DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images

Wang, Ying; Peng, Yuexing; Li, Wei; Alexandropoulos, George C.; Yu, Junchuan; Ge, Daqing; Wang, Xiang

doi:10.1109/tgrs.2022.3197546

Cited by 55 publications

(34 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4) Ablation Experiment on Comparison of Proposed Method with State-of-art Methods: To verify the effectiveness of proposed model, ablation experiment is conducted on UAV road dataset for different state-of-the art methods. We compared proposed AA-ResUNet with various types of standard residual networks like TransUNet [12], DDU-Net [14], ResUNet [27], D-ResUNet [20], and attention network like SE-ResUNet [28] and DA-RoadNet [18]. We augment the standard ResUNet through augmenting the all layers of traditional convolution of all residual standard blocks with close attention using k = 4, v = 4 and N h = 2 heads.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An Attention Augmented Convolution based Improved Residual UNet for Road Extraction

Patil¹

2022

Preprint

View full text Add to dashboard Cite

<p>Recently remote sensing images have become more popular due to improved image quality and resolution. These images have been shown to be a valuable data source for road extraction applications like intelligent transportation systems, road maintenance, and road map making. In recent decades, the use of highly significant deep learning in automatic road extraction from these images has been a hot research area. However, fully automated and highly accurate road extractions from remote sensing images remain a challenge due to topology differences, complicated image backgrounds, and complex contexts. This paper proposes novel attention augmented convolution-based residual UNet architecture (AA-ResUNet) for road extraction, which adopts powerful features of self-attention mechanism and advantageous properties of residual UNet structure. The self-attention mechanism uses attention augmented convolutional operation to capture long-range global information; however, traditional convolution has a fundamental disadvantage: it only performs on local information. Therefore, we use the attention augmented convolutional layer as an alternative to standard convolution layers to obtain more discriminant feature representations. It allows to develop a network with fewer parameters. We also adopt improved residual units in standard ResUNet to the speedup training process and enhance the segmentation accuracy of the network. Experimental results on Massachusetts, DeepGlob Challenge, and UAV Road Dataset show that the AA-ResUNet performs well in road extraction, with Intersection over Union (IoU) (94.27%), lower trainable parameters (1.20 M), and inference time (1.14 sec). Comparative results on the proposed method have proven the supremacy or compatibility in road extraction with ten recently established deep learning approaches.</p>

show abstract

Section: Resultsmentioning

confidence: 99%

“…In [13], the author has published a full-scale densely connected UNet for semantic segmentation in medical images. Ying Wang et al [14] have introduced dualdecoder UNet for road extraction in remote sensing images. However, this architecture depends on dilated convolution and multi-scale fusion for capturing global information.…”

Section: Related Workmentioning

confidence: 99%

An Attention Augmented Convolution based Improved Residual UNet for Road Extraction

Patil¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…[24] proposes an innovative Cascaded Attention DenseUNet (CADUNet) semantic segmentation model by embedding two attention modules, such as global attention and core attention modules, in the DenseUNet framework to extract road information.Wu et al [25] added a channel attention module in the center of the network. This greatly improves the details of the extraction results.wang et al [26] introduce the dilated convolution attention module(DCAM) between the encoder and decoders to increase the receptive field.…”

Section: Introductionmentioning

confidence: 99%

AGD-Linknet: A Road Semantic Segmentation Model for High Resolution Remote Sensing Images Integrating Attention Mechanism, Gated Decoding Block and Dilated Convolution

2023

View full text Add to dashboard Cite

Road information is a kind of important geographic information. Road information extracted from remote sensing images is widely used in map, traffic, navigation, military and many other fields. However, the autonomous extraction of road information from high resolution remote sensing images has some problems such as incoherence, incompleteness and poor connectivity, therefore, a semantic segmentation model for roads in high resolution remote sensing images, called AGD-Linknet, is proposed, which integrates attention mechanisms, gated decoder block, and dilated convolution. This model mainly consists of three parts.Firstly, the stem block is used as the initial convolution layer of the model to reduce the information loss in the convolution stage; Secondly, the series-parallel combined dilated convolution and coordinate attention block into the center of the network, which enlarges the receptive field of the network and improves the feature extraction ability of spatial domain and channel domain information; Finally, in the decoder part, gated convolution is introduced in the decoder part to improve the extraction of road edge. Compared with U-Net, Linknet and D-Linknet on the DeepGlobe dataset, the proposed AGD-Linknet has improved the pixel accuracy, mean intersection over union and F1-Score index of road recognition by 1.41%-11.52%, 0.0077-0.1473, 0.0057-0.1292, and has certain effectiveness and feasibility in many scenarios in rural areas, urban, and suburbs. And can be apply to the tasks of road recognition and extraction in high-resolution remote sensing.

show abstract

“…Obtaining detailed and accurate road information plays a critical role in urban planning, 1 autonomous driving, 2 geographic information system upgrading, 3 and other fields. In recent years, the continuous development of remote-sensing satellite technology has made acquiring remote-sensing images easy 4 , 5 , 6 , 7 , 8 . High-resolution remote sensing images can provide finer spectral, texture, and other features, and fast and accurate extraction of roads from high-resolution remote sensing images is a convenient and effective method for road extraction 9 , 10 , 11 , 12 .…”

Section: Introductionmentioning

confidence: 99%

JAED-Net: joint attention encoder–decoder network for road extraction from remote sensing images

Tuerxun

Qian

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

In road extraction from remote sensing images, the road environment is complex and blocked by trees, buildings, and other objects, making it impossible to extract practical (continuous and complete) road information. We propose a joint attention encoder-decoder network (JAED-Net) for road extraction from remote sensing images to solve these problems. First, JAED-Net encodes a modified residual network as the backbone for road feature extraction. A joint attention module is added to the encoder to enhance the network's ability to learn and express road features. Then, strip convolution is added to the decoder, so the network retains more spatial features, such as the width and connectivity of roads during upsampling. Finally, a hybrid weighted loss function is introduced to train the network and ensure stability because of the unbalanced ratio of road and background pixels in remote sensing images. Experimental validation of the proposed network is performed on three publicly available datasets.

show abstract

DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images

Cited by 55 publications

References 30 publications

An Attention Augmented Convolution based Improved Residual UNet for Road Extraction

An Attention Augmented Convolution based Improved Residual UNet for Road Extraction

AGD-Linknet: A Road Semantic Segmentation Model for High Resolution Remote Sensing Images Integrating Attention Mechanism, Gated Decoding Block and Dilated Convolution

JAED-Net: joint attention encoder–decoder network for road extraction from remote sensing images

Contact Info

Product

Resources

About