DBFGAN: Dual Branch Feature Guided Aggregation Network for remote sensing image

Chu, Shengguang; Xia, Min; Li, Haifeng; Ming, Qian; Zhang, Yonghong

doi:10.1016/j.jag.2022.103141

Cited by 9 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the results were generated by feeding the fused features into a transformer decoder. Chu et al [42] proposed a dual-branch feature-guided aggregation network for CD. This method employs a dual-branch structure composed of a CNN and s transformer to extract both semantic and spatial features at various scales.…”

Section: Hybrid-based Methodsmentioning

confidence: 99%

MSGFNet: Multi-Scale Gated Fusion Network for Remote Sensing Image Change Detection

Wang,

Hao

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) stands out as a pivotal yet challenging task in the interpretation of remote sensing images. Significant developments have been witnessed, particularly with the rapid advancements in deep learning techniques. Nevertheless, challenges such as incomplete detection targets and unsmooth boundaries remain as most CD methods suffer from ineffective feature fusion. Therefore, this paper presents a multi-scale gated fusion network (MSGFNet) to improve the accuracy of CD results. To effectively extract bi-temporal features, the EfficientNetB4 model based on a Siamese network is employed. Subsequently, we propose a multi-scale gated fusion module (MSGFM) that comprises a multi-scale progressive fusion (MSPF) unit and a gated weight adaptive fusion (GWAF) unit, aimed at fusing bi-temporal multi-scale features to maintain boundary details and detect completely changed targets. Finally, we use the simple yet efficient UNet structure to recover the feature maps and predict results. To demonstrate the effectiveness of the MSGFNet, the LEVIR-CD, WHU-CD, and SYSU-CD datasets were utilized, and the MSGFNet achieved F1 scores of 90.86%, 92.46%, and 80.39% on the three datasets, respectively. Furthermore, the low computational costs and small model size have validated the superior performance of the MSGFNet.

show abstract

Section: Hybrid-based Methodsmentioning

confidence: 99%

MSGFNet: Multi-Scale Gated Fusion Network for Remote Sensing Image Change Detection

Wang,

Hao

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In response to the existing issues in networks that connect CNNs with the transformer and networks based purely on the transformer, research has considered the characteristics of the CNN and transformer and proposed a network that integrates both of them [30,56]. This method obtains better performance than the previous two types of networks and suppresses the problem of the misdetection and omission of small changing targets by combining the local detection ability of the CNN and the global modeling capability of the transformer.…”

Section: Transformer-based CD Methodsmentioning

confidence: 99%

A Full-Scale Connected CNN–Transformer Network for Remote Sensing Image Change Detection

Chen,

Zhang,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Recent studies have introduced transformer modules into convolutional neural networks (CNNs) to solve the inherent limitations of CNNs in global modeling and have achieved impressive performance. However, some challenges have yet to be addressed: first, networks with simple connections between the CNN and transformer perform poorly in small change areas; second, networks that only use transformer structures are prone to attaining coarse detection results and excessively generalizing feature boundaries. In addition, the methods of fusing the CNN and transformer have the issue of a unilateral flow of feature information and inter-scale communication, leading to a loss of change information across different scales. To mitigate these problems, this study proposes a full-scale connected CNN–Transformer network, which incorporates the Siamese structure, Unet3+, and transformer structure, used for change detection in remote sensing images, namely SUT. A progressive attention module (PAM) is adopted in SUT to deeply integrate the features extracted from both the CNN and the transformer, resulting in improved global modeling, small target detection capacities, and clearer feature boundaries. Furthermore, SUT adopts a full-scale skip connection to realize multi-directional information flow from the encoder to decoder, enhancing the ability to extract multi-scale features. Experimental results demonstrate that the method we designed performs best on the CDD, LEVIR-CD, and WHU-CD datasets with its concise structure. In particular, based on the WHU-CD dataset, SUT upgrades the F1-score by more than 4% and the intersection over union (IOU) by more than 7% compared with the second-best method.

show abstract

“…Most of the previous studies probed the spatiotemporal distribution and long‐term trends and variation of aerosols and their effects on climate change and human health at different spatial scales using sun photometry daytime data (Cheng et al., 2023; Yin, Wang, Li, Lu, Tian, Yin, et al., 2023). However, nighttime atmospheric chemical reactions are very different from daytime reactions due to the absence of solar light (Luo et al., 2022; Xiong et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

Analysis of nighttime aerosols and relation to covariates over a highly polluted sub‐Saharan site using Mann–Kendall and wavelet coherence approach

Köse,

Tariq,

Uyal

et al. 2024

J of Env Quality

View full text Add to dashboard Cite

High emissions of aerosols and trace gases during nighttime can cause serious air quality, climate, and health issues, particularly in extremely polluted cities. In this paper, an effort has been made to examine the variations in aerosols and trace gases over a sub‐Saharan city of Ilorin (Nigeria) during nighttime. We have used Aerosol Robotic Network data of aerosol optical depth (AOD) at 500 nm, Angstrom exponent (AE) (440/870), and precipitable water (WVC). Both AE and WVC showed a decreasing trend of −0.0012% and −0.0010% per year, respectively. We also analyzed nighttime data of carbon monoxide (CO), methane (CH4), and ozone (O3) from Atmospheric Infrared Sounder and aerosol subtypes from CALIPSO (Cloud‐Aerosol Lidar and Infrared Pathfinder Satellite Observation). AOD, AE, and WVC average values are found to be 0.64 ± 0.33, 0.74 ± 0.24, and 3.40 ± 0.97, respectively. As a result of northeasterly winds carrying Saharan dust during the dry season, the greatest value of AOD (1.29) was observed in February. Desert dust aerosols (37.63%) were the most prevalent type, followed by mixed aerosols (44.15%). Winds at a height of 1500 m above ground level were likely transporting Saharan dust to Ilorin. CALIPSO images revealed that Ilorin's atmosphere contained dust, polluted continental, clean maritime, and polluted dust on high AOD days. The National Oceanic and Atmospheric Administration's vertical sounding profiles showed that the presence of high AOD values was caused by the inversion layer trapping aerosol pollution. Average nighttime concentrations of CO, O3, and CH4 were measured to be 127 ± 18, 29.7 ± 2.1, and 1822.6 ± 12.7 ppbv, respectively. The wavelet coherence spectra exhibited significant quasi‐biannual and quasi‐annual oscillations at statistically significant levels.

show abstract

DBFGAN: Dual Branch Feature Guided Aggregation Network for remote sensing image

Cited by 9 publications

References 32 publications

MSGFNet: Multi-Scale Gated Fusion Network for Remote Sensing Image Change Detection

MSGFNet: Multi-Scale Gated Fusion Network for Remote Sensing Image Change Detection

A Full-Scale Connected CNN–Transformer Network for Remote Sensing Image Change Detection

Analysis of nighttime aerosols and relation to covariates over a highly polluted sub‐Saharan site using Mann–Kendall and wavelet coherence approach

Contact Info

Product

Resources

About