrounds with channel attention to adjust channel weights and learn local features with a strong discriminative ability to overcome the problem of detecting missing edges. Yang et al [38] designed a ViT-based generative adversarial network to mitigate the colour noise problem during imaging in low light environments.…”

Section: B Transformer-based Methodsmentioning

confidence: 99%

Rethinking Building Change Detection: Dual-Frequency Learnable Visual Encoder With Multiscale Integration Network

Xu,

Yu,

Mei

et al. 2024

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

View full text Add to dashboard Cite

Remote sensing (RS) image change detection methods based on deep learning such as convolutional neural networks (CNN) and transformers are still spatial domain-based image processing methods by nature, and their detection accuracy is strongly affected by chromatic aberration due to imaging time, shadows caused by lighting conditions, and object confusion and other disturbances. In this study, we revisit change detection (CD) from a signal processing perspective, framing it as the task of consistency detection of the distributional features of two 2D signals. We aim to extract the primary components of the two signals while suppressing interfering noises. To address this, we propose a novel CD method called DFNet, which leverages a dual-frequency learnable encoder. First, we construct a dualfrequency feature encoder Siamese framework to capture local high-frequency signals and global low-frequency signals using CNN and attention mechanisms after dividing the input RS image signals into two channels. Second, we introduce the frequency explicit visual center (FEVC) module as part of the multifrequency domain dense interaction (MFDDI) module at the decoder stage, allowing long-distance dependency to be established between high-low frequency components in the same layer as well as signal aggregation in regions of small edge variations. In addition, the MFDDI module adopts a layer-bylayer interactive fusion approach to synthesize discriminative information in a wide frequency domain range, enhancing the characterization capability of frequency domain signals. We

show abstract

Section: B Transformer-based Methodsmentioning

confidence: 99%

Rethinking Building Change Detection: Dual-Frequency Learnable Visual Encoder With Multiscale Integration Network

Xu,

Yu,

Mei

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…Yu, Y. et al also used the channel attention mechanism to achieve impressive results in building extraction [31]. Eftekhari, A. et al incorporated both channel and spatial attention mechanisms into the network to address the issues of inadequate boundary and detail extraction in building detection from drone remote sensing images [32]. In summary, DCNN and its variants have been widely accepted by scholars in the remote sensing domain [33].…”

Section: Dcnn In the Remote Sensing Domainmentioning

confidence: 99%

MFFNet: A Building Extraction Network for Multi-Source High-Resolution Remote Sensing Data

Liu,

Xi,

Liu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The use of deep learning methods to extract buildings from remote sensing images is a key contemporary research focus, and traditional deep convolutional networks continue to exhibit limitations in this regard. This study introduces a novel multi-feature fusion network (MFFNet), with the aim of enhancing the accuracy of building extraction from high-resolution remote sensing images of various sources. MFFNet improves feature capture for building targets by integrating deep semantic information from various attention mechanisms with multi-scale spatial information from a spatial pyramid module, significantly enhancing the results of building extraction. The performance of MFFNet was tested on three datasets: the self-constructed Jilin-1 building dataset, the Massachusetts building dataset, and the WHU building dataset. Notably, experimental results from the Jilin-1 building dataset demonstrated that MFFNet achieved an average intersection over union (MIoU) of 89.69%, an accuracy of 97.05%, a recall rate of 94.25%, a precision of 94.66%, and an F1 score of 94.82%. Comparisons with the other two public datasets also showed MFFNet’s significant advantages over traditional deep convolutional networks. These results confirm the superiority of MFFNet in extracting buildings from different high-resolution remote sensing data compared to other network models.

show abstract

“…This augmentation strengthens the network's capability of acquiring hierarchical spatial-context representations and addressing potential disruptive factors, such as season and illumination changes. Spatial attention mechanisms [15][16][17][18] and channel attention mechanisms [19][20][21] play a pivotal role in guiding the network to automatically focus on important information related to images/features in channels or positions while suppressing irrelevant portions that are commonly associated with backgrounds and disruptive elements. For instance, the integration of convolutional block attention modules (CBAM) in [18] facilitates the learning of spatial-wise and channel-wise discriminative features, thereby enhancing change detection.…”

Section: Introductionmentioning

confidence: 99%

Multistage Interaction Network for Remote Sensing Change Detection

Zhou,

Qian,

Ren

2024

Remote Sensing

View full text Add to dashboard Cite

Change detection in remote sensing imagery is vital for Earth monitoring but faces challenges such as background complexity and pseudo-changes. Effective interaction between bitemporal images is crucial for accurate change information extraction. This paper presents a multistage interaction network designed for effective change detection, incorporating interaction at the image, feature, and decision levels. At the image level, change information is directly extracted from intensity changes, mitigating potential change information loss during feature extraction. Instead of separately extracting features from bitemporal images, the feature-level interaction jointly extracts features from bitemporal images. By enhancing relevance to spatial variant information and shared semantic channels, the network excels in overcoming background complexity and pseudo-changes. The decision-level interaction combines image-level and feature-level interactions, producing multiscale feature differences for precise change prediction. Extensive experiments demonstrate the superior performance of our method compared to existing approaches, establishing it as a robust solution for remote sensing image change detection.

show abstract

Building change detection using the parallel spatial-channel attention block and edge-guided deep network

Cited by 17 publications

References 54 publications

Rethinking Building Change Detection: Dual-Frequency Learnable Visual Encoder With Multiscale Integration Network

Rethinking Building Change Detection: Dual-Frequency Learnable Visual Encoder With Multiscale Integration Network

MFFNet: A Building Extraction Network for Multi-Source High-Resolution Remote Sensing Data

Multistage Interaction Network for Remote Sensing Change Detection

Contact Info

Product

Resources

About