Cloud and Cloud Shadow Detection Based on Multiscale 3D-CNN for High Resolution Multispectral Imagery

Chen, Yang; Tang, Luliang; Kan, Zihan; Latif, Aamir; Yang, Xiucheng; Bilal, Muhammad; Li, Qingquan

doi:10.1109/access.2020.2967590

Cited by 16 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed 3D-CNN together with a principal component analysis (PCA) stage (applied to extract the most important information from the images) achieves an overall accuracy above 95%. Another 3D-CNN model for cloud classification was explored in [27], which was tested over two databases (GF-1 WFV validation data and ZY-3 validation data). Such a model reaches an accuracy of 97.27%.…”

Section: Related Workmentioning

confidence: 99%

“…Recent works based on hybrid methods combining 2D-and 3D-CNN [24] have proven that 3D-CNNs enable the joint spatial-spectral feature representation from stacked spatial bands. Such methods have been shown to be less computationally expensive than those solely based on 3D-CNN architectures [25][26][27]. In addition, some exploratory studies exhibit that 3D-CNNs may underperform 2D-CNNs when classes have similar textures across multiple spectral bands [28], and therefore 2D-CNN-based approaches are preferred by the vast majority of recent research works on crop classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

et al. 2021

View full text Add to dashboard Cite

Automatic crop identification and monitoring is a key element in enhancing food production processes as well as diminishing the related environmental impact. Although several efficient deep learning techniques have emerged in the field of multispectral imagery analysis, the crop classification problem still needs more accurate solutions. This work introduces a competitive methodology for crop classification from multispectral satellite imagery mainly using an enhanced 2D convolutional neural network (2D-CNN) designed at a smaller-scale architecture, as well as a novel post-processing step. The proposed methodology contains four steps: image stacking, patch extraction, classification model design (based on a 2D-CNN architecture), and post-processing. First, the images are stacked to increase the number of features. Second, the input images are split into patches and fed into the 2D-CNN model. Then, the 2D-CNN model is constructed within a small-scale framework, and properly trained to recognize 10 different types of crops. Finally, a post-processing step is performed in order to reduce the classification error caused by lower-spatial-resolution images. Experiments were carried over the so-named Campo Verde database, which consists of a set of satellite images captured by Landsat and Sentinel satellites from the municipality of Campo Verde, Brazil. In contrast to the maximum accuracy values reached by remarkable works reported in the literature (amounting to an overall accuracy of about 81%, a f1 score of 75.89%, and average accuracy of 73.35%), the proposed methodology achieves a competitive overall accuracy of 81.20%, a f1 score of 75.89%, and an average accuracy of 88.72% when classifying 10 different crops, while ensuring an adequate trade-off between the number of multiply-accumulate operations (MACs) and accuracy. Furthermore, given its ability to effectively classify patches from two image sequences, this methodology may result appealing for other real-world applications, such as the classification of urban materials.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It can automatically learn and extract deep non-linear features in the training set, which is very suitable for non-linear tasks like image segmentation. Many scholars have introduced deep learning in their research and considered cloud detection as a semantic segmentation task, which achieves a meaningful performance [21][22][23][24][25][26]. For example, Chai et al have used the SegNet model to realize the cloud detection in Landsat-7 and Landsat-8 (L8) images [27].…”

Section: Introductionmentioning

confidence: 99%

Light-Weight Cloud Detection Network for Optical Remote Sensing Images with Attention-Based DeeplabV3+ Architecture

2021

View full text Add to dashboard Cite

Clouds in optical remote sensing images cause spectral information change or loss, that affects image analysis and application. Therefore, cloud detection is of great significance. However, there are some shortcomings in current methods, such as the insufficient extendibility due to using the information of multiple bands, the intense extendibility due to relying on some manually determined thresholds, and the limited accuracy, especially for thin clouds or complex scenes caused by low-level manual features. Combining the above shortcomings and the requirements for efficiency in practical applications, we propose a light-weight deep learning cloud detection network based on DeeplabV3+ architecture and channel attention module (CD-AttDLV3+), only using the most common red–green–blue and near-infrared bands. In the CD-AttDLV3+ architecture, an optimized backbone network-MobileNetV2 is used to reduce the number of parameters and calculations. Atrous spatial pyramid pooling effectively reduces the information loss caused by multiple down-samplings while extracting multi-scale features. CD-AttDLV3+ concatenates more low-level features than DeeplabV3+ to improve the cloud boundary quality. The channel attention module is introduced to strengthen the learning of important channels and improve the training efficiency. Moreover, the loss function is improved to alleviate the imbalance of samples. For the Landsat-8 Biome set, CD-AttDLV3+ achieves the highest accuracy in comparison with other methods, including Fmask, SVM, and SegNet, especially for distinguishing clouds from bright surfaces and detecting light-transmitting thin clouds. It can also perform well on other Landsat-8 and Sentinel-2 images. Experimental results indicate that CD-AttDLV3+ is robust, with a high accuracy and extendibility.

show abstract

“…Xie et al [15] proposed a deep convolutional neural network (CNN) with two branches is designed to predict these superpixels as thick cloud, thin cloud, or non-cloud. Chen et al [16] developed an end-to-end 3D-CNN method for cloud and cloud shadow detection with four band-combination images as the input imagery. Francis et al [17] introduced a Fully Convolutional Network architecture to detect cloud, known as U-net proposed by Ronneberger et al [18], which fuses the shallowest and deepest layers of the network, thus routing low-level visible content to its deepest layers.…”

Section: Introductionmentioning

confidence: 99%

ClouDet: A Dilated Separable CNN-Based Cloud Detection Framework for Remote Sensing Imagery

Guo¹,

Bai²,

Qin³

2021

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

View full text Add to dashboard Cite

Cloud detection is one of the essential procedures in optical remote sensing image processing, because clouds are widely distributed in remote sensing images and causes a lot of challenges, such as climate research and object detection. In this paper, a lightweight deep learning-based framework is proposed to detect cloud in remote sensing imagery. Firstly, a multiple features fusion strategy is designed to extract learnable manual features and convolution features from visible and near-infrared bands. Then, a lightweight fully convolutional neural network (ClouDet) with a micro-architecture named dilated separable convolutional module is used to extract the multiscale contextual information and gradually recovers segmentation results with the same size as input image, which is more effective for large scale cloud detection with larger receptive field, less parameters and lower compute complexity. Thirdly, context pooling is designed to amend the possible misjudgments. Visual and quantitative comparison experiments are conducted on several public cloud detection datasets, which indicates that our proposed method can accurately detect clouds under different conditions, which is more effective and accurate than the compared state-of-the-art methods.

show abstract

Cloud and Cloud Shadow Detection Based on Multiscale 3D-CNN for High Resolution Multispectral Imagery

Cited by 16 publications

References 40 publications

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

Light-Weight Cloud Detection Network for Optical Remote Sensing Images with Attention-Based DeeplabV3+ Architecture

ClouDet: A Dilated Separable CNN-Based Cloud Detection Framework for Remote Sensing Imagery

Contact Info

Product

Resources

About