A fusion algorithm for infrared and visible images based on saliency analysis and non-subsampled Shearlet transform

Zhang, Baohua; Lu, Xiaoqi; Pei, Haiquan; Zhao, Ying

doi:10.1016/j.infrared.2015.10.004

Cited by 83 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IR images are highly influenced by the external environment, such as light, fog, and smog. [ 1 , 2 ]. IR images are superior to VIS images in areas where the VIS image is invisible due to low-light conditions.…”

Section: Introductionmentioning

confidence: 99%

A New Deep Learning Based Multi-Spectral Image Fusion Method

Piao

Chen

Shin

2019

Entropy

View full text Add to dashboard Cite

In this paper, we present a new effective infrared (IR) and visible (VIS) image fusion method by using a deep neural network. In our method, a Siamese convolutional neural network (CNN) is applied to automatically generate a weight map which represents the saliency of each pixel for a pair of source images. A CNN plays a role in automatic encoding an image into a feature domain for classification. By applying the proposed method, the key problems in image fusion, which are the activity level measurement and fusion rule design, can be figured out in one shot. The fusion is carried out through the multi-scale image decomposition based on wavelet transform, and the reconstruction result is more perceptual to a human visual system. In addition, the visual qualitative effectiveness of the proposed fusion method is evaluated by comparing pedestrian detection results with other methods, by using the YOLOv3 object detector using a public benchmark dataset. The experimental results show that our proposed method showed competitive results in terms of both quantitative assessment and visual quality.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Deep Learning Based Multi-Spectral Image Fusion Method

Piao

Chen

Shin

2019

Entropy

View full text Add to dashboard Cite

show abstract

“…7 The super-pixel-based saliency analysis method is used to obtain the target region which leads to the focus areas' accurate extraction. 8 In recent years, many scholars have discovered that multi-scale transform (MST) may be a helpful tool for image fusion. The performance of the fusion result significantly depends on two aspects: MST method selection and effective fusion rules for different scales.…”

Section: Introductionmentioning

confidence: 99%

Microscopy image fusion algorithm based on saliency analysis and adaptive m-pulse-coupled neural network in non-subsampled contourlet transform domain

Yan

Liu

Chen

2017

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Microscopy image fusion, as a new item in related research field, has been extensively used in integrated-circuit defect detection and intaglio-plate-microstructure observation. In this article, a novel microscopy image fusion algorithm based on saliency analysis and adaptive m-pulse-coupled neural network in non-subsampled contourlet transform domain is proposed, in which each original image can be decomposed into a low-frequency subband and a series of high-frequency subbands. A new measurement technique based on image variance permutation entropy is designed for fusion of the low-frequency subbands, and a novel sum-modified Laplacian is chosen as external stimulus which motivates the adaptive m-pulse-coupled neural network for the high-frequency subbands. Yet, the linking strength of the m-pulse-coupled neural network is determined by five features of the saliency map. Then, the selection rules of different subbands are worked based on the corresponding weight measures. Finally, the fusion image is reconstructed via inverse non-subsampled contourlet transform. Experimental results reveal that the proposed algorithm achieves better fused image quality than other traditional representative ones in the aspects of objective evaluation and subjective visual.

show abstract

“…However, their weight map construction process can hardly exclude some other salient regions, which have no relation to the infrared target. Furthermore, Zhang et al [15] proposed a fusion algorithm for infrared and visible images based on saliency analysis and nonsubsampled shearlet transform. That super-pixel-based saliency analysis method is used to extract the salient regions.…”

Section: Introductionmentioning

confidence: 99%

Infrared and Visible Image Fusion based on Saliency Detection and Infrared Target Segment

Li¹,

Song²,

Peng³

2017

dtcse

View full text Add to dashboard Cite

Infrared and visible image fusion is significant to the overall detection and tracking performance of a video surveillance system. Considering the characteristics of infrared and visible images, the ideal fusion of the infrared and visual image should integrate the bright features of the infrared image, while preserving a considerable amount of background information of the visible image. However, current methods use inadequate information extraction. An efficient infrared and visible image fusion method is thus proposed in this paper based on saliency detection and infrared target segmentation. Firstly, an image descriptor, referred to as an image signature, is introduced. The saliency algorithm is implemented to obtain the infrared image region of interest. Secondly, an infrared target is segmented from the region of interest by adopting a thresholding method. Subsequently, the infrared target is added to the image, which is fused from the original infrared and visible image by known image fusion methods. The most remarkable advantage of the proposed method is that it can obtain a clear infrared target. To verify the proposed method, it was experimentally compared with several classic fusion algorithms. By subjectively comparing the fused results, it was demonstrated that the proposed method not only extracted the important infrared targets, but it also showed good visual quality retained in the background information.

show abstract

A fusion algorithm for infrared and visible images based on saliency analysis and non-subsampled Shearlet transform

Cited by 83 publications

References 20 publications

A New Deep Learning Based Multi-Spectral Image Fusion Method

A New Deep Learning Based Multi-Spectral Image Fusion Method

Microscopy image fusion algorithm based on saliency analysis and adaptive m-pulse-coupled neural network in non-subsampled contourlet transform domain

Infrared and Visible Image Fusion based on Saliency Detection and Infrared Target Segment

Contact Info

Product

Resources

About