Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks

Jong, Kevin Louis de; Bosman, Anna Sergeevna

doi:10.1109/ijcnn.2019.8851762

Cited by 71 publications

(41 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, DIs based on log-ratio analysis were used as inputs for the reconstruction network to reconstruct the DIs for SAR images [16]. Feature maps obtained from convolutional layers could be used to generate DIs of optical images [14,25]. DIs defined by the absolute difference between two feature maps were created at each of the five levels of U-net model [25].…”

Section: Generating Label Datamentioning

confidence: 99%

See 1 more Smart Citation

Transfer Change Rules from Recurrent Fully Convolutional Networks for Hyperspectral Unmanned Aerial Vehicle Images without Ground Truth Data

Song

Kim

2020

Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) networks based on supervised learning have been used in diverse CD tasks. However, such supervised CD networks require a large amount of data and only use information from current images. In addition, it is time consuming to manually acquire the ground truth data for newly obtained images. Here, we proposed a novel method for CD in case of a lack of training data in an area near by another one with the available ground truth data. The proposed method automatically entails generating training data and fine-tuning the CD network. To detect changes in target images without ground truth data, the difference images were generated using spectral similarity measure, and the training data were selected via fuzzy c-means clustering. Recurrent fully convolutional networks with multiscale three-dimensional filters were used to extract objects of various sizes from unmanned aerial vehicle (UAV) images. The CD network was pre-trained on labeled source domain data; then, the network was fine-tuned on target images using generated training data. Two further CD networks were trained with a combined weighted loss function. The training data in the target domain were iteratively updated using he prediction map of the CD network. Experiments on two hyperspectral UAV datasets confirmed that the proposed method is capable of transferring change rules and improving CD results based on training data extracted in an unsupervised way.

show abstract

Section: Generating Label Datamentioning

confidence: 99%

“…Feature maps obtained from convolutional layers could be used to generate DIs of optical images [14,25]. DIs defined by the absolute difference between two feature maps were created at each of the five levels of U-net model [25]. The DI then was used by the decoder in copy and concatenate operations instead of feature maps.…”

Section: Generating Label Datamentioning

confidence: 99%

Transfer Change Rules from Recurrent Fully Convolutional Networks for Hyperspectral Unmanned Aerial Vehicle Images without Ground Truth Data

Song

Kim

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Despite the wide availability of CNN, it lacks large amounts of available corresponding change annotations to provide training data, which is necessary to train a reliable change detector in a supervised approach. Focusing on this issue, many recent researches explore alternatives, such as training a weak supervised network [26][27][28], applying an unsupervised approach [29][30][31], or even focusing on noisy data [28]. However, studies on building change detection mainly concentrate on either two-stage detection accompanied with building detection or one-stage without taking the displacement of the buildings into account.…”

Section: Introductionmentioning

confidence: 99%

PGA-SiamNet: Pyramid Feature-Based Attention-Guided Siamese Network for Remote Sensing Orthoimagery Building Change Detection

Jiang

et al. 2020

Remote Sensing

190

View full text Add to dashboard Cite

In recent years, building change detection has made remarkable progress through using deep learning. The core problems of this technique are the need for additional data (e.g., Lidar or semantic labels) and the difficulty in extracting sufficient features. In this paper, we propose an end-to-end network, called the pyramid feature-based attention-guided Siamese network (PGA-SiamNet), to solve these problems. The network is trained to capture possible changes using a convolutional neural network in a pyramid. It emphasizes the importance of correlation among the input feature pairs by introducing a global co-attention mechanism. Furthermore, we effectively improved the long-range dependencies of the features by utilizing various attention mechanisms and then aggregating the features of the low-level and co-attention level; this helps to obtain richer object information. Finally, we evaluated our method with a publicly available dataset (WHU) building dataset and a new dataset (EV-CD) building dataset. The experiments demonstrate that the proposed method is effective for building change detection and outperforms the existing state-of-the-art methods on high-resolution remote sensing orthoimages in various metrics.

show abstract

“…More recently, a deep convolutional neural network (DCNN) can automatically learn a complex feature space from a large amount of image data without heuristic feature extractions. DCNNs have been successfully employed to find and highlight land cover changes [11]- [24].…”

Section: Introductionmentioning

confidence: 99%

“…However, a high degree of computational complexity is required. In contrast, image-based change detection algorithms with a deep learning network have been studied by training temporal images to generate a segmented land cover change [18]- [24]. The difference image (DI) is extracted from an image pair, which is fed into the convolutional neural network (CNN) model to result in a change map [18].…”

Section: Introductionmentioning

confidence: 99%

Change Detection on Multi-Spectral Images Based on Feature-level U-Net

2020

View full text Add to dashboard Cite

This paper proposes a change detection algorithm on multi-spectral images based on feature-level U-Net. A low-complexity pan-sharpening method is proposed to employ not only panchromatic images, but also multi-spectral images for enhancing the performance of the deep neural network. The high-resolution multi-spectral (HRMS) images are then fed into the proposed feature-level U-Net. The proposed feature-level U-Net consists of two-stages: a feature-level subtracting network and U-Net. The feature-level subtracting network is used to extract dynamic difference images (DI) for the use of low-level and high-level features. By employing this network, the performance of change detection algorithms can be improved with a smaller number of layers for U-Net with a low computational complexity. Furthermore, the proposed algorithm detects small changes by taking benefits of both geometrical and spectral resolution enhancement and adopting an intensity-hue-saturation (IHS) pan-sharpening method. A modified of IHS pan-sharpening algorithm is introduced to solve spectral distortion problem by applying mean filtering in high frequency. We found that the proposed change detection on HRMS images gives a better performance compared to existing change detection algorithms by achieving an average F-1 score of 0.62, a percentage correct classification (PCC) of 98.78%, and a kappa of 61.60 for test datasets. INDEX TERMS Convolutional neural network, deep learning, remote sensing, satellite images, change detection.

show abstract

Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks

Cited by 71 publications

References 13 publications

Transfer Change Rules from Recurrent Fully Convolutional Networks for Hyperspectral Unmanned Aerial Vehicle Images without Ground Truth Data

Transfer Change Rules from Recurrent Fully Convolutional Networks for Hyperspectral Unmanned Aerial Vehicle Images without Ground Truth Data

PGA-SiamNet: Pyramid Feature-Based Attention-Guided Siamese Network for Remote Sensing Orthoimagery Building Change Detection

Change Detection on Multi-Spectral Images Based on Feature-level U-Net

Contact Info

Product

Resources

About