Improving hyperspectral image classification by combining spectral, texture, and shape features

Mirzapour, Fardin; Ghassemian, Hassan

doi:10.1080/01431161.2015.1007251

Cited by 112 publications

(33 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The area covered comprises 512 lines by 217 samples with 224 bands. In previous studies, the reference noisy 45 37 M=600 M=70 bands are Band 1-3, 106-114,150-167,221-224 (Kang, Xiurui, and Luyan 2015;Makarau et al 2012;Mirzapour and Ghassemian 2015), and remain in this study. As before, the number of selected target pixels is set to M=1000.…”

Section: Salinas Datamentioning

confidence: 95%

An Automatic Bad Band Pre-Removal Method for Hyperspectral Imagery

Wang

Geng

2019

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

View full text Add to dashboard Cite

For most hyperspectral remote sensing applications, removing bad bands, such as water absorption bands, is a required preprocessing step. Currently, the commonly applied method is by visual inspection, which is very time-consuming and it is easy to overlook some noisy bands. In this study, we find an inherent connection between target detection algorithms and the corrupted band removal. As an example, for the matched filter (MF), which is the most widely used target detection method for hyperspectral data, we present an automatic MF-based algorithm for bad band identification.The MF detector is a filter vector, and the resulting filter output is the sum of all bands weighted by the MF coefficients. Therefore, we can identify bad bands only by using the MF filter vector itself, the absolute value of whose entry accounts for the importance of each band for the target detection. For a specific target of interest, the bands with small MF weights correspond to the noisy or bad ones. Based on this fact, we develop an automatic bad band preremoval algorithm by utilizing the average absolute value of MF weights for multiple targets within a scene. Experiments with three well known hyperspectral datasets show that our method can always identify the water absorption and other low signal-to-noise (SNR) bands that are usually chosen as bad bands manually.

show abstract

Section: Salinas Datamentioning

confidence: 95%

An Automatic Bad Band Pre-Removal Method for Hyperspectral Imagery

Wang

Geng

2019

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

View full text Add to dashboard Cite

show abstract

“…Commercial equipment for automatic optical sorting based on hyperspectral cameras can be found in the market. Although hyperspectral technologies can help characterizing the composition of metallic materials, current hyperspectral processing approaches involve poor characterization of the inherent variability of these materials and their visual appearance (optical texture, geometry, and pattern) of the particles [23]. Besides this, the high amount of data that is inherent to hyperspectral imaging implies slow data processing rate, which is not acceptable for real-time recycling applications [24][25][26].…”

Section: State Of the Artmentioning

confidence: 99%

Highly Evolvable E-waste Recycling Technologies and Systems

Copani

Picone

Colledani

et al. 2019

Factories of the Future

View full text Add to dashboard Cite

Materials recycling is a key process to close the loop of materials in the direction of circular economy. However, the variability of waste and the high volatility of the price of recovered materials are posing serious challenges to the current rigid design of mechanical recycling systems. This is particularly true for Waste Electric and Electronic Equipment (WEEE), whose volume is growing more than other waste streams in Europe due to the diffusion of electronic products and to their short technology cycles. This study is aimed at the development of new flexible recycling systems through the implementation of a Hyper Spectral Imaging system and a simulation model enabling the real-time characterisation of shredded particles and the dynamic optimisation of process parameters for efficient sorting. A hardware and software prototype was realised and tested at the De-and Re-manufacturing pilot plant of CNR-STIIMA. The positive economic impact of flexible recycling systems enabled by new technologies was assessed through scenario analysis.

show abstract

“…In the experiments, 20 water absorption and noisy bands (no. 104-108,150-163, and 220) are removed and the remaining 200 bands are used for the analysis [Mirzapour and Ghassemian, 2015]. Indian Pines scene contains 16 different land-cover classes, and a pseudo color image corresponds to different land cover classes are visually shown in (Figure. 5 (a)-(b)).…”

Section: Experimental Data Setsmentioning

confidence: 99%

Spectral-Spatial Classification of Hyperspectral Imagery Based on Stacked Sparse Autoencoder and Random Forest

Zhao

Wan

Zhao

et al. 2017

European Journal of Remote Sensing

View full text Add to dashboard Cite

It is of great interest in exploiting spectral-spatial information for hyperspectral image (HSI) classification at different spatial resolutions. This paper proposes a new spectral-spatial deep learning-based classification paradigm. First, pixel-based scale transformation and class separability criteria are employed to measure appropriate spatial resolution HSI, and then we integrate the spectral and spatial information (i.e., both implicit and explicit features) together to construct a joint spectral-spatial feature set. Second, as a deep learning architecture, stacked sparse autoencoder provides strong learning performance and is expected to exploit even more abstract and high-level feature representations from both spectral and spatial domains. Specifically, random forest (RF) classifier is first introduced into stacked sparse autoencoder for HSI classification, based on the fact that it provides better tradeoff among generalization performance, prediction accuracy and operation speed compared to other traditional procedures. Experiments on two real HSIs demonstrate that the proposed framework generates competitive performance.

show abstract

Improving hyperspectral image classification by combining spectral, texture, and shape features

Cited by 112 publications

References 30 publications

An Automatic Bad Band Pre-Removal Method for Hyperspectral Imagery

An Automatic Bad Band Pre-Removal Method for Hyperspectral Imagery

Highly Evolvable E-waste Recycling Technologies and Systems

Spectral-Spatial Classification of Hyperspectral Imagery Based on Stacked Sparse Autoencoder and Random Forest

Contact Info

Product

Resources

About