A Global Context-aware and Batch-independent Network for road extraction from VHR satellite imagery

Zhu, Qiqi; Zhang, Yanan; Wang, Lizeng; Zhong, Yanfei; Guan, Qingfeng; Lu, Xiaoyan; Zhang, Liangpei; Li, Deren

doi:10.1016/j.isprsjprs.2021.03.016

Cited by 166 publications

(73 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Roads play an important role in urban planning, traffic navigation, map updating, and other fields [1]. With the rapid development of remote sensing satellites and sensors, it is becoming increasingly easy to collect very high-resolution (VHR) satellite imagery, which can provide sufficient data sources for road extraction.…”

Section: Introductionmentioning

confidence: 99%

“…Although deep learning methods have achieved good results in automatic road extraction, these methods still often produce discontinuous road segments, which cause great difficulties in practical applications. There are two main reasons for this: (1) the occlusions and shadows caused by trees, buildings, etc., may cause a deep learning model to fail to correctly capture the information of occluded and shadowed roads. (2) The texture of a road may be very similar to that of the surrounding ground features, causing the model to be unable to extract clear road boundaries and locations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BSIRNet: A Road Extraction Network with Bidirectional Spatial Information Reasoning

Tan

Dai

2022

Journal of Sensors

View full text Add to dashboard Cite

Automatic extraction of road information from remote sensing images is widely used in many fields, such as urban planning and automatic navigation. However, due to interference from noise and occlusion, the existing road extraction methods can easily lead to road discontinuity. To solve this problem, a road extraction network with bidirectional spatial information reasoning (BSIRNet) is proposed, in which neighbourhood feature fusion is used to capture spatial context dependencies and expand the receptive field, and an information processing unit with a recurrent neural network structure is used to capture channel dependencies. BSIRNet enhances the connectivity of road information through spatial information reasoning. Using the public Massachusetts road dataset and Wuhan University road dataset, the superiority of the proposed method is verified by comparing its results with those of other models.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

BSIRNet: A Road Extraction Network with Bidirectional Spatial Information Reasoning

Tan

Dai

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…The high-spatial resolution also leads to a complex spatial arrangement with high intraclass and low interclass variabilities in HRIs [2]. The classification of HRIs has evolved from pixel-based to object-oriented methods [3]. However, these methods still have no access to the high-level semantics of urban scenes, which are composed of distinct subscenes, such as residential, parking lot, and industrial scenes [4] [5].…”

Section: Introductionmentioning

confidence: 99%

“…These methods are based on extracting the underlying features and clustering and coding the underlying features to obtain more expressive mid-level features [10]. (3) Information extraction methods based on high-level features. These methods achieve mapping from bottom-level features to high-level features [11].…”

Section: Introductionmentioning

confidence: 99%

Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images

Zhu

Chen

Wang

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

High-spatial resolution urban scenes, which contain ecological, social and environmental zones, are composed of diverse functional areas. Depicting urban scenes from both qualitative and quantitative aspects, i.e., scene classification and scene unmixing, are increasingly important tasks. The purpose of scene classification is to mark a scene as a separate category, and this approach is widely applied to qualitatively define scenes. However, with the rapid development of cities, urban scenes usually show a mixed nature, resulting in urban mixed scenes (UMSs). Traditional scene classification cannot describe the mix of urban scenes. Few studies have focused on the quantitative measurements of UMSs, which aim at discovering and analyzing the proportion of different subscenes. In this paper, a scene unmixing framework based on nonnegative matrix factorization for UMSs (UnUMS) is proposed to estimate the mixing ratio of urban scenes. In the UnUMS, a deep feature representation is used for the high-dimensional representation of the image, and then a nonnegative matrix factorization strategy is used to estimate the proportion of UMSs. Finally, the UMS can be described by the proportion of each subscene. To confirm the robust generalizability of UnUMS, the WH-center Mix dataset with a set of small mixed scenes and the WH-hy LMix dataset with a large UMS image are utilized. The root-mean-square error and the newly proposed vector angular distance are utilized to quantitatively evaluate the effect of scene unmixing from different aspects. Experiments with the two datasets demonstrate that UnUMS can accurately estimate the proportions of different scenes for UMS.

show abstract

“…However, the effectiveness of road extraction techniques with deep learning methods is greatly affected by the quality of the sample set, and noise and occlusion problems cause fractures in most road extraction results. It is difficult to obtain extraction accuracy and recall values over 90% simultaneously when using current deep learning methods [19,20]. In addition, no vector topology relationship exists in the extraction results, and the results thus require a large amount of postprocessing to yield product-level data.…”

Section: Introductionmentioning

confidence: 99%

Semi-Automatic Extraction of Rural Roads under the Constraint of Combined Geometric and Texture Features

Tan

Shen

Dai

2021

IJGI

View full text Add to dashboard Cite

The extraction of road information from high-resolution remotely-sensed images has important application value in many fields. Rural roads have the characteristics of relatively narrow widths and diversified pavement materials; these characteristics can easily lead to problems involving the similarity of the road texture with the texture of surrounding objects and make it difficult to improve the automation of traditional high-precision road extraction methods. Based on this background, a semi-automatic rural road extraction method constrained by a combination of geometric and texture features is proposed in this paper. First, an adaptive road width extraction model is proposed to improve the accuracy of the initial road centre point. Then, aiming at the continuous change of curvature of rural roads, a tracking direction prediction model is proposed. Finally, a matching model under geometric texture constraints is proposed, which solves the problem of similarity between road and neighbourhood texture to a certain extent. The experimental results show that by selecting different types of experimental scenes or remotely sensed image data, compared with other methods, the proposed method can not only guarantee the road extraction accuracy but also improve the degree of automation to a certain extent.

show abstract

A Global Context-aware and Batch-independent Network for road extraction from VHR satellite imagery

Cited by 166 publications

References 29 publications

BSIRNet: A Road Extraction Network with Bidirectional Spatial Information Reasoning

BSIRNet: A Road Extraction Network with Bidirectional Spatial Information Reasoning

Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images

Semi-Automatic Extraction of Rural Roads under the Constraint of Combined Geometric and Texture Features

Contact Info

Product

Resources

About