scispace - formally typeset
Open accessJournal ArticleDOI: 10.3390/RS13050930

Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning

02 Mar 2021-Remote Sensing (Multidisciplinary Digital Publishing Institute)-Vol. 13, Iss: 5, pp 930
Abstract: Deep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing challenge how to integrate spatial structure information into these frameworks to classify the HSI with limited training samples. In this study, an effective spectral-spatial HSI classification scheme is proposed based on superpixel pooling convolutional neural network with transfer learning (SP-CNN). The suggested method includes three stages. The first part consists of convolution and pooling operation, which is a down-sampling process to extract the main spectral features of an HSI. The second part is composed of up-sampling and superpixel (homogeneous regions with adaptive shape and size) pooling to explore the spatial structure information of an HSI. Finally, the hyperspectral data with each superpixel as a basic input rather than a pixel are fed to fully connected neural network. In this method, the spectral and spatial information is effectively fused by using superpixel pooling technique. The use of popular transfer learning technology in the proposed classification framework significantly improves the training efficiency of SP-CNN. To evaluate the effectiveness of the SP-CNN, extensive experiments were conducted on three common real HSI datasets acquired from different sensors. With 30 labeled pixels per class, the overall classification accuracy provided by this method on three benchmarks all exceeded 93%, which was at least 4.55% higher than that of several state-of-the-art approaches. Experimental and comparative results prove that the proposed algorithm can effectively classify the HSI with limited training labels.

... read more

Topics: Convolutional neural network (54%), Deep learning (53%), Pooling (53%) ... show more
Citations
  More

9 results found


Open accessJournal ArticleDOI: 10.3390/RS13122275
10 Jun 2021-Remote Sensing
Abstract: Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Therefore, this paper proposed an idea to enhance the generalization performance of CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that, in improving generalization performance, regularization also improves model calibration, which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation, which reveals improved performance as compared to the state-of-the-art models with overall 99.29%, 99.97%, and 100.0% accuracy for Indiana Pines, Pavia University, and Salinas dataset, respectively.

... read more

4 Citations


Open accessJournal ArticleDOI: 10.3390/RS13101922
14 May 2021-Remote Sensing
Abstract: This paper presents a correlation filter object tracker based on fast spatial-spectral features (FSSF) to realize robust, real-time object tracking in hyperspectral surveillance video. Traditional object tracking in surveillance video based only on appearance information often fails in the presence of background clutter, low resolution, and appearance changes. Hyperspectral imaging uses unique spectral properties as well as spatial information to improve tracking accuracy in such challenging environments. However, the high-dimensionality of hyperspectral images causes high computational costs and difficulties for discriminative feature extraction. In FSSF, the real-time spatial-spectral convolution (RSSC) kernel is updated in real time in the Fourier transform domain without offline training to quickly extract discriminative spatial-spectral features. The spatial-spectral features are integrated into correlation filters to complete the hyperspectral tracking. To validate the proposed scheme, we collected a hyperspectral surveillance video (HSSV) dataset consisting of 70 sequences in 25 bands. Extensive experiments confirm the advantages and the efficiency of the proposed FSSF for object tracking in hyperspectral video tracking in challenging conditions of background clutter, low resolution, and appearance changes.

... read more

Topics: Video tracking (68%), Hyperspectral imaging (60%)

4 Citations


Journal ArticleDOI: 10.1007/S10462-021-10018-Y
Wang Chunying1, Liu Baohua1, Liu Lipeng1, Zhu Yanjun1  +3 moreInstitutions (1)
Abstract: Hyperspectral imaging is a non-destructive, nonpolluting, and fast technology, which can capture up to several hundred images of different wavelengths and offer relevant spectral signatures. Hyperspectral imaging technology has achieved breakthroughs in the acquisition of agricultural information and the detection of external or internal quality attributes of the agricultural product. Deep learning techniques have boosted the performance of hyperspectral image analysis. Compared with traditional machine learning, deep learning architectures exploit both spatial and spectral information of hyperspectral image analysis. To scrutinize thoroughly the current efforts, provide insights, and identify potential research directions on deep learning for hyperspectral image analysis in agriculture, this paper presents a systematic and comprehensive review. Firstly, its applications in agriculture are summarized, include ripeness and component prediction, different classification themes, and plant disease detection. Then, the recent achievements are reviewed in hyperspectral image analysis from the aspects of the deep learning models and the feature networks. Finally, the existing challenges of hyperspectral image analysis based on deep learning are summarized and the prospects of future works are put forward.

... read more

4 Citations


Open accessJournal ArticleDOI: 10.1016/J.RSASE.2021.100643
Ali Shebl1, Ali Shebl2, Árpád Csámer1Institutions (2)
Abstract: Machine Learning Algorithms (MLAs) have recently introduced considerable lithologic mapping. Thus, this study scrutinizes the efficacy of Artificial Neural Network (ANN), Maximum Likelihood Classifier (MLC) and Support Vector Machine (SVM) over hybrid datasets including optical (Sentinel 2, ASTER, Landsat OLI and Earth-observing 1 Advanced Land Imager (ALI)), radar (Sentinel 1 and ALOS PALSAR), DEMs and their derivatives (Slope, and Aspect). The study aims to (1) monitor the effect of data dimensionality in enhancing categorization accuracy. (2) disclose the most efficient MLA and most powerful dataset in labeling rock units accurately. (3) highlight the impact of embedding topographical and radar data in lithologic classification. (4) outline the best relation between the number of training pixels and number of utilized bands, in delivering reliable allocation. To achieve these aims, we selected training and testing pixels meticulously, in concordance with a recently published geological map of the study area. We adopted a stacked vector approach for handling the implemented multi-sensor data. Results show that diversifying information sources raised the classification accuracy by approximately 10% for each classifier. SVM and MLC are much better than ANN. Slope is better than aspect and both are less qualified when compared to DEM. Sentinel 1 (C-band) and ALOS PALSAR (L-band) effects are not so different whatever the implemented polarization. Landsat OLI is less qualified in lithologic classification when compared to Sentinel 2, ASTER and ALI. The utilized training pixels should be at least 30N for (N) channels submitted to the classifiers.

