A Coarse-to-Fine Deep Learning Based Land Use Change Detection Method for High-Resolution Remote Sensing Images

Wang, Mingchang; Zhang, Haiming; Sun, Weiwei; Li, Sheng; Wang, Fengyan; Yang, Guodong

doi:10.3390/rs12121933

Cited by 44 publications

(30 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many methods improve the change detection performance by enhancing the discrimination of features; the main idea is to increase the inter-class distance between changed regions and reduce the intra-class distance between unchanged regions. Refs [27,28] constructed mapping relationship between unchanged regions by selecting reliable unchanged regions as training samples which were obtained from the generated coarse change maps. Finally, similarity analysis was performed on the mapped feature pairs to realize change detection.…”

Section: Methods Of Enhancing Feature Discriminationmentioning

confidence: 99%

Adaptive Feature Weighted Fusion Nested U-Net with Discrete Wavelet Transform for Change Detection of High-Resolution Remote Sensing Images

et al. 2021

View full text Add to dashboard Cite

The characteristics of a wide variety of scales about objects and complex texture features of high-resolution remote sensing images make deep learning-based change detection methods the mainstream method. However, existing deep learning methods have problems with spatial information loss and insufficient feature representation, resulting in unsatisfactory effects of small objects detection and boundary positioning in high-resolution remote sensing images change detection. To address the problems, a network architecture based on 2-dimensional discrete wavelet transform and adaptive feature weighted fusion is proposed. The proposed network takes Siamese network and Nested U-Net as the backbone; 2-dimensional discrete wavelet transform is used to replace the pooling layer; and the inverse transform is used to replace the upsampling to realize image reconstruction, reduce the loss of spatial information, and fully retain the original image information. In this way, the proposed network can accurately detect changed objects of different scales and reconstruct change maps with clear boundaries. Furthermore, different feature fusion methods of different stages are proposed to fully integrate multi-scale and multi-level features and improve the comprehensive representation ability of features, so as to achieve a more refined change detection effect while reducing pseudo-changes. To verify the effectiveness and advancement of the proposed method, it is compared with seven state-of-the-art methods on two datasets of Lebedev and SenseTime from the three aspects of quantitative analysis, qualitative analysis, and efficiency analysis, and the effectiveness of proposed modules is validated by an ablation study. The results of quantitative analysis and efficiency analysis show that, under the premise of taking into account the operation efficiency, our method can improve the recall while ensuring the detection precision, and realize the improvement of the overall detection performance. Specifically, it shows an average improvement of 37.9% and 12.35% on recall, and 34.76% and 11.88% on F1 with the Lebedev and SenseTime datasets, respectively, compared to other methods. The qualitative analysis shows that our method has better performance on small objects detection and boundary positioning than other methods, and a more refined change map can be obtained.

show abstract

Section: Methods Of Enhancing Feature Discriminationmentioning

confidence: 99%

Adaptive Feature Weighted Fusion Nested U-Net with Discrete Wavelet Transform for Change Detection of High-Resolution Remote Sensing Images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The false detection rate and missed detection rate is reduced and the accuracy of detection is improved through constructing a neural network to merge the features. Wang et al [25] uses the object-based variation vector analysis method, correlation coefficient method, etc., to comprehensively utilize the various features of the object to participate in the analysis, which can improve the detection accuracy of the change compared with using only one single feature. However, the above methods have a significant dependence on several aspects such as the quality of feature selection and feature weight distribution.…”

Section: Related Workmentioning

confidence: 99%

High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level

Jing

Song

et al. 2019

IEEE Access

View full text Add to dashboard Cite

High-resolution remote sensing images are abundant in texture information, and the detection method of the change of pixel-level mainly analyzes the spectral information of the image, which has certain limitations. In this paper, a high-resolution remote sensing image change detection method combining pixel and object levels is proposed to solve the problem that many pepper and salt phenomenon and false detection in the change detection of pixel-level and object-level change detection method are cumbersome for image segmentation process. We integrate the multi-dimensional features of high-resolution remote sensing images and use random forest classifiers to classify to obtain the pixel-level change detection results. Then, we use the improved U-net network to semantically segment the post-phase remote sensing image to obtain the image object segmentation result. Finally, the consequences of pixel-level change detection and image object segmentation result are fused to obtain the image changing area and the unchanging area. The experimental results demonstrate that the algorithm has a higher accuracy rate and detection precision.

show abstract

“…A fully convolutional network (FCN) has been successfully applied to the end-to-end semantic segmentation of optical remote sensing images [38], showing the flexibility of its structure and the superiority of feature combination strategy. Moreover, with the unique advantages of taking into account local and global information, segmenting images of any size, and achieving pixel-level labeling, it has achieved better results than traditional CNN in remote sensing image classification [39,40] and change detection [41][42][43][44]. U-Net [45,46], developed from FCN, has proved to have better performance than FCN.…”

Section: Introductionmentioning

confidence: 99%

A Novel Squeeze-and-Excitation W-Net for 2D and 3D Building Change Detection with Multi-Source and Multi-Feature Remote Sensing Data

Zhang

Wang

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Building Change Detection (BCD) is one of the core issues in earth observation and has received extensive attention in recent years. With the rapid development of earth observation technology, the data source of remote sensing change detection is continuously enriched, which provides the possibility to describe the spatial details of the ground objects more finely and to characterize the ground objects with multiple perspectives and levels. However, due to the different physical mechanisms of multi-source remote sensing data, BCD based on heterogeneous data is a challenge. Previous studies mostly focused on the BCD of homogeneous remote sensing data, while the use of multi-source remote sensing data and considering multiple features to conduct 2D and 3D BCD research is sporadic. In this article, we propose a novel and general squeeze-and-excitation W-Net, which is developed from U-Net and SE-Net. Its unique advantage is that it can not only be used for BCD of homogeneous and heterogeneous remote sensing data respectively but also can input both homogeneous and heterogeneous remote sensing data for 2D or 3D BCD by relying on its bidirectional symmetric end-to-end network architecture. Moreover, from a unique perspective, we use image features that are stable in performance and less affected by radiation differences and temporal changes. We innovatively introduced the squeeze-and-excitation module to explicitly model the interdependence between feature channels so that the response between the feature channels is adaptively recalibrated to improve the information mining ability and detection accuracy of the model. As far as we know, this is the first proposed network architecture that can simultaneously use multi-source and multi-feature remote sensing data for 2D and 3D BCD. The experimental results in two 2D data sets and two challenging 3D data sets demonstrate that the promising performances of the squeeze-and-excitation W-Net outperform several traditional and state-of-the-art approaches. Moreover, both visual and quantitative analyses of the experimental results demonstrate competitive performance in the proposed network. This demonstrates that the proposed network and method are practical, physically justified, and have great potential application value in large-scale 2D and 3D BCD and qualitative and quantitative research.

show abstract

A Coarse-to-Fine Deep Learning Based Land Use Change Detection Method for High-Resolution Remote Sensing Images

Cited by 44 publications

References 65 publications

Adaptive Feature Weighted Fusion Nested U-Net with Discrete Wavelet Transform for Change Detection of High-Resolution Remote Sensing Images

Adaptive Feature Weighted Fusion Nested U-Net with Discrete Wavelet Transform for Change Detection of High-Resolution Remote Sensing Images

High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level

A Novel Squeeze-and-Excitation W-Net for 2D and 3D Building Change Detection with Multi-Source and Multi-Feature Remote Sensing Data

Contact Info

Product

Resources

About