Road extraction in remote sensing data: A survey

Chen, Ziyi; Deng, Liai; Luo, Yong; Li, Dilong; Marcato, José; Gonçalves, Wesley Nunes; Nurunnabi, Abdul; Li, Jonathan; Wang, Cheng; Li, Deren

doi:10.1016/j.jag.2022.102833

Cited by 61 publications

(49 citation statements)

References 226 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the pixel-wise annotations, weak annotations (such as scribbles [4,36,37], bounding boxes [38], points [39,40] and image-level tags [41,42]) were much easier to obtain. Therefore, weakly supervised learning was more popular in segmentation tasks [2,43]. S. Wu et al proposed a novel model named MD-ResUnet, which used only OSM centerline as weak annotations and achieved good performance in road extraction from remote sensing images [4].…”

Section: Semi-supervised and Weakly Supervised Deep Learning Methodsmentioning

confidence: 99%

“…Additionally, the deep convolutional neural networks (DCNN) [19,20] are typical DL methods used in the image semantic segmentation. Recently, many DL methods have made great progress in road extraction [1,2]. A dualgeneration GAN(DH-GAN) network was proposed to extract the road topologies by D. Costea et al [21].…”

Section: Road Extractionmentioning

confidence: 99%

“…Recently, deep learning methods have been leading in road extraction methods for remote sensing images [1,2]. However, the superior performance of these deep learningbased methods highly depends on massive quantities of precisely annotated training data [3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Chen

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Road networks play a fundamental role in our daily life. It is of importance to extract the road structure in a timely and precise manner with the rapid evolution of urban road structure. Recently, road network extraction using deep learning has become an effective and popular method. The main shortcoming of the road extraction using deep learning methods lies in the fact that there is a need for a large amount of training datasets. Additionally, the datasets need to be elaborately annotated, which is usually labor-intensive and time-consuming; thus, lots of weak annotations (such as the centerline from OpenStreetMap) have accumulated over the past a few decades. To make full use of the weak annotations, we propose a novel semi-weakly supervised method based on adversarial learning to extract road networks from remote sensing imagery. Our method uses a small set of pixel-wise annotated data and a large amount of weakly annotated data for training. The experimental results show that the proposed approach can achieve a maintained performance compared with the methods that use a large number of full pixel-wise annotations while using less fully annotated data.

show abstract

Section: Semi-supervised and Weakly Supervised Deep Learning Methodsmentioning

confidence: 99%

Section: Road Extractionmentioning

confidence: 99%

See 1 more Smart Citation

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Chen

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Deep learning promotes the progress of computer vision, especially in object detection, semantic segmentation, image classification, and other aspects, and it has a good effect. Scholars also began to use deep learning technology to complete remote sensing image road extraction [10][11][12][13]. Although the model based on deep learning has achieved good results in extracting road tasks, and many road extraction algorithms have problems, such as road breaking caused by occlusion, difficult extraction of the narrow road, and incorrect identification of roads and background.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Road Extraction Network Based on MSPFE-Net

Wei

Zhang

2023

Electronics

View full text Add to dashboard Cite

Road extraction is a hot task in the field of remote sensing, and it has been widely concerned and applied by researchers, especially using deep learning methods. However, many models using convolutional neural networks ignore the attributes of roads, and the shape of the road is banded and discrete. In addition, the continuity and accuracy of road extraction are also affected by narrow roads and roads blocked by trees. This paper designs a network (MSPFE-Net) based on multi-level strip pooling and feature enhancement. The overall architecture of MSPFE-Net is encoder-decoder, and this network has two main modules. One is a multi-level strip pooling module, which aggregates long-range dependencies of different levels to ensure the connectivity of the road. The other module is the feature enhancement module, which is used to enhance the clarity and local details of the road. We perform a series of experiments on the dataset, Massachusetts Roads Dataset, a public dataset. The experimental data showed that the model in this paper was better than the comparison models.

show abstract

“…Some of the defects hidden in the training samples can be overcome if a proper loss function is used. For example, giving more weights to minority classes is efficient to deal with class imbalanced training samples [15,16]. Image information-related constraints are introduced to deal with noisy labels [17,18].…”

Section: Introductionmentioning

confidence: 99%

Feature Consistency Constraints-Based CNN for Landsat Land Cover Mapping

Zhao

Luo

et al. 2023

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

View full text Add to dashboard Cite

The cascade of convolution layers and the end-toend training process facilitate CNN feature extraction and transmission, and promote the success of CNN in image processing. However, the drawback of heavily relying on large-scale highquality training samples restricts its applications. To avoid costly and unrealistic manual annotations for large-scale remote sensing images, existing land cover maps are considered as an alternative to manual annotations, in which noisy labels are inevitable. To alleviate the impact of noisy labels, this paper proposes to improve the consistency feature learning ability of CNNs as a feasible solution in practical land cover mapping. Firstly, an intraclass feature consistency constraint is introduced to maintain the consistency of CNN feature maps for the same class. Then, an inter-iteration feature consistency constraint is employed to guide the network to learn features that are consistent with the whole underlying distribution inside a mini-batch. These two feature consistency constraints work in a cooperative and complementary manner with the traditional cross-entropy, and together improve the consistency feature learning ability of the proposed Feature Consistency Network (FCNet). Experimental results demonstrate the effectiveness of the proposed FCNet. Extensive experiments on different network structures validate the generalization of the proposed feature consistency constraints.

show abstract

Road extraction in remote sensing data: A survey

Cited by 61 publications

References 226 publications

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Remote Sensing Image Road Extraction Network Based on MSPFE-Net

Feature Consistency Constraints-Based CNN for Landsat Land Cover Mapping

Contact Info

Product

Resources

About