Saurabh Prasad

Prof. Saurabh Prasad


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 November 2017 in IEEE Transactions on Image Processing
Verified
Journal Article
Open access
HWHao Wu
Hao Wu
SPSaurabh Prasad
Saurabh Prasad
Deep learning has gained popularity in a variety of computer vision tasks. Recently, it has also been successfully applied for hyperspectral image classification tasks. Training deep neural networks such as a convolutional neural network (CNN) for classification requires a large number of labeled samples. However, in remote sensing applications, we usually only have a small amount of labeled data for training because they are expensive to collect, although we still have abundant unlabeled data. In this paper, we propose semi-supervised deep learning for hyperspectral image classification – our approach uses limited labeled data and abundant unlabeled data to train a deep neural network. More specifically, we use deep convolutional recurrent neural networks (CRNN) for hyperspectral image classification by treating each hyperspectral pixel as a spectral sequence. In the proposed semi-supervised learning framework, the abundant unlabeled data are utilized with their pseudo labels (cluster labels). We propose to use all the training data together with their pseudo labels to pre-train a deep CRNN, and then fine-tune using the limited available labeled data. Further, to utilize spatial information in the hyperspectral images, we propose a constrained Dirichlet process mixture model (C-DPMM), a non-parametric Bayesian clustering algorithm, for semi-supervised clustering which includes pairwise must-link and cannot-link constraints – this produces high-quality pseudo-labels, resulting in improved initialization of the deep neural network. We also derived a variational inference (VI) model for the C-DPMM for efficient inference. Experimental results with real hyperspectral image datasets demonstrate that the proposed semi-supervised method outperforms state-of-the-art supervised and semi-supervised learning methods for hyperspectral classification.

31 May 2019 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
Yonghao XuYonghao Xu
Yonghao Xu
BDBo Du
Bo Du
Liangpei ZhangLiangpei Zhang
Liangpei Zhang
DCDaniele Cerra
Daniele Cerra
MPMiguel Pato
Miguel Pato
BSBertrand Le Saux
Bertrand Le Saux
This paper presents the scientific outcomes of the 2018 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2018 Contest addressed the problem of urban observation and monitoring with advanced multi-source optical remote sensing (multispectral LiDAR, hyperspectral imaging, and very high-resolution imagery). The competition was based on urban land use and land cover classification, aiming to distinguish between very diverse and detailed classes of urban objects, materials, and vegetation. Besides data fusion, it also quantified the respective assets of the novel sensors used to collect the data. Participants proposed elaborate approaches rooted in remote-sensing, and also in machine learning and computer vision, to make the most of the available data. Winning approaches combine convolutional neural networks with subtle earth-observation data scientist expertise.

21 March 2017 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HWHao Wu
Hao Wu
SPSaurabh Prasad
Saurabh Prasad
Deep neural networks, such as convolutional neural networks (CNN) and stacked autoencoders, have recently been successfully used to extract deep features for hyperspectral data classification. Recurrent neural networks (RNN) are another type of neural networks, which are widely used for sequence analysis because they are constructed to extract contextual information from sequences by modeling the dependencies between different time steps. In this paper, we study the ability of RNN for hyperspectral data classification by extracting the contextual information from the data. Specifically, hyperspectral data are treated as spectral sequences, and an RNN is used to model the dependencies between different spectral bands. In addition, we propose to use a convolutional recurrent neural network (CRNN) to learn more discriminative features for hyperspectral data classification. In CRNN, a few convolutional layers are first learned to extract middle-level and locally-invariant features from the input data, and the following recurrent layers are then employed to further extract spectrally-contextual information from the features generated by the convolutional layers. Experimental results on real hyperspectral datasets show that our method provides better classification performance compared to traditional methods and other state-of-the-art deep learning methods for hyperspectral data classification.

27 January 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
KSKazem Safari
Kazem Safari
SPSaurabh Prasad
Saurabh Prasad
Demetrio LabateDemetrio Labate
Demetrio Labate
Hyperspectral imagery (HSI) has emerged as a highly successful sensing modality for a variety of applications ranging from urban mapping to environmental monitoring and precision agriculture. Despite the efforts made by the scientific community, developing reliable algorithms of HSI classification remains a challenging problem, especially for high-resolution HSI data where there is often larger intraclass variability combined with a scarcity of the ground-truth data and class imbalance. In recent years, deep neural networks have emerged as a promising strategy for problems of HSI classification where they have shown remarkable potential for learning joint spectral–spatial features efficiently via backpropagation. In this letter, we propose a deep learning strategy for HSI classification that combines different convolutional neural networks, especially designed to efficiently learn joint spatial–spectral features over multiple scales. Our method achieves an overall classification accuracy of 66.73% on the 2018 IEEE GRSS hyperspectral data set—a high-resolution data set that includes 20 urban land-cover and land-use classes.

22 April 2016 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Closed access
XZXiong Zhou
Xiong Zhou
SPSaurabh Prasad
Saurabh Prasad
MCMelba M. Crawford
Melba M. Crawford
Active learning (AL) has been shown to be effective for strategic selection of training samples to support classification of hyperspectral imagery. It is well understood that the performance of classification can further be improved by utilizing the spatial information in hyperspectral images. In this paper, we propose a new wavelet-based multiview AL approach for hyperspectral image classification. Specifically, a three-dimensional redundant wavelet transform (3D-RDWT) is used to generate multiple views that are then integrated in a multiview AL framework. The spatial features generated via 3D-RDWT not only provide sufficient views for multiview AL, but are also less sensitive to additive noise. Within this framework, we also propose new query criteria that result in effective AL. An intersection-based query criterion is proposed to reduce the redundancy within the contention pool. A singularity-based criterion is also used to identify informative pixels by taking spatial information into account when selecting samples. The proposed method is evaluated on four real-world hyperspectral datasets, and the experimental results demonstrate the efficacy of the proposed method compared with traditional AL methods.

23 June 2017 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
XZXiong Zhou
Xiong Zhou
SPSaurabh Prasad
Saurabh Prasad
Classification of hyperspectral images has recently gained significant popularity due to both the development of remote sensing technologies and the advances in image analysis approaches. One crucial step to achieve accurate classification is to acquire sufficient high-quality training data, which is often a time-consuming and expensive process. To alleviate this burden, in this letter, we propose an active and semisupervised learning (SSL) approach that utilizes morphological component analysis (MCA) for classification of hyperspectral images. First, the original hyperspectral data are decomposed into its morphological components via MCA. In each feature domain, the active learning (AL) and SSL are combined to enlarge the training data set based on superpixels. Finally, decision fusion is carried out to integrate the predictions from the two components. The proposed method is tested on both benchmark and real world application hyperspectral data sets. Experimental results indicate that the proposed method can lead to a better classification with respect to the conventional AL approaches.