Technique for infrared and visible image fusion based on non-subsampled shearlet transform and spiking cortical model

Kong, Weiwei; Wang, Binghe; Lei, Yang

doi:10.1016/j.infrared.2015.02.008

Cited by 60 publications

(18 citation statements)

References 36 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The clarity of the image, also known as sharpness, is also assessed using an average gradient (AG) that measures the abrupt and texture information of the image, which is also a positive indicator. The formula is defined as follows: (14) At the same time, information entropy (IE) and cross entropy (CE) were chosen as the evaluation criteria for information quantity to evaluate the image. Information entropy (IE) is the amount of information contained in the image evaluation, information entropy is also a positive standard.…”

Section: Experimental Results and Analysis 41 Evaluation Criteriamentioning

confidence: 99%

“…Experimental results of infrared and visible images As shown in the figure, the fusion of infrared images and visible images is one that can skillfully express heat source information [14] and express scene information. From a subjective point of view, the above methods differ in their ability to extract source image information.…”

Section: Infrared and Visible Light Image Fusion Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Image Fusion Method Based on Non-subsampled Contourlet Wavelet Transform

Wang¹,

Gui-cang²,

Jia³

2018

JMI

View full text Add to dashboard Cite

Abstract. In order to solve the problem of the detail and the indistinct texture of the traditional image fusion algorithm, an image fusion method based on non-subsampled contourlet transform (NSCT) and self-adaptive correlation coefficient operator is proposed, which can effectively preserve the details of the fusion source image information and important structural information. Firstly, the low-pass subband and band-pass subband of the source image are decomposed by NSCT, and then the low-pass subband is fused by the fusion rule of the adaptive region variance, the band-pass subbands are fused by adaptive weights with coefficients gradient as the factor. Finally, through the NSCT inverse transformation to get the result image. The simulation results show that the adaptive algorithm is superior to the fusion method of human control fusion rule.

show abstract

Section: Experimental Results and Analysis 41 Evaluation Criteriamentioning

confidence: 99%

Section: Infrared and Visible Light Image Fusion Experimentsmentioning

confidence: 99%

Adaptive Image Fusion Method Based on Non-subsampled Contourlet Wavelet Transform

Wang¹,

Gui-cang²,

Jia³

2018

JMI

View full text Add to dashboard Cite

show abstract

“…As a way to solve this problem, image fusion keeps the spectral characteristics of low resolution multispectral images and gives it high spatial resolution. Kong et al proposed an infrared and visible image fusion method based on non-subsampled shearlet transform and a spiking cortical model [3]. Li et al [4] introduced a novelty image fusion method based on a sparse feature matrix.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Wheat Spike from Field Based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms

et al. 2018

View full text Add to dashboard Cite

Abstract:To obtain an accurate count of wheat spikes, which is crucial for estimating yield, this paper proposes a new algorithm that uses computer vision to achieve this goal from an image. First, a home-built semi-autonomous multi-sensor field-based phenotype platform (FPP) is used to obtain orthographic images of wheat plots at the filling stage. The data acquisition system of the FPP provides high-definition RGB images and multispectral images of the corresponding quadrats. Then, the high-definition panchromatic images are obtained by fusion of three channels of RGB. The Gram-Schmidt fusion algorithm is then used to fuse these multispectral and panchromatic images, thereby improving the color identification degree of the targets. Next, the maximum entropy segmentation method is used to do the coarse-segmentation. The threshold of this method is determined by a firefly algorithm based on chaos theory (FACT), and then a morphological filter is used to de-noise the coarse-segmentation results. Finally, morphological reconstruction theory is applied to segment the adhesive part of the de-noised image and realize the fine-segmentation of the image. The computer-generated counting results for the wheat plots, using independent regional statistical function in Matlab R2017b software, are then compared with field measurements which indicate that the proposed method provides a more accurate count of wheat spikes when compared with other traditional fusion and segmentation methods mentioned in this paper.

show abstract

“…The fusion algorithms are mainly multi-scale analysis, including laplacain pyramid transform(LP) [4],discrete wavelet(DWT) [5,6], stationary wavelet(SWT), dual-tree complex wavelet (DTCWT) [7], non-subsample contourlet transform(NSCT) [8][9][10], and non-subsample shearlet transform(NSST) [11][12], in order to overcome the drawback of the NSST, Liu et al proposed a new transform named complex discrete shearlet transform (CDST) [13][14][15], and multi-scale transform based on preserving edge is proposed [16].With the development of polarization imaging, the fusion of infrared polarization and intensity image become a concern. Due to advantage of multi-scale transform in the extraction of image feature, the fusion algorithms of two kinds of image are similar with infrared and visible images fusion, and mainly are multi-scale transform.…”

Section: Introductionmentioning

confidence: 99%

Infrared Polarization and Intensity Image Fusion Algorithm Based on Visual Brightness and Contrast Response Function

Zhang¹,

Yang²,

Ji³

et al. 2017

dtetr

View full text Add to dashboard Cite

Abstract. In this paper, a novel fusion algorithm is proposed based on visual brightness and contrast response function, and it can better retain the difference features between infrared and polarization images to improve the visual effect of fused image. Firstly, the source images are enhanced by fractional differentia operator to improve the edge, texture, and brightness. Second, the low frequency and high frequency features of enhanced infrared polarization and intensity image are described by local mean and local skewness. Thirdly, the visual brightness and contrast response function are constructed by using local mean and local skewness based on human visual model. Next, the source images are fused by using the visual brightness and contrast response function, and then two kinds of fused images that are respectively are the low frequency feature fused image and detail feature fused image are gotten. Finally, the fused image is gotten by superposition of the low frequency feature fused image and detail feature fused image. The experiment shows that the result obtained by proposed algorithm performs better in both subjective and objective qualities.

show abstract

Technique for infrared and visible image fusion based on non-subsampled shearlet transform and spiking cortical model

Cited by 60 publications

References 36 publications

Adaptive Image Fusion Method Based on Non-subsampled Contourlet Wavelet Transform

Adaptive Image Fusion Method Based on Non-subsampled Contourlet Wavelet Transform

Recognition of Wheat Spike from Field Based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms

Infrared Polarization and Intensity Image Fusion Algorithm Based on Visual Brightness and Contrast Response Function

Contact Info

Product

Resources

About