... read more

Topics: Support vector machine (53%)

3 Citations


Open accessJournal ArticleDOI: 10.3390/RS13091772
01 May 2021-Remote Sensing
Abstract: Synthetic aperture radar (SAR) image interpretation has long been an important but challenging task in SAR imaging processing. Generally, SAR image interpretation comprises complex procedures including filtering, feature extraction, image segmentation, and target recognition, which greatly reduce the efficiency of data processing. In an era of deep learning, numerous automatic target recognition methods have been proposed based on convolutional neural networks (CNNs) due to their strong capabilities for data abstraction and mining. In contrast to general methods, CNNs own an end-to-end structure where complex data preprocessing is not needed, thus the efficiency can be improved dramatically once a CNN is well trained. However, the recognition mechanism of a CNN is unclear, which hinders its application in many scenarios. In this paper, Self-Matching class activation mapping (CAM) is proposed to visualize what a CNN learns from SAR images to make a decision. Self-Matching CAM assigns a pixel-wise weight matrix to feature maps of different channels by matching them with the input SAR image. By using Self-Matching CAM, the detailed information of the target can be well preserved in an accurate visual explanation heatmap of a CNN for SAR image interpretation. Numerous experiments on a benchmark dataset (MSTAR) verify the validity of Self-Matching CAM.

... read more

Topics: Feature extraction (57%), Feature (computer vision) (56%), Synthetic aperture radar (55%) ... show more

3 Citations


References
  More

55 results found


Open accessJournal ArticleDOI: 10.1109/TPAMI.2012.120
Radhakrishna Achanta1, Appu Shaji1, Kevin Smith2, Aurelien Lucchi  +2 moreInstitutions (2)
Abstract: Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.

... read more

Topics: Image segmentation (53%), Cluster analysis (52%)

6,470 Citations


Open accessJournal ArticleDOI: 10.1109/TASSP.1981.1163711
Abstract: Cubic convolution interpolation is a new technique for resampling discrete data. It has a number of desirable features which make it useful for image processing. The technique can be performed efficiently on a digital computer. The cubic convolution interpolation function converges uniformly to the function being interpolated as the sampling increment approaches zero. With the appropriate boundary conditions and constraints on the interpolation kernel, it can be shown that the order of accuracy of the cubic convolution method is between that of linear interpolation and that of cubic splines. A one-dimensional interpolation function is derived in this paper. A separable extension of this algorithm to two dimensions is applied to image data.

... read more

Topics: Bicubic interpolation (80%), Monotone cubic interpolation (77%), Interpolation (73%) ... show more

2,789 Citations


Open accessJournal ArticleDOI: 10.1155/2015/258619
Wei Hu1, Yangyu Huang1, Li Wei1, Fan Zhang1  +2 moreInstitutions (3)
30 Jul 2015-Journal of Sensors
Abstract: Recently, convolutional neural networks have demonstrated excellent performance on various visual tasks, including the classification of common two-dimensional images. In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain. More specifically, the architecture of the proposed classifier contains five layers with weights which are the input layer, the convolutional layer, the max pooling layer, the full connection layer, and the output layer. These five layers are implemented on each spectral signature to discriminate against others. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector machines and the conventional deep learning-based methods.

... read more

Topics: Deep learning (63%), Convolutional neural network (62%), Hyperspectral imaging (55%) ... show more

826 Citations


Journal ArticleDOI: 10.1109/TGRS.2016.2616355
Wei Li1, Guodong Wu1, Fan Zhang1, Qian Du2Institutions (2)
Abstract: The deep convolutional neural network (CNN) is of great interest recently. It can provide excellent performance in hyperspectral image classification when the number of training samples is sufficiently large. In this paper, a novel pixel-pair method is proposed to significantly increase such a number, ensuring that the advantage of CNN can be actually offered. For a testing pixel, pixel-pairs, constructed by combining the center pixel and each of the surrounding pixels, are classified by the trained CNN, and the final label is then determined by a voting strategy. The proposed method utilizing deep CNN to learn pixel-pair features is expected to have more discriminative power. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than the conventional deep learning-based method.

... read more

Topics: Pixel (54%), Hyperspectral imaging (53%), Feature extraction (53%) ... show more

452 Citations


Journal ArticleDOI: 10.1109/LGRS.2015.2482520
Chao Tao1, Hongbo Pan1, Yansheng Li2, Zhengrou Zou1Institutions (2)
Abstract: In this letter, different from traditional methods using original spectral features or handcraft spectral–spatial features, we propose to adaptively learn a suitable feature representation from unlabeled data. This is achieved by learning a feature mapping function based on stacked sparse autoencoder. Considering that hyperspectral imagery (HSI) is intrinsically defined in both the spectral and spatial domains, we further establish two variants of feature learning procedures for sparse spectral feature learning and multiscale spatial feature learning. Finally, we embed the learned spectral–spatial feature into a linear support vector machine for classification. Experiments on two hyperspectral images indicate the following: 1) the learned spectral–spatial feature representation is more discriminative for HSI classification compared to previously hand-engineered spectral–spatial features, especially when the training data are limited and 2) the learned features appear not to be specific to a particular image but general in that they are applicable to multiple related images (e.g., images acquired by the same sensor but varying with location or time).

... read more

Topics: Feature learning (65%), Feature (computer vision) (64%), Feature extraction (60%) ... show more

269 Citations


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20219