Automatic target detection in hyperspectral image processing: A review of algorithms

Poojary, Nagesh; Hasmitha, Dsouza; Puttaswamy, M R; Kumar, G. Hemantha

doi:10.1109/fskd.2015.7382255

Cited by 16 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is seen that the peak accuracy is saturated at the point when all the bands have been used for the classification. A similar trend has been seen over the many BS papers reported in the literature [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], which makes one speculate why the well-known bell shape of the accuracy-dimensionality curve predicted by Hughes [ 1 ], has not been observed from any experiments so far. Hughes analysis has shown that the theoretical accuracy of a model scales non-linearly with the dimensionality of the dataset: the accuracy should be improved when more spectral bands are utilized for the classification, and furthermore, increasing the dimensionality of the data for classification reduces the accuracy, especially when the training data size is kept constant.…”

Section: Resultssupporting

confidence: 80%

“…Hyperspectral imaging (HSI) that exploits both spectral and spatial features of the scene [ 1 , 2 ], has made it a powerful technique for applications such as geographical mapping [ 3 ], classifications [ 4 ], and target detections [ 5 , 6 ], in multidisciplinary fields of agricultural [ 7 ], food industry [ 8 ], medical [ 9 ], and security [ 10 ], sectors. The usefulness of HSI mainly stems from the very detailed spectral information of the scene that it provides; however, it is also one of the drawbacks of HSI for achieving a high degree of classification or detection accuracy when it has high spectral dimension.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the numerous amount of BS research in the field [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], the classification performances of these reported results are all exhibiting a ‘knee’-shaped accuracy-dimensionality curve, i.e., the accuracy of the classification increases steadily when more bands are utilized for the classification. Moreover, existing BS algorithms are all showing a maximum classification accuracy when all the spectral bands are utilized.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

et al. 2020

View full text Add to dashboard Cite

Despite the numerous band selection (BS) algorithms reported in the field, most if not all have exhibited maximal accuracy when more spectral bands are utilized for classification. This apparently disagrees with the theoretical model of the ‘curse of dimensionality’ phenomenon, without apparent explanations. If it were true, then BS would be deemed as an academic piece of research without real benefits to practical applications. This paper presents a spatial spectral mutual information (SSMI) BS scheme that utilizes a spatial feature extraction technique as a preprocessing step, followed by the clustering of the mutual information (MI) of spectral bands for enhancing the efficiency of the BS. Through the SSMI BS scheme, a sharp ’bell’-shaped accuracy-dimensionality characteristic that peaks at about 20 bands has been observed for the very first time. The performance of the proposed SSMI BS scheme has been validated through 6 hyperspectral imaging (HSI) datasets (Indian Pines, Botswana, Barrax, Pavia University, Salinas, and Kennedy Space Center (KSC)), and its classification accuracy is shown to be approximately 10% better than seven state-of-the-art BS schemes (Saliency, HyperBS, SLN, OCF, FDPC, ISSC, and Convolution Neural Network (CNN)). The present result confirms that the high efficiency of the BS scheme is essentially important to observe and validate the Hughes’ phenomenon in the analysis of HSI data. Experiments also show that the classification accuracy can be affected by as much as approximately 10% when a single ‘crucial’ band is included or missed out for classification.

show abstract

Section: Resultssupporting

confidence: 80%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This leads to a better discrimination among the different materials contained in the image, allowing hyperspectral imagery (HSI) to serve as a tool for the analysis of the surface of the Earth in many applications [26][27][28][29]. The analysis of HSIs involves a wide range of techniques, including classification [29,30], spectral unmixing [31][32][33][34], target and anomaly detection [35][36][37][38]. In recent years, HSI classification has become a popular research topic in the remote sensing field [39].…”

Section: Hyperspectral Image Classificationmentioning

confidence: 99%

Deep&Dense Convolutional Neural Network for Hyperspectral Image Classification

et al. 2018

View full text Add to dashboard Cite

Deep neural networks (DNNs) have emerged as a relevant tool for the classification of remotely sensed hyperspectral images (HSIs), with convolutional neural networks (CNNs) being the current state-of-the-art in many classification tasks. However, deep CNNs present several limitations in the context of HSI supervised classification. Although deep models are able to extract better and more abstract features, the number of parameters that must be fine-tuned requires a large amount of training data (using small learning rates) in order to avoid the overfitting and vanishing gradient problems. The acquisition of labeled data is expensive and time-consuming, and small learning rates forces the gradient descent to use many small steps to converge, slowing down the runtime of the model. To mitigate these issues, this paper introduces a new deep CNN framework for spectral-spatial classification of HSIs. Our newly proposed framework introduces shortcut connections between layers, in which the feature maps of inferior layers are used as inputs of the current layer, feeding its own output to the rest of the the upper layers. This leads to the combination of various spectral-spatial features across layers that allows us to enhance the generalization ability of the network with HSIs. Our experimental results with four well-known HSI datasets reveal that the proposed deep&dense CNN model is able to provide competitive advantages in terms of classification accuracy when compared to other state-of-the-methods for HSI classification.

show abstract

“…Finally, HSI constructs a three-dimensional data T ∈ R I×J×λ . Once the HSI data are obtained, they can be used in many applications, such as detecting and identifying objects at a distance in environmental monitoring [3] or medical image processing [4], finding anomaly in automatic visual inspection [5], or detecting and identifying targets of interest [6,7]. However, as the area of the target scene I × J or the number of quantized spectra λ increase, the manipulation of T demands prohibitively large computational resources and storage space.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Compressive Hyperspectral Imaging Algorithm Based on Sequential Computations of Alternating Least Squares

Lee

2019

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral imaging is widely used to many applications as it includes both spatial and spectral distributions of a target scene. However, a compression, or a low multilinear rank approximation of hyperspectral imaging data, is required owing to the difficult manipulation of the massive amount of data. In this paper, we propose an efficient algorithm for higher order singular value decomposition that enables the decomposition of a tensor into a compressed tensor multiplied by orthogonal factor matrices. Specifically, we sequentially compute low rank factor matrices from the Tucker-1 model optimization problems via an alternating least squares approach. Experiments with real world hyperspectral imaging revealed that the proposed algorithm could compute the compressed tensor with a higher computational speed, but with no significant difference in accuracy of compression compared to the other tensor decomposition-based compression algorithms.

show abstract

Automatic target detection in hyperspectral image processing: A review of algorithms

Cited by 16 publications

References 35 publications

Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

Deep&Dense Convolutional Neural Network for Hyperspectral Image Classification

An Efficient Compressive Hyperspectral Imaging Algorithm Based on Sequential Computations of Alternating Least Squares

Contact Info

Product

Resources

About