MugNet: Deep learning for hyperspectral image classification using limited samples

Pan, Bin; Xu, Xia

doi:10.1016/j.isprsjprs.2017.11.003

Cited by 220 publications

(98 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A trainable block, called the field-of-view (FoV), is proposed in [28] to boost the performance of the FCN. With the successful applications of U-Net in the pixel-wise area labellings, most current models [28][29][30][31][32][33] use encoder-decoder architectures. The mutation models enhance the buildings' semantic boundaries Remote Sens.…”

mentioning

confidence: 99%

“…Audebert et al [32] proposed an efficient multi-scale approach to leverage both a large spatial context and the high-resolution data and investigated the early and late fusion of Lidar and multispectral data to cover the scale variance of buildings from different areas. In [33,34], the extra geographical information (DSM, DEM, and Lidar images) are fed into a carefully designed FCN, together with high-resolution RGB images, and the results indicate that abundant features always lead to sharper predicted building boundaries. Moreover, post-processing methods, such as Guider Filter [1] and Conditional Random Field (CRF) methods [35,36], have been heavily researched and attempted to preserve the structure consistency between the building predictions and the original images.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Web-Net: A Novel Nest Networks with Ultra-Hierarchical Sampling for Building Extraction from Aerial Imageries

et al. 2019

View full text Add to dashboard Cite

How to efficiently utilize vast amounts of easily accessed aerial imageries is a critical challenge for researchers with the proliferation of high-resolution remote sensing sensors and platforms. Recently, the rapid development of deep neural networks (DNN) has been a focus in remote sensing, and the networks have achieved remarkable progress in image classification and segmentation tasks. However, the current DNN models inevitably lose the local cues during the downsampling operation. Additionally, even with skip connections, the upsampling methods cannot properly recover the structural information, such as the edge intersections, parallelism, and symmetry. In this paper, we propose the Web-Net, which is a nested network architecture with hierarchical dense connections, to handle these issues. We design the Ultra-Hierarchical Sampling (UHS) block to absorb and fuse the inter-level feature maps to propagate the feature maps among different levels. The position-wise downsampling/upsampling methods in the UHS iteratively change the shape of the inputs while preserving the number of their parameters, so that the low-level local cues and high-level semantic cues are properly preserved. We verify the effectiveness of the proposed Web-Net in the Inria Aerial Dataset and WHU Dataset. The results of the proposed Web-Net achieve an overall accuracy of 96.97% and an IoU (Intersection over Union) of 80.10% on the Inria Aerial Dataset, which surpasses the state-of-the-art SegNet 1.8% and 9.96%, respectively; the results on the WHU Dataset also support the effectiveness of the proposed Web-Net. Additionally, benefitting from the nested network architecture and the UHS block, the extracted buildings on the prediction maps are obviously sharper and more accurately identified, and even the building areas that are covered by shadows can also be correctly extracted. The verified results indicate that the proposed Web-Net is both effective and efficient for building extraction from high-resolution remote sensing images.The building extraction task has drawn the attention of researchers over recent years. Before the common application of deep learning, there were massive machine learning models that tried to handle this task. In general, the pixel-wise labelling model consists of two sub-modules: the feature descriptor for extracting the semantic features from the original images and the pixel-wise classifier for determining the classes of the pixels. Some carefully designed feature descriptors were widely used in early approaches. Tuermer et al. [4] firstly used the histogram of gradient (HOG) feature descriptor in remote sensing for detecting vehicles. The Haar feature is applied in [5] for detecting buildings' outlines and determining the location of buildings' corners. Additionally, Yang et al. [6] applied the Scale-invariant feature transform [7] (SIFT) for classifying objects in remote sensing images. Unlike the artificially designed feature descriptors, the trainable models are the mainstream for the choices of classifiers....

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Web-Net: A Novel Nest Networks with Ultra-Hierarchical Sampling for Building Extraction from Aerial Imageries

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Some studies lightened the network by utilizing the 1×1 convolutional layers [14], [15]. [16] reduced the parameters by designing a simplified four layers network without hyperparameters, which applied an ensemble manner to utilize spatial-spectral information from hyperspectral data using 20 labeled samples per class. However, a deeper network with more parameters is expected to have a better performance.…”

Section: Introductionmentioning

confidence: 99%

Multitask Deep Learning With Spectral Knowledge for Hyperspectral Image Classification

Liu

Shi

2020

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

In this letter, we propose a multitask deep learning method for classification of multiple hyperspectral data in a single training. Deep learning models have achieved promising results on hyperspectral image classification, but their performance highly rely on sufficient labeled samples, which are scarce on hyperspectral images. However, samples from multiple data sets might be sufficient to train one deep learning model, thereby improving its performance. To do so, we trained an identical feature extractor for all data, and the extracted features were fed into corresponding softmax classifiers. Spectral knowledge was introduced to ensure that the shared features were similar across domains. Four hyperspectral data sets were used in the experiments. We achieved higher classification accuracies on three data sets (Pavia University, Pavia Center, and Indian Pines) and competitive results on the Salinas Valley data compared with the baseline. Spectral knowledge was useful to prevent the deep network from overfitting when the data shared similar spectral response. The proposed method successfully utilized samples from multiple data sets to increase its performance.

show abstract

“…In recent years, Convolutional Neural Network (CNN) [5] has played a very important role in the remote sensing field for image classification, detection, description and segmentation [6][7][8][9][10][11][12], and it also has been widely used in many other fields [13][14][15][16]. CNN constructs multiple layers to learn high-level image features with better discrimination and robustness, as opposed to that in traditional methods [17][18][19], where features have to be handcrafted.…”

Section: Introductionmentioning

confidence: 99%

Automatic Raft Labeling for Remote Sensing Images via Dual-Scale Homogeneous Convolutional Neural Network

Shi

Zou

et al. 2018

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Raft-culture is a way of utilizing water for farming aquatic product. Automatic raft-culture monitoring by remote sensing technique is an important way to control the crop's growth and implement effective management. This paper presents an automatic pixel-wise raft labeling method based on fully convolutional network (FCN). As rafts are always tiny and neatly arranged in images, traditional FCN method fails to extract the clear boundary and other detailed information. Therefore, a homogeneous convolutional neural network (HCN) is designed, which only consists of convolutions and activations to retain all details. We further design a dual-scale structure (DS-HCN) to integrate higher-level contextual information for accomplishing sea-land segmentation and raft labeling at the same time in a uniform framework. A dataset with Gaofen-1 satellite images was collected to verify the effectiveness of our method. DS-HCN shows a satisfactory performance with a better interpretability and a more accurate labeling result.

show abstract

MugNet: Deep learning for hyperspectral image classification using limited samples

Cited by 220 publications

References 53 publications

Web-Net: A Novel Nest Networks with Ultra-Hierarchical Sampling for Building Extraction from Aerial Imageries

Web-Net: A Novel Nest Networks with Ultra-Hierarchical Sampling for Building Extraction from Aerial Imageries

Multitask Deep Learning With Spectral Knowledge for Hyperspectral Image Classification

Automatic Raft Labeling for Remote Sensing Images via Dual-Scale Homogeneous Convolutional Neural Network

Contact Info

Product

Resources

About